RMSE = 496.35 kgha , MAE = 326.40 kgha
Acc: Accuracy: CA: Conservation Agriculture; CI: Crop Indices; CEC: Cation Exchange Capacity; CCC: Concordance Correlation Coefficient; DOY: Day Of Year; EC: Electrical Conductivity; HD: Heading Date; HDM: Heading Date to Maturity; K: Potassium; Mg: Magnesium; N: Nitrogen; OLI: Operational Land Imager; P: Phosphorus; RGB: Red-Green-Blue; S: Sulphur; SOM: Soil Organic Matter; SPAD: Soil and Plant Analyzer Development; STI: Soil Texture Information; STD: Standard Deviation; UAV: Unmanned Aerial Vehicle; UGV: Unmanned Ground Vehicle.
Crop Management: Disease Detection.
Ref | Crop | Input Data | Functionality | Models/Algorithms | Best Output |
---|---|---|---|---|---|
[ ] | Various crops | RGB images | Detection and diagnosis of plant diseases | CNN | Acc = 99.53% |
[ ] | Melon | Fluorescence, thermal images | Detection of Dickeya dadantii in melon plants | LR, SVM, ANN | ANN: Whole leaves: Acc = 96%; F1 score = 0.99 |
[ ] | Tomato | RGB images | Recognition of 10 plant diseases and pests in tomato plants | CNN | Recognition rate = 96% |
[ ] | Avocando | Hyperspectral images | Detection of nitrogen and iron deficiencies and laurel wilt disease in avocando | DT, MLP | MLP: Detection at early stage: Acc = 100% |
[ ] | Maize | RGB images | Examination of nine factors affecting disease detection in maize fields | CNN | Acc values: (1) Original dataset: 76%; Background removed: 79%; (2) Subdivided (full): 87%; (3) Subdivided (reduced): 81% |
[ ] | Milk thistle | Spectral measurements form spectroradiometer | Identification of Microbotryum silybum in milk thistle plants | MLP-ARD | Acc = 90.32% |
[ ] | Tomato | Spectral measurements form spectroradiometer | Detection of leaf diseases (target, bacterial spots and late blight) in tomato | KNN | Acc values: (1) Healthy leaves: 100%, (2) Asymptomatic: 100%, (3) Early stage: 97.8%, (4) Late stage: 100% |
[ ] | Maize | RGB images | Identification of eight types of leaf diseases in maize | CNN | (1) GoogLeNet: Acc = 98.9%; (2) Cifar10: Acc = 98.8% |
[ ] | Various crops | RGB images | Identification of six plant leaf diseases | RBFN | (1) Early blight: Acc = 0.8914; (2) Common rusts: Acc = 0.8871 |
[ ] | Citrus | RGB images | Detection and classification of citrus diseases | SVM | Acc values: 1st dataset: 97%; 1st and 2nd dataset: 89%; 3rd dataset: 90.4% |
[ ] | Grape | Multispectral images from UAV | Identification of infected areas | CNN | (1) Color space YUV: Acc = 95.84%; (2) Color space YUV and ExGR: Acc = 95.92% |
[ ] | Soybeean | RGB images | Detection and classification of three leaf diseases in soybeans | SVM | (1) Healthy: Acc = 82%; (2) Downy mildew: Acc = 79%; (3) Frog eye: Acc = 95.9%; (4) Septoria leaf blight: Acc = 90% |
[ ] | Millet | RGB images | Identification of fungal disease (mildew) in pearl millet | CNN | Acc = 95.00%, Precision = 90.50%, Recall = 94.50%, F1 score = 91.75% |
[ ] | Maize | RGB images from UAV | Detection of northern leaf blight in maize | CNN | Acc = 95.1% |
[ ] | Wheat | RGB images from UAV | Classification of helminthosporium leaf blotch in wheat | CNN | Acc = 91.43%, |
[ ] | Avocado | RGB images, multispectral images | Detection of laurel wilt disease in healthy and stressed avocado plants in early stage | MLP, KNN | Healthy vs. Nitrogen deficiency using 6 bands images: (1) MLP: Acc = 98%; (2) KNN: Acc = 86% |
[ ] | Basil | RGB images | Identification and classification of five types of leave diseases in four kinds of basil leaves | DT, RF, SVM, AdaBoost, GLM, ANN, NB, KNN, LDA | RF: Acc = 98.4% |
[ ] | Various crops | RGB images | Identification of several diseases on leaves | CNN | Acc values: (1) Healthy: 89%; (2) Mildly diseased: 31%; (3) Moderately diseased: 87%; (4) Severely diseased: 94% |
[ ] | Tea | RGB images from UAV | Identification of tea red Scab, tea leaf blight and tea red leaf spot diseases in tea leaves | SVM, DT, RF, CNN | CNN: Acc values: (1) tea red Scab: 0.7; (2) tea leaf blight: 1.0; (3)tea red leaf spot: 1.0 |
[ ] | Wheat | Hyperspectral images from UAV | Detection of yellow rust in wheat plots | CNN | Acc = 0.85 |
[ ] | Grape | RGB images | Detection of grapevine yellows in red grapes | CNN | Sensitivity = 98.96% Specificity = 99.40% |
[ ] | Maize | RGB images from UAV | Detection of northern leaf blight in maize | CNN | Acc = 0.9979, F1 score = 0.7153 |
[ ] | Sugar beet | RGB images | Detection and classification of diseased leaf spots in sugar beet | CNN | Acc = 95.48% |
[ ] | Various crops | RGB images | Identification of various plant leaf diseases | CNN | Acc = 96.46% |
[ ] | Strawberry | RGB images | Detection of powdery mildew in strawberry leaves | LDA | (1) Artificial lighting conditions: recall = 95.26%, precision = 95.45%, F1 score = 95.37%; (2) Natural lighting conditions: recall = 81.54%, precision = 72%, F1 score = 75.95% |
[ ] | Various different crops | RGB images | Detection of diseased plants | DL | Acc = 93.67% |
[ ] | Citrus | Hyperspectral images from UAV | Detection of canker disease on leaves and immature fruits | RBFN, KNN | RBFN: Acc values: (a) asymptomatic: 94%, (b) early stage: 96%, (c) late stage: 100% |
[ ] | Grape | RGB images | Detection of diseased vine on leaves | SVM | Acc = 95% |
[ ] | Wheat | RGB images | Identification of three leaf diseases in wheat | CNN | Acc values: (1) Septoria: 100%; (2) Tan Spot: 99.32%; (3) Rust: 99.29% |
[ ] | Grape | Spectral measurements form spectroradiometer | Classification of Flavescence dorée disease in grapevines | SVM, LDA | SVM: Acc = 96% |
[ ] | Papaya | RGB images | Recognition of five papaya diseases | SVM | Acc = 90%, Precision = 85.6% |
[ ] | Rice | RGB images | Recognition and classification of rice infected leaves | KNN, ANN | ANN: Acc = 90%, Recall = 88% |
[ ] | Tomato | Hyperspectral images from UAV | Detection of bacterial spot and target spot on tomato leaves | MLP, STDA | MLP: Acc values: (a) bacterial spot: 98%, (b) target spot: 97% |
[ ] | Squash | Hyperspectral images from UAV and laboratory measurements | Classification of powdery mildew in squash | RBFN | Acc values: (1) Laboratory: Asymptomatic: 82%, Late stage: 99%; (2) Field conditions: Early stage: 89%, Late disease stage: 96% |
[ ] | Tomato | Hyperspectral images from UAV and laboratory measurements | Detection of bacterial spot and target spot on tomato leaves | RBFN, STDA | Field conditions: Acc values: (a) Healthy vs. BS: 98%, (b) Healthy vs. TS: 96%, (c) Healthy vs. TYLC: 100% |
[ ] | Tomato | RGB images | Identification of various diseases in tomato | CNN | Acc values: (1) PV dataset: 98.4%; (2) 2nd dataset: 98.7%; (3) Field data: 86.27% |
[ ] | Walnut | RGB images | Identification of anthracnose infected leaves | CNN | Acc values: (1) RGB: 95.97%; (2) Grayscale: 92.47%; (3) Fast Fourier: 92.94% |
[ ] | Various crops | RGB images | Classification of infected leaves | DBN | Acc = 0.877, Sensitivity = 0.862, Specificity = 0.877 |
[ ] | Grape | Multispectral images from UAV | Detection of Mildew disease in vineyards | CNN | Acc values: (1) Grapevine-level: 92%; (2) Leaf level: 87% |
[ ] | Rice | RGB images, videos | Video detection of brown spot, stem borer and sheath blight in rice | CNN | (1) Brown spot: Recall = 75.0%, Precision = 90.0%; (2) Stem borer: Recall = 45.5%, Precision = 71.4%; (3) Sheath blight: Recall = 74.1%, Precision = 90.9% |
[ ] | Cassava | RGB images | Detection and classification of diseased leaves of fine-grain cassava | CNN | Acc = 93% |
[ ] | Banana | Satellite spectral data, Multispectral images from UAV, RGB images from UAV | Detection of banana diseases in different African landscapes | RF, SVM | RF: Acc = 97%, omissions error = 10%; commission error = 10%; Kappa coefficient = 0.96 |
[ ] | Tomato | RGB images | Detection of early blight, leaf mold and late blight on tomato leaves | CNN | Acc = 98% |
[ ] | Pepper | Spectral reflectance at 350–2500 nm | Detection of fusarium disease in pepper leaves | ANN, NB, KNN | ΚNN: Average success rate = 100% |
[ ] | Tomato | Spectral measurements form spectroradiometer | Detection of fusarium disease on pepper leaves | CNN | Acc = 98.6% |
[ ] | Citrus | Multispectral images from UAV | Detection of citrus greening in citrus orchards | SVM, KNN, MLR, NB, AdaBoost, ANN | AdaBoost: Acc = 100% |
[ ] | Soybean | RGB images | Prediction of charcoal rot disease in soybean | GBT | Sensitivity = 96.25%, specificity = 97.33% |
[ ] | Wheat | RGB images from UAV | Detection of wheat lodging | RF, CNN, SVM | CNN: Acc = 93% |
[ ] | Tomato | Weather data | Prediction of powdery mildew disease in tomato plants | ELM | Acc = 89.19%, AUC = 88.57% |
[ ] | Soybean | RGB images | Diagnosis of soybean leaf diseases | CNN | Acc = 98.14% |
[ ] | Potato | RGB images | Identification of early and late blight disease | NB, KNN, SVM | SVM: Average Acc = 99.67% |
[ ] | Various crops | RGB images | Quantification of uncertainty in detection of plant diseases | BDL | Mean softmax probability values: (1) Healthy: 0.68; (2) Non-Healthy: 0.72; |
[ ] | Coffee | Satellite spectral data | Identification of coffee berry necrosis via satellite imagery | MLP, RF, NB | NB: Acc = 0.534 |
[ ] | Tomato | RGB images | Recognition of blight, powdery mildew, leaf mold fungus and tobacco mosaic virus diseases | CNN | Faster RCNN: mAP = 97.01% |
[ ] | Maize | RGB images | Diagnosis of northern leaf blight, gray leaf spot, and common rust diseases | CNN | Acc = 98.2%; macro average precision = 0.98 |
[ ] | Grape | RGB images | Detection of black measles, black rot, leaf blight and mites on leaves | CNN | mAP = 81.1% |
[ ] | Grape | Weather data, expert input (disease incidence form visual inspection) | Forecasting downy mildew in vineyards | GLM, LASSO, RF, GB | GB: AUC = 0.85 |
[ ] | Maize | RGB images | Detection of northern leaf blight in maize | CNN | mAP = 91.83% |
[ ] | Onion | RGB images | Detection of downy mildew symptoms in onions field images | WSL | [email protected] = 74.1–87.2% |
[ ] | Coffee | RGB images | Detection of coffee leaf rust via remote sensing and wireless sensor networks | CNN | F1 score = 0.775, -value = 0.231 |
[ ] | Tomato | Weather data, multispectral images captured from UAV | Detection of late blight disease | CNN | Acc values: AlexNet: (1) Transfer learning: 89.69%; (2) Feature extraction: 93.4%, |
[ ] | Rice | RGB images | Detection of brown rice planthopper | CNN | Average recall rate = 81.92%, average Acc = 94.64% |
[ ] | Grape | UAV multispectral images, depth map information | Detection of vine diseases | CNN | VddNet: Accuracy = 93.72% |
[ ] | Apple | RGB images | Identification of apple leaf diseases (S, FS, CR) | CNN | Improved VGG16: Acc = 99.40%(H), 98.04% (S), 98.33%(FS), 100%(CR) |
[ ] | Cotton | UAV multispectral images | Disease classification of cotton root rot | KM, SVM | KM: Acc = 88.39%, Kappa = 0.7198 |
Acc: Accuracy; AUC: Area Under Curve; CR: Cedar Rust; ExGR: Excess Green Minus Excess Red; FS: Frogeye Spot; H: Healthy; mAP: mean Average Precision; RGB: Red-Green-Blue; S: Scab; TYLC: Tomato Yellow Leaf Curl; UAV: Unmanned Aerial Vehicle; VddNet: Vine Disease Detection Network.
Crop Management: Weed Detection.
Ref | Input Data | Functionality | Models/Algorithms | Best Output |
---|---|---|---|---|
[ ] | RGB images | Classification of thinleaf (monocots), broa leaf (dicots) weeds | AdaBoost with NB | Acc values: (1) Original dataset: 98.40%; (2) expanded dataset: 94.72% |
[ ] | RGB images from UAV | Detection of weeds in bean, spinach fields | CNN | Acc values: (1) Bean field: 88.73%; (2) Spinach field: 94.34% |
[ ] | RGB images | Detection of four weed species in sugar beet fields | SVN, ANN | Overall Acc: SVM: 95.00%; Weed classification: SVM: 93.33%; Sugar beet plants: SVM: 96.67% |
[ ] | RGB images from UAV, multispectral images | Detection of Gramineae weed in rice fields | ANN | Best system: 80% < M/M < 108%, 70% < MP < 85% |
[ ] | RGB images | Classification of crops (three species) and weeds (nine species) | CNN | Average Acc: 98.21±0.55% |
[ ] | Multispectral and RGB images from UAV | Weed mapping between and within crop rows, (1) cotton; (2) sunflower | RF | Weed detection Acc: (1) Cotton: 84% (2) Sunflower: 87.9% |
[ ] | Hyperspectral images | Recognition of three weed species in maize crops | RF | Mean correct classification rate: (1) Zea mays: 1.0; (2) Convolvulus arvensis: 0.789; Rumex: 0.691; Cirsium arvense 0.752 |
[ ] | RGB images from UAV | Detection of weeds in early season maize fields | RF | Overall Acc = 0.945, Kappa = 0.912 |
[ ] | RGB images from UAV | Weed mapping and prescription map generation in rice field | FCN | Overall Acc = 0.9196, mean intersection over union (mean IU) = 0.8473 |
[ ] | Handheld multispectral data | Weed detection in maize and sugar beet row-crops with: (1) spectral method; (2) spatial; (3) both methods | SVM | Mean detection rate: (1) spectral method: 75%; (2) spatial: 79%; (3) both methods: 89% |
[ ] | Multispectral images from UAV | Development of Weed/crop segmentation, mapping framework in sugar beet fields | DNN | AUC: (1) background: 0.839; (2) crop: 0.681; (3) weed: 0.576 |
[ ] | RGB images | Classification of potato plant and three weed species | ANN | Acc = 98.1% |
[ ] | RGB images | Estimation of weed growth stage (18 species) | CNN | Maximum Acc = 78% (Polygonum spp.), minimum Acc = 46% (blackgrass), average Acc = 70% (the number of leaves) and 96% for deviation of two leaves |
[ ] | Multispectral images | Classification of corn (crop) and silver beet (weed) | SVM | Precision = 98%, Acc = 98% |
[ ] | RGB images | Classification of Carolina Geranium within strawberry plants | CNN | F1 score values: (1) DetectNet: (0.94, highest); (2) VGGNet: 0.77; (3) GoogLeNet: 0.62 |
[ ] | RGB images | Classification of weeds in organic carrot production | CNN | Plant-based evaluation: Acc = 94.6%, Precision = 93.20%, Recall = 97.5%, F1 Score = 95.32% |
[ ] | Grayscale images from UGV | Recognition of Broad-leaved dock in grasslands | CNN, SVM | VGG-F: Acc = 96.8% |
[ ] | Multispectral images from UAV | Mapping of Black-grass weed in winter wheat fields | CNN | Baseline model: AUC = 0.78; Weighted kappa = 0.59; Average misclasssification rate = 17.8% |
[ ] | RGB images | Segmentation of rice and weed images at seedling stage in paddy fields | FCN | Semantic segmentation: Average Acc rate = 92.7% |
[ ] | RGB images from UGV | Creation of multiclass dataset for classification of eight Australian rangelands weed species | CNN | RS-50: Average Acc = 95.7%, average inference time = 53.4 ms per image |
[ ] | RGB images | Evaluation of weed detection, spraying and mapping system. Two Scenarios: (1) artificial weeds, plants; (2) real weeds, plants | CNN | Scenario: (1) Acc = 91%, Recall = 91%; (2) Acc = 71%, Precision = 78% (for plant detection and spraying Acc) |
[ ] | RGB images | Detection of goldenrod weed in wild blueberry crops | LC, QC | QC: Acc = 93.80% |
[ ] | RGB images | Detection of five weed species in turfgrass | CNN | Precision values: Dollar weed: VGGNet (0.97); old world diamond-flower: VGGNet (0.99); Florida pusley: VGGNet (0.98); annual bluegrass: DetectNet (1.00) |
[ ] | RGB images | Detection of three weed species in perennial ryegrass | CNN | Precision values: Dandelion: DetectNet (0.99); ground ivy: VGGNet (0.99), spotted spurge: AlexNet (0.87) |
[ ] | RGB images, multispectral images from UGV | Crop-weed classification along with stem detection | FCN | Overall: Mean precision = 91.3%, Mean recall = 96.3% |
[ ] | RGB images | Identification of crops (cotton, tomato) and weeds (velvetleaf and nightsade) | CNN, SVM, XGBoost, LR | Densenet and SVM: micro F1 score = 99.29% |
[ ] | Videos recordings | Classification of two weeds species in rice field | ANN, KNN | Acc values: Right channel (76.62%), Left channel (85.59%) |
[ ] | RGB images | Weed and crop discrimination in paddy fields | MCS, SRF, SVM | Acc values: Right channel (76.62%), Left channel (85.59%) |
[ ] | Gray-scale and RGB images | Weed and crop discrimination in carrot fields | RF | Acc = 94% |
[ ] | Multispectral and RGB images | Discrimination of weed and crops with similar morphologies | CNN | Acc = 98.6% |
[ ] | RGB images | Detection of C. sepium weed and sugar beet plants | CNN | mAP = 0.751–0.829 [email protected] = 0.761–0.897 |
[ ] | RGB images | Recognition of eight types of weeds in rangelands | CNN, RNN | DeepWeeds dataset: Acc = 98.1% |
[ ] | Multispectral images from UAV | Weed estimation on lettuce crops | SVM, CNN | F1 score values: (1) SVM: 88%; (2) CNN-YOLOv3: 94%; (3) Mask R-CNN: 94% |
[ ] | RGB images | Examination of pre-trained DNN for improvements in weed identification | CNN | (1) Xception: improvement = 0.51%; (2) Inception-Resnet: improvement = 1.89% |
[ ] | RGB images from UAV | Detection of five weeds in soybean fields | CNN | Faster RCNN: precision = 065, recall = 0.68, F1 score = 0.66, IoU = 0.85 |
[ ] | RGB images | Detection of goose grass weed in tomato, strawberry fields | CNN | (1) Strawberry: (a) entire plant: F1 score = 0.75, (b) leaf blade: F1 score = 0.85; (2) Tomato: (a) entire plant: F1 score = 0.56, (b) leaf blade: F1 score = 0.65 |
[ ] | Video recordings | Detection of five weed species in Marfona potato fields | ANN | Correct classification rate = 98.33% |
[ ] | In situ measurements, satellite spectral data | Identification of gamba grass in pasture fields | XGBoost | Balanced Acc = 86.9% |
[ ] | RGB images from UAV, satellite spectral data | Weed maps creation in oat fields | RF | Acc values: (1) Subset A: 89.0%; (2) Subset B: 87.1% |
[ ] | In situ measurements, RGB images from UAV | Identification of Italian ryegrass in early growth wheat | DNN | Presicion = 95.44%, recall = 95.48%, F score = 95.56% |
[ ] | RGB images from UGV | Weed detection evaluation of a spraying robot in potato fields on: (1) Image-level; (2) application-level; (3) field-level | CNN | YOLOv3: (1) Image-level: recall = 57%, precision = 84%; (2) application-level: plants detected = 83%; (3) field-level: correct spraying = 96% |
[ ] | RGB images from UGV | Detection of four weed species in maize and bean crops | CNN | Average precision = 0.15–0.73 |
[ ] | RGB images from UAV | Detection of Colchicum autumnale in grassland sites | CNN | U-Net: Precision = 0.692, Recall = 0.886, F2 score = 0.839 |
[ ] | RGB images from UAV | Weed mapping of Rumex obtusifolius in native grasslands | CNN | VGG16: Acc = 92.1%, F1 score = 78.7% |
Acc: Accuracy; AUC: Area under Curve; IoU: Intersection over Union; mAP: mean Average Precision; RGB: Red-Green-Blue; UAV: Unmanned Aerial Vehicle; UGV: Unmanned Ground Vehicle.
Crop Management: Crop Recognition.
Ref | Crop | Input Data | Functionality | Models/Algorithms | Best Output |
---|---|---|---|---|---|
[ ] | Various crops | Satellite spectral data | Classification of early-season crops | RF | Beginning of growth stage: acc = 97.1%, kappa = 93.5% |
[ ] | Various crops | Satellite spectral and phenological data | Identification of various crops from remote sensing imagery | SVM, RF, DF | DF: (1) 2015: overall acc = 88%; (2) 2016: overall acc = 85% |
[ ] | Maize, Rice, Soybean | Satellite spectral data | Three-dimensional classification of various crops | CNN, SVM, KNN | CNN: (1) 2015: overall acc = 0.939, kappa = 0.902; (2) 2016: overall acc = 0.959, kappa = 0.924 |
[ ] | Various crops | Satellite spectral data, in situ data | Identification of crops growing under plastic covered greenhouses | DT | Overall acc = 75.87%, Kappa = 0.63 |
[ ] | Various crops | Satellite data, phenological, in situ data | Classification of various crops | NB, DT, KM | KM: overall acc = 92.04%, Kappa = 0.7998 |
[ ] | Cabbage, Potato | RGB images from UAV, in situ data | Classification of potato and cabbage crops | SVM, RF | SVM: overall acc = 90.85% |
[ ] | Various crops | Satellite spectral data | Classification of various crops | SVM | Overall acc = 94.32% |
[ ] | Various crops | Satellite spectral data, in situ data | Classification of various crops in large areas | EBT, DT, WNN | EBT: overall acc = 87% |
[ ] | Various crops | Satellite spectral data, in situ data | Classification of various crops | SVM | overall acc = 92.64% |
[ ] | Various crops | Field location, in situ and satellite spectral data | Classification of six crops with small sample sizes | FFNN, ELM, MKL, SVM | MKL: accuracy = 92.1% |
[ ] | Wolfberry, Maize, Vegetables | Satellite spectral data | Crop classification in cloudy and rainy areas | RNN | Landsat-8: overall acc = 88.3%, Kappa = 0.86 |
[ ] | Maize, Canola, Wheat | Satellite spectral data, in situ data | Crop classification | RF, ANN, SVM | RF: overall acc = 0.93, Kappa = 0.91 |
[ ] | Various crops | Satellite spectral data | Classification of various crop types | Combination of FCN-LSTM | Acc = 86%, IoU = 0.64 |
[ ] | Various crops | Satellite spectral data | Crop classification of various crops | LightGBM | Highest acc: 92.07% |
[ ] | Maize, Peanut, Soybeans, Rice | Satellite spectral and in situ data | Prediction of different crop types | FCN, SVM, RF | Best crop mapping: FCN: acc = 85%, Kappa = 0.82 |
[ ] | Various crops | Satellite spectral and in situ data | Classification of early growth crops | CNN, RNN, RF | Highest Kappa: 1D CNN: 0.942 |
[ ] | Various crops | Satellite spectral and in situ data | Classification of various crops | CNN, LSTM, RF, XGBoost, SVM | CNN: acc = 85.54%, F1 score = 0.73 |
[ ] | Various crops | Satellite spectral data | Classification of parcel-based crops | LSTM, DCN | DCN: overall acc = 89.41% |
[ ] | Various crops | Satellite spectral data | Classification of crops in farmland parcel maps | LSTM, RF, SVM | LSTM: overall acc = 83.67%, kappa = 80.91% |
[ ] | Various crops | Satellite spectral data, in situ data | Crop classification | SVM, RF, CNN-RNN, GBM | Pixel R-CNN: acc = 96.5% |
[ ] | Zea mays, Canola, radish | Grayscale testbed data | Classification of the crops | SVM | Quadratic SVM: Precision = 91.87%, Recall = 91.85%, F1 score = 91.83% |
[ ] | Rice | Morphological data | Classification of two rice species (Osmancik-97 and Cammeo) | LR, MLP, SVM, DT, RF, NB, KNN | LR: acc = 93.02% |
[ ] | Soybean | Hyperspectral data, seed properties | Discrimination of 10 soybean seed varieties | TS-FFNN, SIMCA, PLS-DA, BPNN | TS-FFNN in terms of identification Acc, stability and computational cost |
[ ] | Cotton | Hyperspectral data, seed properties | Identification of seven cotton seed varieties: (1) Full spectra, (2) Effective wavelengths | PLS-DA, LGR, SVM, CNN | (1) Full spectra: CNN-SoftMax: 88.838%; (2) Effective wavelengths: CNN-SVM: 84.260% |
[ ] | Various plants | RGB images of leaves | Recognition of 15 plant species of Swedish leaf dataset | CNN | Macro average: (1) Precision = 0.97, (2) Recall = 0.97, (3) F1 score = 0.97 |
[ ] | Various shrubs and trees | RGB images of leaves | Identification of 30 shrub and trees species | RF, SVM, AdaBoost, ANN | SVM: acc = 96.5–98.4% |
[ ] | Various plants | RGB images of leaves | Identification of seven plant species | BPNN, SOM, KNN, SVM | BPNN: Recognition rate = 92.47% |
[ ] | Various crops | Satellite spectral data | Crop classification | SVM | SVM (RBF): overall acc values: (1) 2016: 88.3%; (2) 2017: 91%; (3) 2018: 85.00% |
[ ] | Various crops | Satellite spectral data | Crop classification | FCN | 3D FCN: overall acc = 97.56%, Kappa = 95.85% |
[ ] | Cotton, Rice, Wheat, Gram | Satellite spectral data | Crop classification | RF, KM | RF: acc = 95.06% |
[ ] | Various crops | Satellite spectral data | Crop classification | SVM, RF, CART | RF: overall acc = 97.85%, Kappa = 0.95 |
[ ] | Various crops | Satellite spectral data, in situ data | Crop classification | RF | overall acc = 75%, Kappa = 72% |
[ ] | Maize, Soybean | Satellite spectral data | Crop classification | RF, MLP, LSTM | LSTM: confidence interval = 95% |
[ ] | Various crops | Satellite spectral and in situ data | Crop classification | XGBoost, SVM, RF, MLP, CNN, RNN | CNN: overall acc = 96.65% |
[ ] | Rice | Satellite spectral data | Crop classification | CNN, SVM, RF, XGboost, MLP | CNN: overall acc = 93.14%, F1 score = 0.8552 |
[ ] | Various crops | Satellite spectral and in situ data | Crop classification | RF | Overall acc = 0.94, Kappa = 0.93 |
[ ] | Various crops | Satellite spectral data | Crop classification | CNN, LSTM, SVM | CNN: overall acc = 95.44%, Kappa = 94.51% |
[ ] | Various crops | Satellite spectral data | Crop classification prior to harvesting | DT, KNN, RF, SVM | RF: overall acc = 81.5%, Kappa = 0.75 |
[ ] | Various crops | Satellite spectral data | Crop classification | CNN | Overall acc = 98.19% |
[ ] | Various crops | Satellite spectral data | Crop classification | SVM, DA, DT, NNL | NNL: F1 score = 0.88 |
[ ] | Banana, Rice, Sugarcane, Cotton | Satellite spectral and in situ data | Crop classification | SVM | Overall acc = 89% |
[ ] | Various crops | Satellite spectral and in situ data | Crop classification | RF | Overall acc = 93.1% |
Acc: Accuracy; IoU: Intersection over Union; RGB: Red-Green-Blue; UAV: Unmanned Aerial Vehicle.
Crop Management: Crop Quality.
Ref | Crop | Input Data | Functionality | Models/Algorithms | Best Output |
---|---|---|---|---|---|
[ ] | Apples | Quality features, (flesh firmness, soluble solids, fruit mass and skin color) | Classification of apple total quality: very poor, poor, medium, good and excellent | FIS, ANFIS | FIS: acc values: (1) 2005: 83.54%; 2006: 92.73%; 2007: 96.36% |
[ ] | Pepper | RGB images, quality features (color, mass and density of peppers) | Recognition of pepper seed quality | BLR, MLP | MLP: 15 traits, stability = 99.4%, predicted germination = 79.1%, predicted selection rate = 90.0% |
[ ] | Soybeans | Satellite spectral and soil data | Estimation of crop gross primary productivity | RF, ANN | ANN: R = 0.92, RMSE = 1.38 gCdm |
[ ] | Wheat | RGB images captured by UAV | Estimation of aboveground nitrogen content combining various VI and WFs | PLSR, PSO-SVR | PSO-SVR: R = 0.9025, RMSE = 0.3287 |
[ ] | Millet, rye, maize | RGB images captured in laboratory | Assessment of grain crops seed quality | CNN | Faster R-CNN: (1) Pearl millet: mAP = 94.3%; (2) rye: mAP = 94.2%, (3) Maize: mAP = 97.9% |
[ ] | Jatropha curcas | X-ray imaging | Prediction of vigor and germination | LDA | Acc values: Fast germination: 82.08%; Slow germination: 76.00%; Non-germinated: 88.24% |
[ ] | Various legumes | Spectral data form spectroradiomener | Estimation of five warm-season legumes forage quality | PLS, SVM, GP | SVM: All five crops: = 0.92–0.99, IVTD: = 0.42–0.98 |
[ ] | Forage grass | X-ray imaging | Prediction of vigor and seed germination | LDA, PLS-DA, RF, NB, SVM | PLS-DA: Acc values: (1) Vigor: FT-NIR: 0.61, X-ray: 0.68, Combination: 0.58; (2) Germination: FT-NIR: 0.82, X-ray: 0.86, Combination: 0.82 |
[ ] | Tomato | RGB images | Dimensions and mass estimation for quality inspection | (1) DSM, (2) Dimensions (CNN), (3) Mass estimation on: (a) MMD (BET, GPR, SVR, ANN, GPR), (b) EDG (BET, GPR, SVR, ANN) | (1) DSM: precision = 99.7%; MAE values: (2) Width (2.38), Length (2.58); (3) Mass estimation: (a) MMD (4.71), (b) EDG (13.04) |
[ ] | Peach | Hyperspectral images | Estimation of soluble solids content | SAE-RF | R = 0.9184, RMSE = 0.6693 |
Acc: Accuracy; DSM: Detection and Segmentation Module; EDG: Estimated Dimensions Geometry; IVTD: In Vitro True Digestibility; RGB; Red-Green-Blue; MMD: Manually Measured Dimensions; mAP: mean Average Precision; PSO: Particle Swarm Optimization; RGB; Red-Green-Blue; SAE: Stacked AutoEncoder; VI: Vegetation Indices; WF: Wavelet Features.
Water management.
Ref | Property | Input Data | Functionality | Models/Algorithms | Best Output |
---|---|---|---|---|---|
[ ] | Crop water status | Weather data, crop water status, thermal images | Prediction of vineyard’s water status. Scenario A: with RT; Scenario B: without RT | REPTree | (1) Scenario A: prediction: R = 0.58, RMSE = 0.204 MPa; (2) Scenario B: prediction: R = 0.65, RMSE = 0.184 MPa. |
[ ] | Crop water status | Crop water status, hyperspectral data | Discrimination of stressed and non-stressed vines | RF, XGBoost | RF: Acc = 83.3%, Kappa = 0.67 |
[ ] | Groundwater level | Water table depth, weather data | Prediction of water table depth | LSTM, FFNN, | LSTM: R = 0.789–0.952 |
[ ] | Irrigation scheduling | Weather, irrigation, soil moisture, yield data | Prediction of weekly irrigation plan in jojoba orchards | DTR, RFR, GBRT, MLR, BTC | (1) Regression: GBRT: Acc = 93%; (2) Classification: GBRT: Acc = 95% |
[ ] | Crop water status | Water status, multispectral UAV data | Estimation of vineyard water status | MLR, ANN | ANN: R = 0.83 |
[ ] | ET | Weather data | Estimation of daily ET | ELM, WANN | ELM: RMSE values: Region case A: 0.1785 mm/day; Region case B: 0.359 mm/day |
[ ] | ET | Weather data | Estimation of daily ET | RF, M5Tree, GBDT, XGBoost, SVM, RF | XGBoost: RMSE = 0.185–0.817 mmday |
[ ] | Soil water content | Weather data, volumetric soil moisture content | Prediction of one-day-ahead volumetric soil moisture content | FFNN, LSTM | LSTM: R > 0.94 |
[ ] | Infiltration | Field data, moisture content, cumulative infiltration of soil | Estimation of cumulative infiltration of soil | SVM, ANN, ANFIS | ANFIS: RMSE = 0.8165 cm, CC = 0.9943 |
[ ] | Soil water content | Weather data, soil moisture difference, ultraviolet radiation | Prediction of soil moisture | SVR | R = 0.98, R = 0.96, MSE = 0.10 |
[ ] | Soil water content | Simulated soil moisture data, weather data | Forecasting of monthly soil moisture for: Scenario A: upper; Scenario B: lower layers | ELM | (1) Scenario A: RRMSE = 19.16%; (2) Scenario B: RRMSE = 18.99% |
[ ] | ET | Weather and in situ crop data | Estimation of actual ET Scenario A: rainfed maize field under non-mulching; Scenario B: partial plastic film mulching | ANN, SVM | ANN: Scenario A: ET = 399.3 mm, RMSE = 0.469, MAE = 0.376; Scenario B: ET = 361.2 mm, RMSE = 0.421, MAE = 0.322 |
[ ] | Infiltration and infiltration rate | Soil and hydraulic data | Prediction of cumulative infiltration and infiltration rate in arid areas | ANFIS, SVM, RF | SVM: RMSE values: cumulative infiltration: 0.2791 cm, infiltration rate: 0.0633 cmh |
[ ] | Water quality | NIR spectroscopy. | Estimation of water pollution level | CNN | RMSE = 25.47 mgL |
[ ] | ET | Weather data, simulated ET data | Estimation of ET : (1) 2011–2015; (2) 2016–2017 | LSTM | (1) Predictions in 3 sites: R > 0.90; (2) All sites: RMSE = 0.38–0.58 mmday |
[ ] | Soil water content | Weather data, potential ET, simulated soil moisture data | Estimation of soil moisture | FFNN, Ross-IES | FFNN: RMSE = 0.15–0.25, NSE = 0.71–0.91 |
[ ] | ET | Weather data, simulated ET data, soil data | Estimation of daily kikuyu grass crop ET | RT, SVR, MLP, KNN, LGR, MLR, BN, RFC | RFC: R = 0.9936, RMSE = 0.183 mmday , MRE = 6.52% |
[ ] | Drought | Weather data | Evaluation of farmers’ draught perception | RF, DT | Most influential parameters: farmer’s age, education level, years of experience and number of cultivated land plots |
[ ] | ET | Weather and soil data; simulated ET | Prediction of daily potato ET | ANN, AdaBoost, KNN | KNN: R = 0.8965, RMSE = 0.355 mm day , MSE = 0.126 mm day |
[ ] | Soil water erosion | In situ data, geological, and weather data | Susceptibility mapping of soil erosion from water | RF, GP, NB | RF: Acc = 0.91, kappa = 0.94, POD = 0.94 |
[ ] | ET, drought | Weather data, simulated ET index | Prediction of drought | SVR | Fuzzy-SVR: R = 0.903, RMSE = 0.137, MAE = 0.105 |
[ ] | ET | Weather data, simulated ET | Estimation of daily ET | CNN, ANN, XGBoost, RF | CNN: (1) Regional: R = 0.91, RMSE = 0.47; (2) Local: R = 0.92, RMSE = 0.37 |
[ ] | ET | Weather data | Estimation of daily ET | ELM, ANN, RF | ELM: R = 0.920, MAE = 0.394 mmday |
[ ] | ET | Weather data | Prediction of ET in semi-arid and arid regions | CART, CCNN, SVM | SVM: (1) Station I: R = 0.92; (1) Station II: R = 0.97 |
[ ] | Pan evaporation | Weather data | Prediction of monthly pan evaporation | ELM, ANN, M5Tree | ELM: R = 0.864–0.924, RMSE = 0.3069–0.4212 |
[ ] | ET | Weather data, simulated ET | Evaluation of ML algorithms in daily reference ET prediction | Cubist, SVM, ANN, MLR | Cubist: R = 0.99, RMSE = 0.10 mmday , MAE = 0.07 mmday |
[ ] | ET | Weather data, simulated ET | Estimation of ET | SVM, MLP, CNN, GRNN, GMDH | SVM: R = 0.96–1.00, ME = 95–99% |
[ ] | Drought | Weather data, simulated Palmer Z-index values | Estimation of Palmer drought severity index | ANN, DT, LR, SVM | ANN: R = 0.98, MSE = 0.40, RMSE = 0.56 |
[ ] | Water quality | In-situ water quality data, hyperspectral, satellite data. | Estimation of inland water quality. | LSTM, PLSR, SVR, DNN | DNN: R = 0.81, MSE = 0.29, RMSE = 0.54 |
[ ] | Groundwater | In-situ water quality data, hyperspectral, satellite spectral data | Estimation of water quality | DT | Acc = 81.49%, ROC = 87.75% |
[ ] | Groundwater | Weather data, ET, satellite spectral data, land use | Estimation of groundwater withdrawals | RF | R = 0.93, MAE = 4.31 mm, RMSE = 13.50 mm |
[ ] | Groundwater nitrate concentration | Various geo-environmental data | Comparison of different ML models for estimating nitrate concentration | SVM, Cubist, RF, Bayesian-ANN | RF: R = 0.89, RMSE = 4.24, NSE = 0.87 |
Acc: Accuracy; CC: Coefficient of Correlation; ET: Evapotranspiration; ET o : reference EvapoTranspiration; ROC: Receiver Operating Characteristic; ME: Model Efficiency; NSE: Nash-Sutcliffe model efficiency Coefficient; POD: Probability Of Detection.
Soil management.
Ref | Property | Input Data | Functionality | Models/Algorithms | Best Output |
---|---|---|---|---|---|
[ ] | Soil organic matter | Soil properties, spectrometer NIR data | Estimation of soil organic matter | ELM, SVM | TRI-ELM: R = 0.83, RPIQ = 3.49 |
[ ] | Soil microbial dynamics | Microbial dynamics measurements from root samples | Prediction of microbial dynamics: (1) BP; (2) PS and (3) ACCA | ANN, SVR, FIS | SCFIS: (1) BP: RMSE = 1350000, R = 1.00; (2) PS: RMSE = 45.28, R = 1.00; (3) ACCA: RMSE = 271, R = 0.52 |
[ ] | Soil salinity | Soil salinity, hyperspectral data, satellite data | Prediction of soil salinity | Bootstrap BPNN | BPNN with hyperspectral data: R = 0.95, RMSE = 4.38 g/kg |
[ ] | Soil properties | Simulated topographic attributes, satellite data | Prediction of SOC, CCE, clay content | Cu, RF, RT, MLR | (1) CCE: Cu: R = 0.30, RMSE = 9.52; (2) SOC: Cu, RF: R = 0.55; (3) Clay contents: RF: R = 0.15, RMSE = 7.86 |
[ ] | Soil organic matter | Soil properties, weather data, terrain, satellite spectral data | Prediction of soil organic matter | DT, BDT, RF, GBRT | GBRT: ME = 1.26 g/kg, RMSE = 5.41 g/kg, CCC = 0.72 |
[ ] | Soil organic matter | soil properties, satellite, land cover, topographic, weather data | Prediction of soil organic matter | CNN, RF, XGBoost | XGBoost: ME = 0.3663 g/kg, MSE = 1.0996 g/kg |
[ ] | Electrical conductivity | soil properties, simulated electrical conductivity | Prediction of soil electrical conductivity | MLP | MLP: WI = 0.780, E = 0.725, E = 0.552 |
[ ] | Soil moisture content | Hyperspectral images data, UAV, soil moisture content data samples | Estimation of soil moisture content | RF, ELM | RF: R = 0.907,RMSEP = 1.477, RPD = 3.396 |
[ ] | Soil temperature | Weather data | Estimation of soil temperature at various depths | ELM, GRNN, BPNN, RF | ELM: RMSE = 2.26–2.95 °C, MAE = 1.76–2.26 °C, NSE = 0.856–0.930, CC = 0.925–0.965 |
[ ] | SOC | Soil properties, vis-NIR spectral data | Estimation of SOC | RF | R = 0.74–0.84, RMSEP = 0.14–0.18%, RPD = 1.98–2.5 |
[ ] | Soil properties | Soil properties, visible-NIR, MIR spectral data | Prediction of total carbon, cation exchange capacity and SOC | PLSR, Cu, CNN | CNN: R = 0.95–0.98 |
[ ] | Soil properties | Soil properties, simulated organic, mineral samples, soil spectral data | Estimation of various soil properties | CNN | RMSE values: OC: 28.83 g/kg, CEC: 8.68 cmol /kg, Clay: 7.47%, Sand: 18.03%, pH: 0.5 g/kg, N: 1.52 g/kg |
[ ] | Soil moisture content, soil ET | Soil properties, water, weather and crop data | Estimation of soil moisture content and soil ET | NN-RBF | Soil MC: RMSE = 0.428, RSE = 0.985, MSE = 0.183, RPD = 8.251 |
[ ] | Soil salinity | Soil salinity, crop field temperature | Estimation of leaching water requirements for saline soils | Naive Bayes classifier | Acc = 85% |
[ ] | Soil erosion | Weather data, satellite, soil chemical data | Estimation of soil erosion susceptibility | Combination of GWR-ANN | GWR-ANN: AUC = 91.64% |
[ ] | Soil fertility | Spectral, weather data, EC, soil properties | Prediction of soil fertility and productivity | PLS | (1) Productivity: RMSEC = 0.20 T/ha, RMSECV = 0.54 T/ha, R = 0.9189; (2) Organic matter: R = 0.9345, RMSECV = 0.54%; (3) Clay: R = 0.9239, RMSECV = 5.28% |
[ ] | Soil moisture | Multispectral images from UAV, in situ soil moisture, weather data. | Retrieval of surface soil moisture | BRT, RF, SVR, RVR | BRT: MAE = 3.8% |
[ ] | Soil moisture | Soil samples, simulated PWP, field capacity data | Estimation of PWP and field capacity | ANN, KNN, DL | R = 0.829, R = 0.911, MAE = 0.027 |
[ ] | Soil temperature | Weather data | Estimation of soil temperature | GMDH, ELM, ANN, CART, MLR | ELM: R = 0.99 |
[ ] | Soil moisture | Soil samples, on-field thermal, simulated soil moisture data | Estimation of soil moisture content | ANN, SVM, ANFIS | SVM: R = 0.849, RMSE = 0.0131 |
[ ] | Gully erosion | Geological, environmental, geographical data | Evaluation of gully erosion susceptibility mapping | RF, CDTree, BFTree, KLR | RF: AUC = 0.893 |
[ ] | Groundwater salinity | Topographic, groundwater salinity data | Evaluation of groundwater salinity susceptibility maps | StoGB, RotFor, BGLM | BGLM: Kappa = 0.85 |
[ ] | Heavy metals transfer | Soil and crop properties | Identification of factors related to heavy metals transfer | RF, GBM, GLM | RF: R = 0.17–0.84 |
[ ] | Land suitability | Soil properties, weather, topography data | Prediction of land suitability maps | SVM, RF | RF: Kappa = 0.77, overall acc = 0.79 |
[ ] | SOC | Soil properties, satellite, simulated environmental data | Prediction of SOC | MLR, SVM, Cu, RF, ANN | RF: R = 0.68 |
[ ] | Electrical conductivity, SOC | Soil properties, weather data | Electrical conductivity and SOC prediction | GLM | (1) EC: MSPE = 0.686, MAPE = 0.635; (2) OC: MSPE = 0.413, MAPE = 0.474 |
[ ] | SOC, soil moisture | Proximal spectral data, electrical conductivity, soil samples data | Prediction of SOC and soil moisture 3D maps | Cu, RF | Cu: R = 0.76, CCC = 0.84, RMSE = 0.38% |
[ ] | Soil aggregate stability | Soil samples data | Prediction of soil aggregate stability | GLM, ANN | ANN: R = 0.82 |
[ ] | SOC | Soil samples, weather, topographic, satellite data | Prediction of SOC | Cu, RF, SVM, XGBoost, KNN | Best SOC prediction: RF: RMSE = 0.35%, R = 0.6 |
[ ] | Soil moisture | In situ soil moisture, satellite data | Estimation of surface soil moisture | SVM, RF, ANN, EN | RF: NSE = 0.73 |
[ ] | SOC | Composite surface soil, satellite, weather data | Prediction of SOC | SVM, ANN, RT, RF, XGBoost, DNN | DNN: MAE = 0.59%, RMSE = 0.75%, R = 0.65, CCC = 0.83 |
[ ] | Gully erosion | Topographic, weather, soil data | Mapping of gully erosion susceptibility | LMT, NBTree, ADTree | LMT: AUC = 0.944 |
[ ] | Gully erosion | Satellite spectral data | Identification of gully erosion | LDA, SVM, RF | Best overall acc: RF: 98.7% |
[ ] | Gully erosion | Satellite, weather, land type maps data | Gully erosion mapping | LGR | Acc = 68%, Kappa = 0.42 |
ACCA: Aminoyclopropane-1-carboxylate; AUC: Area Under Curve; BP: Bacterial Population; CC: Coefficient of Correlation; CCC: Concordance Correlation Coefficient; CCE: Calcium Carbonate Equivalent; ET: EvaporoTransporation; MIR: Mid InfraRed; NSE: Nash-Sutcliffe model efficiency Coefficient; NIR: Near-InfraRed; PS: Phosphate Solubilization; PWP: Permanent Wilting Point; RPIQ: Ratio of Performance to Interquartile Range; RPD: Relative Percent Deviation; SOC: Soil Organic Carbon; WI: Willmott’s Index.
Livestock Management: Animal Welfare.
Ref | Animal | Input Data | Functionality | Models/Algorithms | Best Output |
---|---|---|---|---|---|
[ ] | Swine | 3D, 2D video images | Detection of pigs tail posture as a sign of tail biting | LMM | Low vs. not low tails: Acc = 73.9%, Sensitivity = 88.4%, Specificity = 66.8% |
[ ] | Sheep | Accelerometer and gyroscope attached to the ear and collar of sheep | Classification of Grazing and Rumination Behavior in Sheep | RF, SVM, KNN, Adaboost | RF: Highest overall acc: collar: 92%; ear: 91% |
[ ] | Sheep | Accelerometer, gyroscope data | Classification of sheep behavior (lying, standing and walking) | RF | Acc = 95%, F1-score = 91–97% for: ear: 32 Hz, 7 s, collar: 32 Hz, 5 s |
[ ] | Swine | RGB images | Recognition of pigs feeding behavior | CNN | Faster R-CNN: Precision = 99.6%, recall = 86.93% |
[ ] | Swine | RGB images, depth images | Recognition of lactating sow postures | CNN | Faster R-CNN: Sow posture: (1) Recumbency: night: 92.9%, daytime: 84.1%; (2) Standing: at night: 0.4%, daytime: 10.5% (3) Sitting: night: 0.55%, daytime: 3.4% |
[ ] | Cattle, Sheep, sheepdog | Audio field recordings data | Classification of animals’ vocalization | SVM | Acc: cattle: 95.78%, sheep: 99.29%, dogs: 99.67% |
[ ] | Cattle | Accelerometer data | Detection of sheep rumination. | SVM | Acc = 86.1% |
[ ] | Sheep | Ear-borne accelerometer data, observation recordings | Classification of grazed sheep behavior Scenario A: walking, standing, lying, grazing Scenario B: active/inactive Scenario C: body posture | CART, SVM, LDA, QDA | (1) Scenario A: SVMAcc: 76.9%; (2) Scenario B: CART Acc: 98.1%; (3) Scenario C: Acc: LDA 90.6% |
[ ] | Goat | On-farm videos, weather data | Classification of goats behavior (1) Anomaly detection (2) Feeding/non-feeding | KNN, SVR, CNN | (1) Most accurate: KNN: Acc = 95.02–96.5%; (2) Faster R-CNN: Eating: 55.91–61.33 %, Non-feeding (Resting): 79.91–81.53 % |
[ ] | Cattle, sheep | UAV Video data | Counting and classification of cattle, sheep | CNN | Mask R-CNN: Cattle: Acc = 96%; Sheep: Acc = 92% |
[ ] | Cattle | Accelerometer data | Prediction of dairy cows behavior at pasture | XGBoost, SVM, AdaBoost, RF | Best predictions for most behaviours: XGBoost: sensitivity = 0.78 |
[ ] | Cattle | Pedometers | Detection of early lameness in dairy cattle | RF, KNN | RF: acc = 91% |
[ ] | Cattle | Environmental heat stressors data | Evaluation of heat stressors influence in dairy cows physiological responses | RF, GBM, ANN, PLR | RF: (1) RR: RMSE = 9.695 respmin ; (2) ST: RMSE = 0.334 °C |
[ ] | Cattle | Diets nutrient levels data | Prediction of dairy cows diet energy digestion | ELM, LR, ANN, SVM | Best performance: kernel-ELM: (1) DE: R = 08879, MAE = 4.0606; (2) ED: R = 0899, MAE = 2.3272 |
[ ] | Cattle | Routine herd data | Detection of lameness in dairy herds | GLM, RF, GBM, XGBoost, CART | GBM: AUC = 0.75, Sensitivity = 0.58, Specificity = 0.83 |
[ ] | Poultry | Air quality data | Early prediction of Coccidiosis in poultry farms | KNN | AUC = 0.897–0.967 |
[ ] | Cattle | On-farm questionnaires, clinical and milk records | Prediction of mastitis infection in dairy herds | RF | CONT vs. ENV: Acc = 95%, PPV = 100%, NPV = 95% |
[ ] | Cattle | Location (transceiver) and accelerometer data | Detection of dairy cows in estrus | KNN, LDA, CART, BPNN, KNN | BPNN: specificity = 85.71% |
[ ] | Cattle | Mid-NIR spectral data using spectrometer | Prediction of bovine tuberculosis in dairy cows | CNN | Accuracy = 71%, sensitivity = 0.79, specificity = 0.65 |
[ ] | Cattle | Metabolomics data from serum samples | Evaluation of metabotypes existence in overconditioned dairy cows | RF, NB, SMO, ADT | ADT: acc = 84.2% |
[ ] | Cattle | Accelerometer data | Classification of cows’ behavior | GBDT, SVM, RF, KNN | GBDT: acc = 86.3%, sensitivity = 80.6% |
[ ] | Sheep | Gyroscope and accelerometer ear sensors | Detection of lame and non-lame sheep in three activities | RF, SVM, MLP, AdaBoost | RF: overall acc = 80% |
[ ] | Cattle | Activity and rumination data | Prediction of calving day in cattle | RNN, RF, LDA, KNN, SVM | RNN/LSTM: Sensitivity = 0.72, Specificity = 0.98 |
AUC: Area Under Curve; Cont: Contagious; DE: Digestible Energy; ED: Energy Digestibility; ENV: Environmental; DWT: Discrete Wavelet Transform; MFCCs: Mel-Frequency Cepstral Coefficients; NIR: Near InfraRed; NPV: Negative Predictive Value; PTZ: Pan-Tilt-Zoom; PPV: Positive Predictive Value; RGB: Red-Green-Blue; RR: Respiration Rate; ST: Skin Temperature.
Livestock Management: Livestock Production.
Ref | Animal | Input Data | Functionality | Models/Algorithms | Best Output |
---|---|---|---|---|---|
[ ] | Cattle | Depth images in situ BCS evaluation data | Estimation of BCS, Scenario A: HER = 0.25; Scenario B: HER = 0.5 | CNN | Scenario A: Acc = 78%; Scenario B: Acc = 94% |
[ ] | Swine | Weather, physiological data | Prediction of piglets temperature Scenario A: skin-surface; Scenario B: hair-coat; Scenario C: core | DNN, GBR, RF, GLR | Best prediction: Scenario C: DNN: error = 0.36% |
[ ] | Poultry | Depth, RGB images data | Classification of flock of chickens’ behavior | CNN | Acc = 99.17% |
[ ] | Cattle | Accelerometer, observations recordings data | Classification of cattle behaviour Scenario A: grazing; Scenario B: standing; Scenario C: ruminating | RF | Highest F-scores: RF: Scenario A: 0.914; Scenario B: 0.89; Scenario C: 0.932 |
[ ] | Sheep | Phenotypic, weather data | Prediction of on-farm water and electricity consumption on pasture based Irish dairy farms | BAG, ANN, MT | Scenario 3: MT: R = 0.95, MAE = 0.88 μm, RMSE = 1.19 |
[ ] | Cattle | Milk production, environmental data | Prediction of on-farm water and electricity consumption on pasture based Irish dairy farms | CART, RF, ANN, SVM | Electricity consumption prediction: SVM: relative prediction error = 12% |
[ ] | Goat | RGB data | Detection of dairy goats from surveillance video | CNN | Faster R-CNN: Acc = 92.49 % |
[ ] | Cattle | Animal feed, machinery, milk yield data | Estimation of energy use targets for buffalo farms | ANN | 30.5 % of total energy input can be saved if targeted inputs are followed |
[ ] | Cattle | 3D images data | Prediction of liveweight and carcass characteristics | ANN, SLR | ANN: Liveweight: R = 0.7, RMSE = 42; CCW: R = 0.88, RMSE = 14; SMY: R = 0.72, RMSE = 14 |
[ ] | Swine | RGB images | Detection and pig counting on farms | CNN | MAE = 1.67, RMSE = 2.13, detection speed = 42 ms per image |
[ ] | Sheep | Biometric traits, body condition score data | Prediction of commercial meat cuts and carcass traits | MLR, ANN, SVR, BN | SVM: Neck weight: R = 0.63, RMSE = 0.09 kg; HCW: R = 0.84, RMSE = 0.64 |
[ ] | Cattle | Data produced by REIMS | Prediction of beef attributes (muscle tenderness, production background, breed type and quality grade) | SVM, RF, KNN, LDA, PDA, XGBoost, LogitBoost, PLS-DA | Best Acc: SVM: 99% |
[ ] | Sheep | Carcass, live weight and environmental records | Estimation of sheep carcass traits (IMF, HCW, CTLEAN, GRFAT, LW) | DL, GBT, KNN, MT, RF | Highest prediction of all traits: RF: (1) IMF: R = 0.56, MAE = 0.74; (2) HCW: R = 0.88, MAE = 1.19; (3) CTLEAN: R = 0.88, MAE = 0.76 |
[ ] | Swine | ADG, breed, MT, gender and BBFT | Identification of pigs’ limb condition | RF, KNN, ANN, SVM, NB, GLM, Boost, LDA | RF: Acc = 0.8846, Kappa = 0.7693 |
[ ] | Cattle | Activity, weather data | Prediction of cows protein and fat content, milk yield and actual concentrate feed intake, Scenario (1) only cows with similar heat tolerance; Scenario (2) all cows | ANN | (1) Scenario A: n = 116, 456; R = 0.87; slope = 0.76; (2) Scenario B: n = 665, 836; R = 0.86; slope = 0.74 |
[ ] | Cattle | Animal behavior, feed intake, estrus events data | Detection of estrus in dairy heifers | GLM, ANN, RF | RF: Acc = 76.3–96.5% |
[ ] | Cattle | Infrared thermal images | Estimation of deep body temperature | LRM, QRM | Higher correlation: QRM: R = 0.922 |
[ ] | Cattle | Liveweight, biophysical measurements data | Prediction of Carcass traits and marbling score in beef cattle | LR, MLP, MT, RF, SVM | SVM: carcass weight: R = 0.945, MAE = 0.139; EMA: R = 0.676, MAE = 4.793; MS: R = 0.631, MAE = 1.11 |
ACFW: Adult Clean Fleece Weight; ADG: Average Daily Gain; AFD: Adult Fibre Diameter; AGFW: Adult Greasy Fleece Weight; ASL: Adult Staple Length; ASS: Adult Staple Strength; BBFT: Bacon/BackFat Thickness; BCS: Body Condition Score; CCW: Cold Carcass Weights; CTLEAN: Computed Tomography Lean Meat Yield; DBT: Deep Body Temperature; EMA: Eye Muscle Area; GWAS: Genome-Wide Association Studies; GRFAT: Greville Rule Fat Depth; HER: Human Error Range; IMF: IntraMuscular Fat; HCW: Hot Carcass Weight; LW: Loin Weight; MS: Marbling Score; MT: Muscle Thickness; REIMS: Rapid Evaporative Ionization Mass Spectrometry; RGB: Red-Green-Blue; SMY: Saleable Meat Yield.
Abbreviations for machine learning models.
Abbreviation | Model |
---|---|
ANN | Artificial Neural Network |
BM | Bayesian Models |
DL | Deep Learning |
DR | Dimensionality Reduction |
DT | Decision Trees |
EL | Ensemble Learning |
IBM | Instance Based Models |
SVM | Support Vector Machine |
Abbreviations for machine learning algorithms.
Abbreviation | Model | Model |
---|---|---|
AdaBoost | EL | Adaptive Boosting |
ADT | DT | Alternating Decision Trees |
ANFIS | ANN | Adaptive-Neuro Fuzzy Inference Systems |
ARD | BM | Automatic Relevance Determination |
Bayesian-ANN | ANN | Bayesian Artificial Neural Network |
BAG | EL | Bagging Algorithm |
BDT | DT | Bagging Decision Trees |
BDL | BM,ANN | Bayesian Deep Learning |
BET | EL | Bagged Ensemble Tree |
BGLM | BM, Regression | Bayesian Generalized Linear Model |
BLR | Regression | Binary Logistic Regression |
BN | BM | Bayesian Network |
BPNN | ANN | Back-Propagation Neural Networks |
BRT | DT,EL | Boosted Regression Trees |
BTC | EL | Boosted Trees Classifiers |
CART | DT | Classification And Regression Trees |
CCNN | ANN | Cascade Correlation Neural Networks |
CDTree | DT | Credal Decision Trees |
CNN | ANN | Convolutional Neural Networks |
Cu | Regression | Cubist |
DBN | ANN | Deep Belief Networks |
DF | EL,SVM | Decision Fusion |
DLS | Regression | Damped Least Squares |
DNN | ANN | Deep Neural Networks |
DTR | DT, Regression | Decision Tree Regression |
EBT | DT,EL | Ensemble Bagged Trees |
ERT | DT | Extremely Randomized Trees |
ELM | ANN | Extreme Learning Machines |
EN | Regression | Elastic Net |
FCN | ANN | Fully Convolutional Networks |
FIS | ANN | Fuzzy Inference System |
FFNN | ANN | Feed Forward Neural Networks |
GBM | EL | Gradient Boosting Model |
GBT | DT | Gradient Tree Boosting |
GBR | Regression | Gradient Boosted Regression |
GBRT | DT, Regression | Gradient Boosted Regression Trees |
GBDT | DT,EL | Gradient Boosted Decision Trees |
GLM | Regression | General Linear Model |
GMDH | DR | Group Method of Data Handling |
GNB | BM | Gaussian Naive Bayes |
GP | ΒΜ | Gaussian Processes |
GPR | ΒΜ | Gaussian Process Regression |
GRNN | ANN | Generalized Regression Neural Networks |
GWR | Regression | Geographically Weighted Regression |
KM | IBM | K-Means |
KNN | IBM | K-Nearest Neighbors |
LASSO | Regression | Least Absolute Shrinkage and Selection Operator |
LDA | DR | Linear Discriminant Analysis |
LightGBM | EL | Light Gradient Boosting Machine |
LMT | Regression, DT | Logistic Model Trees |
LGR | Regression | LoGistic Regression |
LMM | Regression | Linear Mixed Model |
LR | Regression | Linear Regression |
LSTM | ANN | Long-Short Term Memory |
LogitBoost | EL | Logistic Boosting |
M5Tree | DT | M5 model Trees |
MANN | ANN | Modular Artificial Neural Networks |
MARS | Regression | Multivariate Adaptive Regression Splines |
MCS | EL | Multiple Classifier System |
MKL | DR | Multiple Kernel Learning |
MLP | ANN | Multi-Layer Perceptron |
MLR | Regression | Multiple Linear Regression |
MT | DT | Model Trees |
NB | BM | Naïve Bayes |
NBTree | BM, DT | Naïve Bayes Trees |
NNL | IBM | Nearest Neighbor Learner |
OLS | Regression | Ordinary Least Squares |
PLSR | Regression | Partial Least Squares Regression |
PLS-DA | Regression, DR | Partial Least Squares Discriminant Analysis |
QC | Regression | Quadratic Classifier |
QDA | DR | Quadratic Discriminant Analysis |
QRM | Regression | Quadratic Regression Model |
RBFN | ANN | Radial Basis Function Networks |
REPTree | DT | Reduced Error Pruning Tree |
RFC | EL | Randomizable Filtered Classifier |
RFR | EL, Regression | Random Forest Regression |
RNN | ANN | Recurrent Neural Network |
RQL | Regression | Regression Quantile LASSO |
RF | EL | Random Forest |
Ross-IES | EL | Ross Iterative Ensemble Smoother |
RotFor | EL | Rotation Forest |
RVMR | Regression | Relevance Vector Machine Regression |
SCFIS | ANN | Subtractive Clustering Fuzzy Inference System |
STDA | DR | Stepwise Discriminant Analysis |
SMO | SVM | Sequential Minimal Optimization |
SMLR | Regression | Stepwise Multiple Linear Regression |
SOM | DR | Self-Organising Maps |
StoGB | EL | Stochastic Gradient Boosting |
SVR | SVM | Support Vector Regression |
TS-FNN | ANN | Takagi-Sugeno Fuzzy Neural Networks |
XGBoost | EL | Extreme Gradient Boosting |
WANN | ANN | Wavelet Artificial Neural Networks |
WEL | EL | Weighted Ensemble Learning |
WNN | IBM | Weighted Nearest Neighbors |
WSL | EL | Weakly Supervised Learning |
Conceptualization, D.B.; methodology, L.B., G.D., R.B., D.K. and A.C.T.; investigation, L.B. and G.D.; writing—original draft preparation, L.B. and A.C.T.; writing—review and editing, L.B., G.D., D.K., A.C.T., R.B. and D.B.; visualization, L.B.; supervision, D.B. All authors have read and agreed to the published version of the manuscript.
This work has been partly supported by the Project “BioCircular: Bio-production System for Circular Precision Farming” (project code: T1EDK- 03987) co-financed by the European Union and the Greek national funds through the Operational Programme Competitiveness, Entrepreneurship and Innovation, under the call RESEARCH—CREATE—INNOVATE.
The authors declare no conflict of interest.
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.
1678 Accesses
8 Citations
Explore all metrics
Machine learning has created new opportunities for data-intensive study in interdisciplinary domains as a result of the advancement of big data technologies and high-performance computers. Search engines, email spam filters, websites that offer personalized recommendations, banking software that alerts users to suspicious activity, and a plethora of smartphone apps that perform tasks like voice recognition, image recognition, and natural language processing are just a few examples of the online and offline services that have incorporated machine learning in recent years. One of the most crucial areas where machine learning applications still has to be investigated is agriculture, which directly affects people’s well-being. In this article, a literature review on machine learning algorithms used in agriculture is presented. The proposed paper deal with various crop management applications which are categorised into five parts i.e., Weed and pest detection, Plant disease detection, Stress detection in plants, Smart farms or automation in farms and the last one is Crop yield estimation and prediction. The articles’ filtering and categorization show how machine learning may improve agriculture. This article examines machine learning breakthroughs in agriculture. This paper’s findings show that by using novel machine learning approaches, models may achieve improved accuracy and shorter inference time for real-world applications.
This is a preview of subscription content, log in via an institution to check access.
Subscribe and save.
Price includes VAT (Russian Federation)
Instant access to the full article PDF.
Rent this article via DeepDyve
Institutional subscriptions
Data availability.
Data sharing not applicable to this article as no datasets were generated or analysed during the current study
Abade A, Ferreira PA, de Barros Vidal F (2021) Plant diseases recognition on images using convolutional neural networks: A systematic review. Comput Electron Agric. 185. https://doi.org/10.1016/j.compag.2021.106125
Alam M, Alam MS, Roman M, Tufail M, Khan MU, Khan MT. Real-Time Machine-Learning Based Crop/Weed Detection and Classification for Variable-Rate Spraying in Precision Agriculture. In: 2020 7th International Conference on Electrical and Electronics Engineering, ICEEE 2020. Institute of Electrical and Electronics Engineers Inc.; 2020. p. 273–80
Albuquerque CKG, Polimante S, Torre-Neto A, Prati RC (2020) Water spray detection for smart irrigation systems with Mask R-CNN and UAV footage. 2020 IEEE Int Work Metrol Agric For MetroAgriFor 2020 - Proc, 236–240. https://doi.org/10.1109/MetroAgriFor50201.2020.9277542
Alessandrini M, Calero Fuentes Rivera R, Falaschetti L, Pau D, Tomaselli V, Turchetti C (2021) A grapevine leaves dataset for early detection and classification of esca disease in vineyards through machine learning. Data Br. 35
AlZu’bi S, Hawashin B, Mujahed M, Jararweh Y, Gupta BB (2019) An efficient employment of internet of multimedia things in smart and future agriculture. Multimed Tools Appl. 78(20):29581–29605. https://doi.org/10.1007/s11042-019-7367-0
Article Google Scholar
Ang KLM, Seng JKP (2021) Big data and machine learning with hyperspectral information in agriculture. IEEE Access 9:36699–36718. https://doi.org/10.1109/ACCESS.2021.3051196
Appeltans S, Pieters JG, Mouazen AM (2021) Detection of leek white tip disease under field conditions using hyperspectral proximal sensing and supervised machine learning. Comput Electron Agric. 190:106453.Available from https://www.sciencedirect.com/science/article/pii/S0168169921004701 . Accessed 12 Mar 2023
Araus JL, Cairns JE (2014) Field high-throughput phenotyping: The new crop breeding frontier. Trends Plant Sci 19(1):52–61. https://doi.org/10.1016/j.tplants.2013.09.008
Asad MH, Bais A (2020) Weed detection in canola fields using maximum likelihood classification and deep convolutional neural network. Inf Process Agric 7(4):535–545. https://doi.org/10.1016/j.inpa.2019.12.002
Ataş M, Yardimci Y, Temizel A (2012) A new approach to aflatoxin detection in chili pepper by machine vision. Comput Electron Agric 87:129–141
Bakhshipour A, Jafari A (2018) Evaluation of support vector machine and artificial neural networks in weed detection using shape features. Comput Electron Agric 145:153–160
Barbedo JGA (2019) Detection of nutrition deficiencies in plants using proximal images and machine learning: A review. Comput Electron Agric. Elsevier B.V.; 162: 482–92
Benos L, Tagarakis AC, Dolias G, Berruto R, Kateris D, Bochtis D (2021) Machine Learning in Agriculture: A Comprehensive Updated Review. Sensors 21(11):3758. https://doi.org/10.3390/s21113758
Bhange M, Hingoliwala HA (2015) Smart Farming: Pomegranate Disease Detection Using Image Processing. In: Procedia Computer Science. Elsevier; p. 280–8
Bienertova-Vasku J, Lenart P, Scheringer M (2020) Eustress and Distress: Neither Good Nor Bad, but Rather the Same? BioEssays. 42(7)
Boissard P, Martin V, Moisan S (2008) A cognitive vision approach to early pest detection in greenhouse crops. Comput Electron Agric 62(2):81–93
Brinkhoff J, Vardanega J, Robson AJ (2020) Land cover classification of nine perennial crops using sentinel-1 and -2 data. Remote Sens. 12(1)
Cattivelli L et al (2008) Drought tolerance improvement in crop plants: An integrated view from breeding to genomics. F Crop Res 105(1–2):1–14. https://doi.org/10.1016/j.fcr.2007.07.004
Chen M et al (2021) A reinforcement learning approach to irrigation decision-making for rice using weather forecasts. Agric Water Manag. 250(March):106838. https://doi.org/10.1016/j.agwat.2021.106838
Chen Y-R, Chao K, Kim MS. Machine vision technology for agricultural applications. Available from: www.elsevier.com/locate/compag . Accessed 12 Mar 2023
Chen J, Liu Q, Gao L (2021) Deep convolutional neural networks for tea tree pest recognition and diagnosis. Symmetry (Basel) 13(11):1–12. https://doi.org/10.3390/sym13112140
Conrad AO, Li W, Lee DY, Wang GL, Rodriguez-Saona L, Bonello P (2020) Machine learning-based presymptomatic detection of rice sheath blight using spectral profiles. Plant Phenomics. 2020
Cravero A, Sepúlveda S (2021) Use and adaptations of machine learning in big data—applications in real cases in agriculture. Electron 10(5):1–35. https://doi.org/10.3390/electronics10050552
Daniya T, Vigneshwari S (2019) A review on machine learning techniques for rice plant disease detection in agricultural research. Int J Adv Sci Technol 28(13):49–62
Google Scholar
Dawei W, Limiao D, Jiangong N, Jiyue G, Hongfei Z, Zhongzhi H (2019) Recognition pest by image-based transfer learning. J Sci Food Agric 99(10):4524–4531. https://doi.org/10.1002/jsfa.9689
de Castro AI, Torres-Sánchez J, Peña JM, Jiménez-Brenes FM, Csillik O, López-Granados F (2018) An automatic random forest-OBIA algorithm for early weed mapping between and within crop rows using UAV imagery. Remote Sens. 10(2)
Dian Bah M, Hafiane A, Canals R (2018) Deep learning with unsupervised data labeling for weed detection in line crops in UAV images. Remote Sens 10(11):1–22. https://doi.org/10.3390/rs10111690
Etienne A, Saraswat D (2019) Machine learning approaches to automate weed detection by UAV sensors. Int Soc Opt Photonics. 11008
Evstatiev BI, Gabrovska-Evstatieva KG (2021) A review on the methods for big data analysis in agriculture. IOP Conf Ser Mater Sci Eng. 1032(1): https://doi.org/10.1088/1757-899X/1032/1/012053
Friedel CC, Jahn KHV, Sommer S, Rudd S, Mewes HW, Tetko IV (2005) Support vector machines for separation of mixed plant-pathogen EST collections based on codon usage. Bioinformatics 21(8):1383–1388
Ganesh Babu R, Chellaswamy C (2022) Different stages of disease detection in squash plant based on machine learning. J Biosci. 47(1)
Garibaldi-márquez F, Flores G, Mercado-ravell DA, Ramírez-pedraza A, Valentín-coronado LM (2022) Weed Classification from Natural Corn Field-Multi-Plant Images Based on Shallow and Deep Learning. 1–22
Guo Q, Kelly M, Graham CH (2005) Support vector machines for predicting distribution of Sudden Oak Death in California. Ecol Modell 182(1):75–90
Harakannanavar SS, Rudagi JM, Puranikmath VI, Siddiqua A, Pramodhini R (2022) Plant leaf disease detection using computer vision and machine learning algorithms. Glob Transitions Proc 3(1):305–310
Helm JM et al (2020) Machine Learning and Artificial Intelligence: Definitions, Applications, and Future Directions. Curr Rev Musculoskelet Med 13(1):69–76. https://doi.org/10.1007/s12178-020-09600-8
Islam N, Rashid MM, Wibowo S, Xu CY, Morshed A, Wasimi SA, et al. (2021) Early weed detection using image processing and machine learning techniques in an australian chilli farm. Agric. 11(5)
Jansen MA, Potters G (2017) Stress: The Way of Life. Plant Stress Physiology, 2nd edn. CABI, London, UK, pp ix–xiv
Javidan SM, Banakar A, Vakilian KA, Ampatzidis Y (2023) Diagnosis of grape leaf diseases using automatic K-means clustering and machine learning. Smart Agric Technol 3:100081
Jiang Q, Wu G, Tian C, Li N, Yang H, Bai Y, et al. (2021) Hyperspectral imaging for early identification of strawberry leaves diseases with machine learning and spectral fingerprint features. Infrared Phys Technol. 118
Jose A, Nandagopalan S, Venkata CM, Akana S (2021) Artificial Intelligence Techniques for Agriculture Revolution: A Survey. Ann Rom Soc Cell Biol. 25(4): 2580–2597. Available: http://annalsofrscb.ro . Accessed 12 Mar 2023
Jung J, Maeda M, Chang A, Bhandari M, Ashapure A, Landivar-Bowles J (2021) The potential of remote sensing and artificial intelligence as tools to improve the resilience of agriculture production systems. Curr Opin Biotechnol 70:15–22. https://doi.org/10.1016/j.copbio.2020.09.003
Karadağ K, Tenekeci ME, Taşaltın R, Bilgili A (2020) Detection of pepper fusarium disease using machine learning algorithms based on spectral reflectance. Sustain Comput Inform Syst. 28
Kaur N, Devendran V (2020) Novel plant leaf disease detection based on optimize segmentation and law mask feature extraction with SVM classifier. Mater Today Proc
Khan MA, Ali M, Shah M, Mahmood T, Ahmad M, Jhanjhi NZ et al (2021) Machine learning-based detection and classification of walnut fungi diseases. Intell Autom Soft Comput 30(3):771–785
van Klompenburg T, Kassahun A, Catal C (2020) Crop yield prediction using machine learning: A systematic literature review. Comput Electron Agric. Elsevier B.V. Vol. 177
Kong W, Liu F, Zhang C, Bao Y, Yu J, He Y (2014) Fast detection of peroxidase (POD) activity in tomato leaves which infected with Botrytis cinerea using hyperspectral imaging. Spectrochim Acta - Part A Mol Biomol Spectrosc 118:498–502
Kounalakis T, Triantafyllidis GA, Nalpantidis L (2019) Deep learning-based visual recognition of rumex for robotic precision farming. Comput Electron Agric. 165(October). https://doi.org/10.1016/j.compag.2019.104973
Kulkarni P, Karwande A, Kolhe T, Kamble S, Joshi A, Wyawahare M. Plant Disease Detection Using Image Processing and Machine Learning
Kumar KKEK (2022) Detection of rice plant disease using AdaBoostSVM classifier. Agron J 114(4):2213–2229
Article MathSciNet Google Scholar
Lampridi MG, Sørensen CG, Bochtis D (2019) Agricultural sustainability: A review of concepts and methods. Sustain. 11(18). https://doi.org/10.3390/su11185120
Lan Y, Huang Z, Deng X, Zhu Z, Huang H, Zheng Z, et al. (2020) Comparison of machine learning methods for citrus greening detection on UAV multispectral images. Comput Electron Agric. 171
Langemeier M, Dobbins C, Nielsen B, Vyn T, Casteel S, Johnson B (2021) Purdue Crop Cost & Return Guide, Purdue University, 2021
Leonardo MM, Carvalho TJ, Rezende E, Zucchi R, Faria FA (2019) Deep Feature-Based Classifiers for Fruit Fly Identification (Diptera: Tephritidae). Proc - 31st Conf Graph Patterns Images. SIBGRAPI 2018:41–47. https://doi.org/10.1109/SIBGRAPI.2018.00012
Li N, Ren Z, Li D, Zeng L (2020) Review: Automated techniques for monitoring the behaviour and welfare of broilers and laying hens: towards the goal of precision livestock farming. Animal 14(3):617–625. https://doi.org/10.1017/S1751731119002155
Li D, Yang W, Wang S (2010) Classification of foreign fibers in cotton lint using machine vision and multi-class support vector machine. Comput Electron Agric 74(2):274–279
Liakos K, Busato P, Moshou D, Pearson S, Bochtis D (2018) Machine Learning in Agriculture: A Review. Sensors 18(8):2674. https://doi.org/10.3390/s18082674
Lindenthal M, Steiner U, Dehne HW, Oerke EC (2005) Effect of downy mildew development on transpiration of cucumber leaves visualized by digital infrared thermography. Phytopathology 95(3):233–240. https://doi.org/10.1094/PHYTO-95-0233
Liu Y et al (2022) Forest pest identification based on a new dataset and convolutional neural network model with enhancement strategy. Comput Electron Agric. 192(June 2021):106625. https://doi.org/10.1016/j.compag.2021.106625
Loey M, ElSawy A, Afify M (2020) Deep learning in plant diseases detection for agricultural crops: A survey. Int J Serv Sci Manag Eng Technol 11(2):41–58. https://doi.org/10.4018/IJSSMET.2020040103
Mayuri KP, Priya VC (2018) Role of Image Processing and Machine Learning Techniques in Disease Recognition, Diagnosis and Yield Prediction of Crops: a Review. Int J Adv Res Comput Sci. 9(2):975–8887. https://doi.org/10.26483/ijarcs.v9i2.5793
Meng T, Jing X, Yan Z, Pedrycz W (2020) A survey on machine learning for data fusion. Inf Fusion 57:115–129. https://doi.org/10.1016/j.inffus.2019.12.001
Meshram V, Patil K, Meshram V, Hanchate D, Ramkteke SD (2021) Machine learning in agriculture domain: A state-of-art survey. Artif Intell Life Sci 1:100010. https://doi.org/10.1016/j.ailsci.2021.100010 . ( ISSN 2667-3185 )
Milioto A, Lottes P, Stachniss C (2017) Real-time blob-wise sugar beets vs weeds classification for monitoring fields using convolutional neural networks. ISPRS Ann Photogramm Remote Sens Spat Inf Sci 4(2W3):41–48. https://doi.org/10.5194/isprs-annals-IV-2-W3-41-2017
Moshia ME, Newete SW (2019) Mexican poppy (Argemone mexicana) control in cornfield using deep learning neural networks: a perspective. Acta Agric Scand Sect B Soil Plant Sci 69(3):228–234. https://doi.org/10.1080/09064710.2018.1536225
Mourtzinis S, Esker PD, Specht JE et al (2021) Advancing agricultural research using machine learning algorithms. Sci Rep 11(1):17879. https://doi.org/10.1038/s41598-021-97380-7
Myers SS et al (2017) Climate Change and Global Food Systems: Potential Impacts on Food Security and Undernutrition. Annu Rev Public Health 38(December):259–277. https://doi.org/10.1146/annurev-publhealth-031816-044356
Neelakantan P (2022) Analyzing the best machine learning algorithm for plant disease classification. Mater Today Proc
Nilsson H-E (1995) Remote sensing and image analysis in plant pathology. Available: www.annualreviews.org . Accessed 17 Mar 2023
Ning X, Tian W, Yu Z, Li W, Bai X, Wang Y (2022) HCFNN: High-order coverage function neural network for image classification. Pattern Recog 131:108873. https://doi.org/10.1016/j.patcog.2022.108873
Ning X, Xu S, Nan F, Zeng Q, Wang C, Cai W, Li W, Jiang Y (2022) Face editing based on facial recognition features. IEEE Trans Cogn Dev Syst 14(5):1547–1558. https://doi.org/10.1109/TCDS.2022.3182650
Oppermann R, Paracchini M (2012) HNV Farming–Central to European Cultural Landscapes and Biodiversity. High Nature Value Farming in Europe: 35 European Countries—Experiences and Perspectives; Verlag Regionalkultur: Ubstadt-Weiher, Germany
Ouhami M, Hafiane A, Es-Saady Y, El Hajji M, Canals R (2021) Computer vision, IoT and data fusion for crop disease detection using machine learning: A survey and ongoing research. Remote Sensing. MDPI AG, Vol. 13
Ozyurp B, Sunol AK, Camurdan MC, Mogilp P, Hall LO (1998) Chemical plant fault diagnosis through a hybrid symbolic-connectionist machine learning approach. Comput Chem Eng 22:299–321
Partel V, Charan Kakarla S, Ampatzidis Y (2019) Development and evaluation of a low-cost and smart technology for precision weed management utilizing artificial intelligence. Comput Electron Agric. 157(December 2018):339–350. https://doi.org/10.1016/j.compag.2018.12.048
Patrício DI, Rieder R (2018) Computer vision and artificial intelligence in precision agriculture for grain crops: A systematic review. Comput Electron Agric 153(August):69–81. https://doi.org/10.1016/j.compag.2018.08.001
Peng H, Li Z, Zhou Z, Shao Y (2022) Weed detection in paddy field using an improved RetinaNet network. Comput Electron Agric. 199:107179. https://doi.org/10.1016/J.COMPAG.2022.107179
Pérez AJ, Pez FL, Benlloch JV, Christensen S (2000) Colour and shape analysis techniques for weed detection in cereal fields. Computers and Electronics in Agriculture. Vol. 25. Available from: www.elsevier.com/locate/compag . Accessed 17 Mar 2023
Prasad BR, Ramashri T, Naidu KR (2020) Vectored machine learning rearing process: Early Detection of leaf diseases. J Sci Ind Res 79(7):619–625
Pritam Patil MC, Patil DD, Subramanium P (2020) Detection and Identification of Rice Leaf Diseases using Multiclass SVM. Int Res J Eng Technol. Available from: www.irjet.net . Accessed 17 Mar 2023
Pushpanathan K, Hanafi M, Mashohor S, FazlilIlahi WF (2021) Machine learning in medicinal plants recognition: a review. Artif Intell Rev 54(1):305–327. https://doi.org/10.1007/s10462-020-09847-0
Raza SEA, Prince G, Clarkson JP, Rajpoot NM (2015) Automatic detection of diseased tomato plants using thermal and stereo visible light images. PLoS One. 10(4)
Römer C, Bürling K, Hunsche M, Rumpf T, Noga G, Plümer L (2011) Robust fitting of fluorescence spectra for pre-symptomatic wheat leaf rust detection with Support Vector Machines. Comput Electron Agric 79(2):180–188
Rosegrant MW, Ringler C, Zhu T (2009) Water for agriculture: Maintaining food security under growing scarcity. Annu Rev Environ Resour 34:205–222
Rumpf T, Mahlein AK, Steiner U, Oerke EC, Dehne HW, Plümer L (2010) Early detection and classification of plant diseases with Support Vector Machines based on hyperspectral reflectance. Comput Electron Agric 74(1):91–99
Saggi MK, Jain S (2019) Reference evapotranspiration estimation and modeling of the Punjab Northern India using deep learning. Comput Electron Agric 156:387–398. https://doi.org/10.1016/j.compag.2018.11.031
Saleem R, Shah JH, Sharif M, Yasmin M, Yong HS, Cha J (2021) Mango leaf disease recognition and classification using novel segmentation and vein pattern technique. Appl Sci. 11(24)
Samuel AL (1959) Some Studies in Machine Learning Using the Game of Checkers. IBM J Res Dev 44(1):206–226. https://doi.org/10.1147/rd.441.0206
dos Santos Ferreira A, Freitas DM, da Silva GG, Pistori H, Folhes MT (2019) Unsupervised deep learning and semi-automatic data labeling in weed discrimination. Comput Electron Agric. 165. https://doi.org/10.1016/j.compag.2019.104963
Shrivastava VK, Pradhan MK (2021) Rice plant disease classification using color features: a machine learning paradigm. J Plant Pathol 103(1):17–26
Silva DM, Bernardin T, Fanton K, Nepaul R, Pádua L, Sousa JJ, et al. (2021) Automatic detection of Flavescense Dorée grapevine disease in hyperspectral images using machine learning. In: Procedia Computer Science. Elsevier B.V.; 125–32
Sobiyaa P, Jayareka KS, Maheshkumar K, Naveena S, Rao KS (2022) Paddy disease classification using machine learning technique. Mater Today Proc
Soltani N et al (2016) Potential Corn Yield Losses from Weeds in North America. Weed Technol 30(4):979–984. https://doi.org/10.1614/wt-d-16-00046.1
Song X, Zhang G, Liu F, Li D, Zhao Y, Yang J (2016) Modeling spatio-temporal distribution of soil moisture by deep learning-based cellular automata model. J Arid Land 8(5):734–748. https://doi.org/10.1007/s40333-016-0049-0
Sonka ST (2016) Big data: Fueling the next evolution of agricultural innovation. J Innov Manag 4(1):114–136. https://doi.org/10.24840/2183-0606_004.001_0008
Sørensen CAG, Kateris D, Bochtis D (2019) ICT Innovations and Smart Farming. Commun Comput Inf Sci 953:1–19. https://doi.org/10.1007/978-3-030-12998-9_1
Sowmya BJ, Shetty C, Seema S, Srinivasa KG (2020) Chapter 7 - Utility system for premature plant disease detection using machine learning. Siddhartha Bhattacharyya VSDGAK, editor. 149–172
Su WH (2020) Advanced machine learning in point spectroscopy, rgb-and hyperspectral-imaging for automatic discriminations of crops and weeds: A review. Smart Cities 3(3):767–792. https://doi.org/10.3390/smartcities3030039
Subeesh A et al (2022) Deep convolutional neural network models for weed detection in polyhouse grown bell peppers. Artif Intell Agric 6:47–54. https://doi.org/10.1016/j.aiia.2022.01.002
Sundmaeker H, Verdouw CN, Wolfert J (2016) Freire LP (2016) Internet of Food and Farm 2020. In: Vermesan O, Friess P (eds) Digitising the Industry. River Publishers, Ljubljana, Slovenia, pp 129–150
Sunil GC, Zhang Y, Koparan C, Ahmed MR, Howatt K, Sun X (2022) Weed and crop species classification using computer vision and deep learning technologies in greenhouse conditions. J Agric Food Res. 9(June):100325. https://doi.org/10.1016/j.jafr.2022.100325
Tang J, Arvor D, Corpetti T, Tang P (2021) Mapping center pivot irrigation systems in the southern amazon from sentinel-2 images. Water (Switzerland) 13(3):1–17. https://doi.org/10.3390/w13030298
Thenmozhi K, Reddy US (2019) Crop pest classification based on deep convolutional neural network and transfer learning. Comput Electron Agric. 164(June):104906. https://doi.org/10.1016/j.compag.2019.104906
Tian K, Li J, Zeng J, Evans A, Zhang L (2019) Segmentation of tomato leaf images based on adaptive clustering number of K-means algorithm. Comput Electron Agric.165
Vázquez-Hernández MC, Parola-Contreras I, Montoya-Gómez LM, Torres-Pacheco I, Schwarz D, Guevara-González RG (2019) Eustressors: Chemical and physical stress factors used to enhance vegetables production. Sci Hortic (Amsterdam) 250:223–229. https://doi.org/10.1016/j.scienta.2019.02.053
Virnodkar SS, Pachghare VK, Patil VC, Jha SK (2020) Remote sensing and machine learning for crop water stress determination in various crops: a critical review. 21(5). Springer US. https://doi.org/10.1007/s11119-020-09711-9
Wäldchen J, Rzanny M, Seeland M, Mäder P (2018) Automated plant species identification—Trends and future directions. PLoS Comput Biol 14(4):1–19. https://doi.org/10.1371/journal.pcbi.1005993
Wang C, Wang X, Zhang J, Zhang L, Bai X, Ning X, Zhou J, Hancock E (2022) Uncertainty Estimation for Stereo Matching Based on Evidential Deep Learning. Pattern Recog 124:108498. https://doi.org/10.1016/j.patcog.2021.108498
Wang A, Xu Y, Wei X, Cui B (2020) Semantic Segmentation of Crop and Weed using an Encoder-Decoder Network and Image Enhancement Method under Uncontrolled Outdoor Illumination. IEEE Access 8:81724–81734. https://doi.org/10.1109/ACCESS.2020.2991354
Wang A, Zhang W, Wei X (2019) A review on weed detection using ground-based machine vision and image processing techniques. Comput Electron Agric 158(January):226–240. https://doi.org/10.1016/j.compag.2019.02.005
Wen Z, Tao Y (1999) Building a rule-based machine-vision system for defect inspection on apple sorting and packing lines. Expert Syst Appl 16(3):307–313
Xu G, Zhang F, Shah SG, Ye Y, Mao H (2011) Use of leaf color images to identify nitrogen and potassium deficient tomatoes. Pattern Recognit Lett 32(11):1584–1590. https://doi.org/10.1016/j.patrec.2011.04.020
Yashodha G, Shalini D (2020) An integrated approach for predicting and broadcasting tea leaf disease at early stage using IoT with machine learning - A review. Mater Today Proc. 37(Part 2):484–488. https://doi.org/10.1016/j.matpr.2020.05.458
Yuan Y, Chen L, Wu H, Li L (2022) Advanced agricultural disease image recognition technologies: A review. Inf Process Agric 9(1):48–59. https://doi.org/10.1016/j.inpa.2021.01.003
Zamani AS, Anand L, Rane KP, Prabhu P, Buttar AM, Pallathadka H, et al. (2022) Performance of Machine Learning and Image Processing in Plant Leaf Disease Detection. J Food Qual. 2022
Zecca F (2019) The Use of Internet of Things for the Sustainability of the Agricultural Sector: The Case of Climate Smart Agriculture. Int J Civ Eng Technol, 10(03): 494–501: http://www.iaeme.com/IJCIET/index.asp
Zhou J, Fu X, Zhou S, Zhou J, Ye H, Nguyen HT (2019) Automated segmentation of soybean plants from 3D point cloud using machine learning. Comput Electron Agric 162:143–153
Zhou R, Kaneko S, Tanaka F, Kayamori M, Shimizu M (2014) Disease detection of Cercospora Leaf Spot in sugar beet by robust template matching. Comput Electron Agric 108:58–70
Zou K, Ge L, Zhou H, Zhang C, Li W (2021) Broccoli seedling pest damage degree evaluation based on machine learning combined with color and shape features. Inf Process Agric 8(4):505–514
Zubler AV, Yoon JY (2020) Proximal Methods for Plant Stress Detection Using Optical Sensors and Machine Learning. Biosensors. 10(12), https://doi.org/10.3390/BIOS10120193
Download references
Authors and affiliations.
Computer Science and Engineering, NIT, Hamirpur, 177005, HP, India
Ishana Attri, Lalit Kumar Awasthi & Teek Parval Sharma
You can also search for this author in PubMed Google Scholar
Correspondence to Ishana Attri .
Conflicts of interests/competing interests.
All authors certify that they have no affiliations with or involvement in any organization or entity with any financial interest or non-financial interest in the subject matter or materials discussed in this manuscript.
Publisher's note.
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Lalit Kumar Awasthi and Teek Parval Sharma contributed equally to this work.
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
Reprints and permissions
Attri, I., Awasthi, L.K. & Sharma, T.P. Machine learning in agriculture: a review of crop management applications. Multimed Tools Appl 83 , 12875–12915 (2024). https://doi.org/10.1007/s11042-023-16105-2
Download citation
Received : 16 September 2022
Revised : 03 May 2023
Accepted : 26 June 2023
Published : 01 July 2023
Issue Date : February 2024
DOI : https://doi.org/10.1007/s11042-023-16105-2
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative
You are accessing a machine-readable page. In order to be human-readable, please install an RSS reader.
All articles published by MDPI are made immediately available worldwide under an open access license. No special permission is required to reuse all or part of the article published by MDPI, including figures and tables. For articles published under an open access Creative Common CC BY license, any part of the article may be reused without permission provided that the original article is clearly cited. For more information, please refer to https://www.mdpi.com/openaccess .
Feature papers represent the most advanced research with significant potential for high impact in the field. A Feature Paper should be a substantial original Article that involves several techniques or approaches, provides an outlook for future research directions and describes possible research applications.
Feature papers are submitted upon individual invitation or recommendation by the scientific editors and must receive positive feedback from the reviewers.
Editor’s Choice articles are based on recommendations by the scientific editors of MDPI journals from around the world. Editors select a small number of articles recently published in the journal that they believe will be particularly interesting to readers, or important in the respective research area. The aim is to provide a snapshot of some of the most exciting work published in the various research areas of the journal.
Original Submission Date Received: .
Find support for a specific problem in the support section of our website.
Please let us know what you think of our products and services.
Visit our dedicated information section to learn more about MDPI.
A review of machine learning techniques in agroclimatic studies.
2.1. ml’s techniques in agricultural practices, 2.2. distinguishing between ml and dl in agricultural applications, 2.3. enhancing ml accessibility in agriculture with automl, 3. applications of ml and dl in agriculture, 4. search, screening, and review process, 5. results and discussion, 5.1. algorithms and metrics used in agriculture applications, 5.2. challenges and best practices in applying ml to agriculture, 5.3. transparency gaps in data processing for agricultural ml, 5.4. challenges in model architecture and training transparency, 5.5. enhancing replicability and scalability in agriculture through automl, 5.6. future research directions, 6. conclusions, author contributions, data availability statement, conflicts of interest.
Click here to enlarge figure
Reference | ML Technique | Agricultural Application |
---|---|---|
[ , ] | Decision Tree | Crop Yield Prediction, Disease Detection, Soil Assessment |
[ , , ] | Random Forest | Crop Yield Prediction, Disease Detection, Soil Assessment |
[ , ] | Extreme Gradient Boosting | Crop Yield Prediction, Soil Assessment |
[ , ] | Naive Bayes | Crop Yield Prediction, Disease Detection |
[ , ] | K-Nearest Neighbors | Crop Yield Prediction, Disease Detection |
[ ] | Ensemble Traditional ML Models | Crop Yield Prediction |
[ ] | Multi-Linear Regressor | Crop Yield Prediction |
[ ] | RNN | Crop Yield Prediction |
[ ] | LSTM | Crop Yield Prediction |
[ ] | Support Vector Regression | Crop Yield Prediction |
[ , , , ] | CNN | Crop Yield Prediction, Disease Detection |
[ ] | GNN | Crop Yield Prediction |
[ ] | U-Net | Crop Yield Prediction |
[ , , ] | ANN | Crop Yield Prediction, Disease Detection |
[ ] | DBSCAN | Crop Yield Prediction |
[ , ] | Support Vector Machine | Crop Yield Prediction, Disease Detection, Smart Farming |
[ ] | Vision Transformers | Disease Detection |
[ ] | VGG-RNN Hybrid | Soil Assessment |
[ , ] | MLP | Soil Assessment |
The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
Tamayo-Vera, D.; Wang, X.; Mesbah, M. A Review of Machine Learning Techniques in Agroclimatic Studies. Agriculture 2024 , 14 , 481. https://doi.org/10.3390/agriculture14030481
Tamayo-Vera D, Wang X, Mesbah M. A Review of Machine Learning Techniques in Agroclimatic Studies. Agriculture . 2024; 14(3):481. https://doi.org/10.3390/agriculture14030481
Tamayo-Vera, Dania, Xiuquan Wang, and Morteza Mesbah. 2024. "A Review of Machine Learning Techniques in Agroclimatic Studies" Agriculture 14, no. 3: 481. https://doi.org/10.3390/agriculture14030481
Article access statistics, further information, mdpi initiatives, follow mdpi.
Subscribe to receive issue release notifications and newsletters from MDPI journals
Machine learning applications in agriculture: a review for opportunities, challenges, and outcomes.
Application of machine learning in agriculture: recent trends and future research avenues, application of machine learning techniques in modern agriculture: a review, artificial intelligence technology in the agricultural sector: a systematic literature review, machine learning in agriculture domain: a state-of-art survey, comprehensive survey on applications of internet of things, machine learning and artificial intelligence in precision agriculture, crop prediction from soil parameters using light ensemble learning model, smart farming prediction models for precision agriculture: a comprehensive survey.
205 references, machine learning in agriculture: a review, a comprehensive review on automation in agriculture using artificial intelligence, sensors driven ai-based agriculture recommendation model for assessing land suitability, machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: a review, crop yield prediction and efficient use of fertilizers, review—machine learning techniques in wireless sensor network based precision agriculture, a systematic literature review on machine learning applications for sustainable agriculture supply chain performance, iot and machine learning approaches for automation of farm irrigation system, predictive analysis to improve crop yield using a neural network model, intelligent irrigation system using artificial intelligence and machine learning: a comprehensive review, related papers.
Showing 1 through 3 of 0 Related Papers
IMAGES
VIDEO
COMMENTS
Abstract: The digital transformation of agriculture has evolved various aspects of management into. artificial intelligent systems for the sake of making value from the ever-increasing data ...
Abstract: Machine learning has emerged with big data technologies and high-performance computing. to create new opportunities for data intensive science in the multi-disciplinary agri-technologies ...
Rising global population and climate change realities dictate that agricultural productivity must be accelerated. Results from current traditional research approaches are difficult to extrapolate ...
1.1. General Context of Machine Learning in Agriculture. Modern agriculture has to cope with several challenges, including the increasing call for food, as a consequence of the global explosion of earth's population, climate changes [], natural resources depletion [], alteration of dietary choices [], as well as safety and health concerns [].As a means of addressing the above issues, placing ...
Agriculture is considered as a backbone of economy and source of employment in the developing countries like India. Agriculture contributes 15.4% in the GDP of India. Agriculture activities are broadly categorized into three major areas: pre-harvesting, harvesting and post harvesting. Advancement in area of machine learning has helped improving ...
Section 6 (Challenges and Research Opportunities) discusses the challenges associated with implementing ML in agricultural systems. Finally, Section 7 (Conclusions, Limitations, and Future Work) summarises the main findings of the present SLR and how they contribute to the current understanding of ML in agriculture. 2.
This paper is divided into 6 main sections: The first part is the introductory part in which the basic introduction about machine learning applications in agriculture is dis-cussed. Section 2 describes the methods and material used in this review and the criteria for how to choose the research work for this paper.
Abstract: Machine learning has emerged with big data technologies and high-performance computing to create new opportunities for data intensive science in the multi-disciplinary agri-technologies domain. In this paper, we present a comprehensive review of research dedicated to applications of machine learning in agricultural production systems.
View PDF HTML (experimental) Abstract: Food production is a vital global concern and the potential for an agritech revolution through artificial intelligence (AI) remains largely unexplored. This paper presents a comprehensive review focused on the application of machine learning (ML) in agriculture, aiming to explore its transformative potential in farming practices and efficiency enhancement.
Machine Learning In Agriculture: A Review. May 2021. Authors: Azeem Ayaz Mirani. Shaheed Benazir Bhutto University, Shaheed Banziabad Sindh pakistan. Engr Dr Muhammad Suleman Memon. Department of ...
some papers have explored various ML models, a comprehensive review is still needed in this emerging field. This paper aims to provide that review, focusing on the unique features and applications of recent ML models in agriculture. The organization of the paper is as follows: Section2begins by outlining the scope of the studies covered in this ...
In this study, we give a thorough analysis of machine learning use in agriculture. There are several pertinent publications that highlight important and distinctive characteristics of well-known ML models. Our paper basically deals with the Our research examines the expansion of machine learning methods in agriculture over the last two decades.
Machine learning has emerged with big data technologies and high-performance computing to create new opportunities for data intensive science in the multi-disciplinary agri-technologies domain. In this paper, we present a comprehensive review of research dedicated to applications of machine learning in agricultural production systems. The works analyzed were categorized in (a) crop management ...
A comprehensive review focused on the application of machine learning (ML) in agriculture, aiming to explore its transformative potential in farming practices and efficiency enhancement and introduces the concept of ML and delving into the realm of smart agriculture. Food production is a vital global concern and the potential for an agritech revolution through artificial intelligence (AI ...
The practice of cultivating the soil, producing crops, and keeping livestock is referred to as farming. Agriculture is critical to a country's economic development. Nearly 58 percent of a country's primary source of livelihood is farming. Farmers till date had adopted conventional farming techniques. These techniques were not precise thus ...
Progress in agricultural productivity and sustainability hinges on strategic investments in technological research. Evolving technologies such as the Internet of Things, sensors, robotics, Artificial Intelligence, Machine Learning, Big Data, and Cloud Computing are propelling the agricultural sector towards the transformative Agriculture 4.0 paradigm. The present systematic literature review ...
The interplay of machine learning (ML) and deep learning (DL) within the agroclimatic domain is pivotal for addressing the multifaceted challenges posed by climate change on agriculture. This paper embarks on a systematic review to dissect the current utilization of ML and DL in agricultural research, with a pronounced emphasis on agroclimatic impacts and adaptation strategies.
Only journal papers were considered eligible that were published within 2018-2020. The results indicated that this topic pertains to different dis-ciplines that favour convergence research at the international level. Furthermore, crop management was observed to be at the centre of attention. A plethora of machine learning algorithms were used,
The paper synthesizes recent research and developments in AI applications, covering key areas such as crop monitoring, resource management, decision support systems, and automation. The adoption of AI-driven techniques, including machine learning, computer vision, and sensor technologies, is reshaping traditional farming methods by providing ...
A systematic review of ML applications in the field of agriculture shows how knowledge-based agriculture can improve the sustainable productivity and quality of the product. Agriculture plays a vital role in the economic growth of any country. With the increase of population, frequent changes in climatic conditions and limited resources, it becomes a challenging task to fulfil the food ...
Evolving technologies such as the Internet of Things, sensors, robotics, Artificial Intelligence, Machine Learning, Big Data, and Cloud Computing are propelling the agricultural sector towards the ...
21.1 Introduction. ticial intelligence (AI) is the study of too. s and technologies which are used tofisolve tasks that require human intelligence. Tasks such as natural language under. standing, processing, generation, visual perception, decision making, and many. more. Machine learning and deep learning are the two most widely used AI ...
advantages of using machine learning in agriculture and contributing to a more systematic research on this topic. Keywords: machine learning; crop management; water management; soil management; livestock management; artificial intelligence; precision agriculture; precision livestock farming 1. Introduction 1.1. General Context of Machine ...
Request PDF | On Apr 26, 2024, Murugesan Mohana Keerthi and others published Integrating IoT and Machine Learning for Smart Irrigation Systems in Agriculture | Find, read and cite all the research ...