Empowering Agrifood System with Artificial Intelligence: A Survey of the Progress, Challenges and Opportunities

Tao Chen^{1 ∗}, Liang Lv^{1 ∗}, Di Wang^{2 ∗}, Jing Zhang^{23 †}, Yue Yang¹ , Zeyang Zhao¹ , Chen Wang¹ , Xiaowei Guo¹ , Hao Chen¹ , Qingye Wang¹ , Yufei Xu³ , Qiming Zhang³ , Bo Du^{2 †}, Liangpei Zhang² , Dacheng Tao⁴

¹ China University of Geosciences, ² Wuhan University, ³ The University of Sydney, ⁴ Nanyang Technological University

^∗ Equal contribution, ^† Corresponding author

Update | Introduction | Mindmaps | Methods | Reference

Update

2024.09.26 The survey is accepted by ACM Computing Surveys, and the arXiv is updated!

2023.05.03 The manuscript is post on arXiv!

Introduction

Artificial intelligence (AI) techniques such as deep learning (DL) have demonstrated their strong abilities in various areas, including language, vision, remote sensing (RS), and agrifood systems applications. In this study, we thoroughly review how AI techniques can transform agrifood systems and contribute to the modern agrifood industry. Firstly, we summarize the data acquisition methods in agrifood systems, including acquisition, storage, and processing techniques. Secondly, we present a progress review of AI methods in agrifood systems, specifically in agriculture, animal husbandry, and fishery, covering topics such as agrifood classification, growth monitoring, yield prediction, and quality assessment. We hope this survey could reveal the immense potential of AI in agrifood systems, stimulate discussions on the reasonable use of AI technologies in agriculture, and inspire further research and practical implementation of AI in agriculture, with the goal of enhancing the productivity, efficiency, safety, and sustainability of our agrifood systems.

Fig.1 - The relationship between this (white lines) and other surveys, which are shown as black dots.

Fig.2 - Different AI methods are suitable to various agrifood applications.

The deployment of AI technology in agrifood systems has also activated many opportunities, where cutting-edge exploration experiences in AI fields, such as multimodal and scalable models can be leveraged by agriculture applications, improving software and hardware infrastructures simultaneously. 

Fig.3 - AI models enable reading agrifood product information. The results are obtained by DeepSolo with ViTAEv2.

Architectures

Data Source, Storage and Preprocessing

Applications for Data and Method Selection

AI Methods for Agrifood System

Agrifood Classification

Year	Input	Methods	Paper Title	Pub.
2014	ASTER	SVM+SVM	Object-based image classification of summer crops with machine learning methods	Remote Sensing
2014	Hyperion sensor	ELM, OP-ELM, BayesNet, SVM, 1-NN, C4.5	Extreme learning machines for soybean classification in remote sensing hyperspectral images	Neurocomputing
2017	Landsat 8, Sentinel-1	MLP, ENN, 1D-CNNs, 2D-CNNs	Deep learning classification of land cover and crop types using remote sensing data	IEEE Geoscience And Remote Sensing Letters
2017	MODIS, Landsat TM, Landsat ETM+	Improved algorithm to identify flooding and transplanting of paddy rice fields	Spatiotemporal patterns of paddy rice croplands in China and India from 2000 to 2015	Science of the Total Environment
2018	Onsite devices, AVIRIS	ND-SVM, RoSVM, RF	Feature-ensemble-based novelty detection for analyzing plant hyperspectral datasets	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
2018	Sentinel-1, Sentinel-2	Hierarach RF	Synergistic use of radar Sentinel-1 and optical Sentinel-2 imagery for crop mapping: A case study for Belgium	Remote Sensing
2019	Sentinel-1	1D CNNs, LSTM RNNs, GRU RNNs, RF	Evaluation of three deep learning models for early crop classification using sentinel-1A imagery time series — A case study in Zhanjiang, China	Remote sensing
2019	Sentinel-2	Polynomial-SVM, RBF-SVM, RF, ANN, CART-DT	Mapping sugar cane in complex land scapes by integrating multi-temporal Sentinel-2 images and machine learning algorithms	Land Use Policy
2020	Landsat Analysis Ready Data	DCM, Transformer, MLP, RF	Deep Crop Mapping: A multi-temporal deep learning approach with improved spatial generalizability for dynamic corn and soybean mapping	Remote Sensing of Environment
2020	Onsite devices, RADARSAT-2, VENµS	Conv1D, MLP, LSTM, XGBoost, RF, SVM	Synergistic use of multi-temporal RADARSAT-2 and VEN𝜇S data for crop classification based on 1D convolutional neural network	Remote Sensing
2021	Zhuhai-1, Sentinel-2, Sentinel-1	DOCC	DOCC: Deep one-class crop classification via positive and unlabeled learning for multi-modal satellite imagery	International Journal of Applied Earth Observations and Geoinformation
2021	UAV	DeeplabV3+, PSPNet, SegNet, U-Net	Depth semantic segmentation of tobacco planting areas from unmanned aerial vehicle remote sensing images in plateau mountains	Journal of Spectroscopy
2022	Landsat 8, Sentinel-2, Onsite devices	KNN, RF, SVM, GBDT	Remote Sensing and Machine Learning Modeling to Support the Identification of Sugarcane Crops	IEEE Access
2022	UAV	ViT B-16, ViT B-32, EfficientNet B0, EfficientNet B1, ResNet 50	Transformer neural network for weed and crop classification of high resolution UAV images	Remote sensing
2022	UAV	HSI-transunet, SegNet, SETR, UNet, TransUNet	HSI-TransUNet: a transformer based semantic segmentation model for crop mapping from UAV hyperspectral imagery	Computers and Electronics in Agriculture

Agrifood Growth Monitoring

Year	Input	Methods	Paper Title	Pub.
2012	Manned aircraft	LME regression, RF, SVR, Cu	Forest biomass estimation from airborne LiDAR data using machine learning approaches	Remote Sensing of Environment
2012	Laboratory conditions	MLR, PLSR	Detecting powdery mildew of winter wheat using leaf level hyperspectral measurements	Computers and Electronics in Agriculture
2013	Onsite devices	DDA	Development of a deterministic downscaling algorithm for remote sensing soil moisture footprint using soil and vegetation classifications	Water Resources Research
2014	UAV	PROSAIL	Inversion of the PROSAIL model to estimate leaf area index of maize, potato, and sunflower fields from unmanned aerial vehicle hyperspectral data	International Journal of Applied Earth Observation and Geoinformation
2015	UAV	K-means, Rk-means, SSSVM, KNN, LINSVM, SVM	A semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method	Applied Soft Computing
2016	HJ satellite	SVR, ANN, RF	Estimation of biomass in wheat using random forest regression algorithm and remote sensing data	The Crop Journal
2017	Sentinel-2, Landsat-8	OPTRAM, TOTRAM	The optical trapezoid model: A novel approach to remote sensing of soil moisture applied to Sentinel-2 and Landsat-8 observations	Remote Sensing of Environment
2017	Onsite devices	SDA, FDA, kNN	Field detection of anthracnose crown rot in strawberry using spectroscopy technology	Computers and Electronics in Agriculture
2018	Onsite devices	SVR, MLR	Evaluation of citrus gummosis disease dynamics and predictions with weather and inversion based leaf optical model	Computers and Electronics in Agriculture
2018	Onsite devices	ND-SVM, RoSVM	Feature-ensemble-based novelty detection for analyzing plant hyperspectral datasets	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
2018	Manned aircraft	LM, RF, NN, SVMR, SVML, GBM, CU	Integration of high resolution remotely sensed data and machine learning techniques for spatial prediction of soil properties and corn yield	Computers and Electronics in Agriculture
2019	UAV, Onsite devices	ANN, SVM, RF	Modeling alpine grassland forage phosphorus based on hyperspectral remote sensing and a multi-factor machine learning algorithm in the east of Tibetan Plateau,China	ISPRS Journal of Photogrammetry and Remote Sensing
2019	Landsat-8	SLR, PLSR, SVM, ANN, OK	Prediction of soil organic carbon based on Landsat 8 monthly NDVI data for the Jianghan Plain in Hubei Province, China	Remote Sensing
2019	UAV	MLR, SVM, ANN, RF	Modeling maize above-ground biomass based on machine learning approaches using UAV remote-sensing data	Plant Methods
2019	UAV	OLS, SVM, BP, RF	Estimating maize above-ground biomass using 3D point clouds of multi-source unmanned aerial vehicle data at multi-spatial scales	Remote Sensing
2020	Onsite devices	HOG, SURF, GLCM, ANN, SVM	Effect of directional augmentation using supervised machine learning technologies: A case study of strawberry powdery mildew detection	Biosystems Engineering
2021	UAV	NN, GLM, GBM, DRF	Estimation of root zone soil moisture from ground and remotely sensed soil information with multi sensor data fusion and automated machine learning	Remote Sensing of Environment
2021	RADARSAT-2	PCC, SVM-RFE, RF, SVR, GBRT	Estimating soil moisture over winter wheat fields during growing season using machine-learning methods	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
2021	UAV	PLSR, ANN, RF, SVM	Estimation of paddy rice nitrogen content and accumulation both at leaf and plant levels from UAV hyperspectral imagery	Remote Sensing
2021	SMAPVEX-12	SVR, RF, GBDT, XGBoost	Deep learning-based estimation of crop biophysical parameters using multi-source and multi-temporal remote sensing observations	Agronomy
2021	Onsite devices	LDA, K-NN, SVM	Spectroscopic detection of rice leaf blast infection from asymptomatic to mild stages with integrated machine learning and feature selection	Remote Sensing of Environment
2022	Onsite devices	RFR, SLR	Improving Estimation of Winter Wheat Nitrogen Status Using Random Forest by Integrating Multi-Source Data Across Different Agro-Ecological Zones	Frontiers in Plant Science
2022	UAV	PLSR, kNN, RFR, BPNN	Estimation of soil moisture content under high maize canopy coverage from UAV multimodal data and machine learning	Agricultural Water Management
2022	UAV	SVR, ELM, RF	An assessment of multi-view spectral information from UAV-based color-infrared images for improved estimation of nitrogen nutrition status in winter wheat	Precision Agriculture
2022	UAV	CNN+BA, CNN+PSO, CNN+MAML	Weed density extraction based on few-shot learning through UAV remote sensing RGB and multispectral images in ecological irrigation area	Frontiers in Plant Science
2022	UAV	EfficientNet, ResNet, ViT	Transformer neural network for weed and crop classification of high resolution UAV images	Remote Sensing

Agrifood Yield Prediction

Year	Input	Methods	Paper Title	Pub.
2013	Onsite devices	SMF	MODIS-based corn grain yield estimation model incorporating crop phenology information	Remote Sensing of Environment
2016	AVHRR, MODIS	MLR, BNN, MOB	Crop yield forecasting on the Canadian Prairies by remotely sensed vegetation indices and machine learning methods	Agricultural and Forest Meteorology
2019	USDA-NASS, SMAP, MODIS	PLR, KRR	Synergistic integration of optical and microwave satellite data for crop yield estimation	Remote Sensing of Environment
2019	Onsite devices	LR, SVR, ANN, RF, SGB	California almond yield prediction at the orchard level with a machine learning approach	Frontiers in Plant Science
2019	Onsite devices, NASA LPDAAC, BMO	STC	An approach to forecast grain crop yield using multi-layered, multi-farm data sets and machine learning	Precision Agriculture
2019	Onsite devices, Sentinel-2	MR, RF, SVM	Monitoring within-field variability of corn yield using Sentinel-2 and machine learning techniques	Remote Sensing
2019	MODIS	LASSO, RF, XGBoost, LSTM	Combining optical, fluorescence, thermal satellite, and environmental data to predict county-level maize yield in China using machine learning approaches	Remote Sensing
2019	UAV	CNN	Crop yield prediction with deep convolutional neural networks	Computers and Electronics in Agriculture
2020	UAV	PLSR, RFR, SVM, DNN-F1, DNN-F2	Soybean yield prediction from UAV using multimodal data fusion and deep learning	Remote Sensing of Environment
2020	USDA NASA, MODIS, PRISM	OLS, LASSO, SVM, RF, AdaBoost, DNN	Combining multi-source data and machine learning approaches to predict winter wheat yield in the conterminous United States	Remote Sensing
2020	Onsite devices, UAV	LR, MLR, SMLR, PLSR, ANN, RF	Wheat growth monitoring and yield estimation based on multi-rotor unmanned aerial vehicle	Remote Sensing
2020	MODIS, Onsite devices, SILO	RF, CU, XB, SVMl, SVMr, MLP, MARS, GP, kNN	Estimating wheat yields in Australia using climate records, satellite image time series and machine learning methods	ISPRS Journal of Photogrammetry and Remote Sensing
2020	MOD13Q1	GPR, SVM, RF	Prediction of winter wheat yield based on multi-source data and machine learning in China	Remote Sensing
2020	MODIS	OLS, RF, LSTM	Satellite-based soybean yield forecast: Integrating machine learning and weather data for improving crop yield prediction in southern Brazil	Agricultural and Forest Meteorology
2020	UAV	Pretrained CNN, CNN-LSTM, ConvLSTM, 3D-CNN	Crop yield prediction using multitemporal UAV data and spatio-temporal deep learning models	Remote Sensing
2020	AVHRR, SoilGrids	LSTM-CNN, RF, SVM, LR	Winter wheat yield prediction at county level and uncertainty analysis in main wheat-producing regions of China with deep learning approaches	Remote Sensing
2021	MODIS	DT, RF, SVM, LSTM, 2D-CNN, SSTNN	Crop yield prediction from multi-spectral, multi-temporal remotely sensed imagery using recurrent 3D convolutional neural networks	International Journal of Applied Earth Observation and Geoinformation
2021	DSASI-MADR, ASAP	LASSO, RF, MLP, SVR, GBR	Yield forecasting with machine learning and small data: What gains for grains?	Agricultural and Forest Meteorology
2021	Onsite devices, Landsat, MODIS, CMA	LASSO, LightGBM, LSTM	Integrating satellite-derived climatic and vegetation indices to predict smallholder maize yield using deep learning	Agricultural and Forest Meteorology
2021	Sentinel-2, MODIS	LIN, RID, SVR, GPR, CNN-2D, CNN-3D	Rice-yield prediction with multi-temporal sentinel-2 data and 3D CNN: A case study in Nepal	Remote Sensing
2021	Onsite devices, UAV	SPAD, CCC, LAI, AGB	Remote estimation of grain yield based on UAV data in different rice cultivars under contrasting climatic zone	Field Crops Research
2021	MODIS	DT, RF, SVM, LSTM, 2D-CNN, 3DMKGP	Exploiting hierarchical features for crop yield prediction based on 3-d convolutional neural networks and multikernel gaussian process	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
2022	MODIS, COMS MI, RDAPS, IRRI	RSCM, FFNN, 1D-CNN, LSTM, 1D-CNN+LSTM, LSTM+1D-CNN	Predicting rice yield at pixel scale through synthetic use of crop and deep learning models with satellite data in South and North Korea	Science of The Total Environment

Agrifood Quality Assessment

Year	Input	Methods	Paper Title	Pub.
2018	Onsite devices	SVM	Comparison of features for strawberry grading classification with novel dataset	IC3INA
2018	Onsite devices	CNN, AlexNet, GoogLeNet, VGGNet, Xception, MobileNet	Evaluation of deep convolutional neural network architectures for strawberry quality inspection	International Journal of Engineering & Technology

Pasture Monitoring and Evaluation

Year	Input	Methods	Paper Title	Pub.
2019	Onsite devices, UAV	ANN, SVM, RF	Modeling alpine grassland forage phosphorus based on hyperspectral remote sensing and a multi-factor machine learning algorithm in the east of Tibetan Plateau, China	ISPRS Journal of Photogrammetry and Remote Sensing
2021	UAV	GAM, RF	Predicting pasture biomass using a statistical model and machine learning algorithm implemented with remotely sensed imagery	Computers and Electronics in Agriculture
2021	Sentinel-2, Onsite devices	MLP	Estimating pasture biomass using sentinel-2 imagery and machine learning	Remote Sensing
2021	Public datasets	DeepPaSTL	DeepPaSTL: Spatio-temporal deep learning methods for predicting long-term pasture terrains using synthetic datasets	Agronomy
2022	Onsite devices	PLS, RF	Estimating pasture quality of Mediterranean grasslands using hyperspectral narrow bands from field spectroscopy by Random Forest and PLS regressions	Computers and Electronics in Agriculture

Animal Individual Monitoring

Year	Input	Methods	Paper Title	Pub.
2015	Laboratory conditions	PNN	Classification of fresh and frozen-thawed pork muscles using visible and near infrared hyperspectral imaging and textural analysis	Meat Science
2016	GeoEye, SWISSTOPO	CNN	Detection of fragmented rectangular enclosures in very high resolution remote sensing images	IEEE Transactions on Geoscience and Remote Sensing
2018	Onsite devices	Fisherface, VGG-Face+SVM, CNN	Towards on-farm pig face recognition using convolutional neural networks	Computers in Industry
2018	Onsite devices	Fully automatic computer vision system	Implementation of an automatic 3D vision monitor for dairy cow locomotion in a commercial farm	Biosystems Engineering
2018	Onsite devices	FCN, SDS	High-accuracy image segmentation for lactating sows using a fully convolutional network	Biosystems Engineering
2020	Onsite devices	Fast R-CNN	Automatic recognition of lactating sow postures by refined two-stream RGB-D faster R-CNN	Biosystems Engineering
2020	ImageNet, NADIS, Pixabay, Flickr, Gettyimages	AlexNet, LeNet, VGG16, DenseNet-201, Inception-v3, ResNet-50, DarkNet	Automated sheep facial expression classification using deep transfer learning	Computers and Electronics in Agriculture
2020	Onsite devices	VGG-16	Cattle face recognition method based on parameter transfer and deep learning	Journal of Physics: Conference Series
2020	Onsite devices	YOLOV3+LSTM, YOLOV3+BLSTM, YOLOV3+GRU, YOLOV3+Stacked LSTM, YOLOV3+SVM, YOLOV3+KNN, YOLOV3+DTC	Lameness detection of dairy cows based on the YOLOv3 deep learning algorithm and a relative step size characteristic vector	Biosystems Engineering
2020	Onsite devices	EFMYOLOv3, SSD, YOLOv3	Automatic recognition of dairy cow mastitis from thermal images by a deep learning detector	Computers and Electronics in Agriculture
2020	Onsite devices	Fast-RCNN-VGG16, YOLOv3-Darknet53	Deep learning-based hierarchical cattle behavior recognition with spatio-temporal information	Computers and Electronics in Agriculture
2020	Onsite devices	CNN	Assessment of dairy cow heat stress by monitoring drinking behaviour using an embedded imaging system	Biosystems Engineering
2021	Onsite devices	AlexNet, VGG16, ResNet50, MobilNet V2, GoogLeNet	Individual dairy cow identification based on lightweight convolutional neural network	Plos One
2021	Public datasets	AP-10K	Ap-10k: A benchmark for animal pose estimation in the wild	Arxiv Preprint
2022	MS COCO datasets	ViTPose	Vitpose: Simple vision transformer baselines for human pose estimation	NeurIPS
2022	Public datasets	GMFlow	GMflow: Learning optical flow via global matching	CVPR
2022	Onsite devices, MODIS	GLM, GAM, RF, GBM, NNET, MARS, FDA, CT, SVM, NB, ADA	Exploration of machine learning models to predict the environmental and remote sensing risk factors of haemonchosis in sheep flocks of Rajasthan, India	Acta Tropica

Fishing Area Identification And Prediction

Year	Input	Methods	Paper Title	Pub.
2017	Sentinel-1	Connected Component Segmentation	Large-scale assessment of coastal aquaculture ponds with Sentinel-1 time series data	Remote Sensing
2018	GF-1	DS-HCN, AT, DeepLab	Automatic raft labeling for remote sensing images via dual-scale homogeneous convolutional neural network	Remote Sensing
2019	Landsat TM, OLI, GF-1	SVM	Extracting aquaculture ponds from natural water surfaces around inland lakes on medium resolution multispectral images	International Journal of Applied Earth Observation and Geoinformation
2020	GF-2	HDCUNet, FCN-8s, SegNet, U-Net, TS	Research on a novel extraction method using Deep Learning based on GF-2 images for aquaculture areas	International Journal of Remote Sensing
2020	Landsat, GF-1, ALOS, ZY-3	RCSANet	RCSANet: A full convolutional network for extracting inland aquaculture ponds from high-spatial-resolution images	Remote Sensing
2021	GF-1, GF-2	Semi-SSN	Semi-/Weakly-supervised semantic segmentation method and its application for coastal aquaculture areas based on multi-source remote sensing images—taking the Fujian coastal area (mainly Sanduo) as an example	Remote Sensing
2022	NOAA, METOP-1, METOP-2, MODIS	HE-DFNETS	HE‐DFNETS: a novel hybrid deep learning architecture for the prediction of potential fishing zone areas in Indian Ocean using remote sensing images	Computational Intelligence and Neuroscience

Fish Production Forecast

Year	Input	Methods	Paper Title	Pub.
2020	Onsite devices	Faster MSSDLite, YOLOv3, Faster RCNN, HOG+SVM	Real-time robust detector for underwater live crabs based on deep learning	Computers and Electronics in Agriculture
2020	Onsite devices	YOLOv3	Automatic detection of Western rock lobster using synthetic data	ICES Journal of Marine Science
2021	UAV	YOLOv3	Seecucumbers: Using deep learning and drone imagery to detect sea cucumbers on coral reef flats	Drones
2022	Onsite devices	MaskRCNN	Coastal fisheries resource monitoring through A deep learning-based underwater video analysis	Estuarine, Coastal and Shelf Science
2022	Onsite devices, MODIS, Landsat, GSW JRC	XGBoost	Remote sensing modeling of environmental influences on lake fish resources by machine learning: A practice in the largest freshwater lake of China	Frontiers in Environmental Science
2023	Onsite devices	MobileCenterNet, ResNet-CenterNet	Real-time detection of underwater river crab based on multi-scale pyramid fusion image enhancement and MobileCenterNet model	Computers and Electronics in Agriculture
2024	Onsite devices	FMRFT	FMRFT: Fusion Mamba and DETR for Query Time Sequence Intersection Fish Tracking	arXiv

Fish Product Classification

Year	Input	Methods	Paper Title	Pub.
2020	Laboratory conditions	Mask-RCNN	An application of Convolutional Neural Network to lobster grading in the Southern Rock Lobster supply chain	Food Control
2020	Onsite devices	CNN	Fish recognition model for fraud prevention using convolutional neural networks	Advances in Computational Intelligence

Reference

If you find this repo is helpful, please consider giving this repo a ⭐ and citing:

@article{agrifoodsurveys,
author = {Chen, Tao and Lv, Liang and Wang, Di and Zhang, Jing and Yang, Yue and Zhao, Zeyang and Wang, Chen and Guo, Xiaowei and Chen, Hao and Wang, Qingye and Xu, Yufei and Zhang, Qiming and Du, Bo and Zhang, Liangpei and Tao, Dacheng},
title = {Empowering Agrifood System with Artificial Intelligence: A Survey of the Progress, Challenges and Opportunities},
year = {2024},
volume = {57},
number = {2},
journal = {ACM Computing Surveys},
doi = {10.1145/3698589}
}