[{"text":"00N0I00000KT1fD","value":"utm_source"},{"text":"00N0I00000KT1fI","value":"utm_medium"},{"text":"00N0I00000KT1fN","value":"utm_campaign"},{"text":"00N0I00000KT1fS","value":"uterm"},{"text":"00N0I00000KT1md","value":"adgroupname"},{"text":"00N0I00000KT1mx","value":"keyword"},{"text":"00N0I00000KT1nR","value":"creative"},{"text":"00N0I00000KT1ng","value":"devicemodel"},{"text":"00N0I00000KT1nq","value":"placement"},{"text":"00N0I00000KT1ot","value":"target"},{"text":"00N0I00000KT1o0","value":"device"},{"text":"00N0I00000KT1o5","value":"network"},{"text":"00N0I00000KT1oA","value":"matchtype"},{"text":"00N0I00000KT1oF","value":"gclid"},{"text":"00N0I00000KT1nM","value":"campaignname"},{"text":"00N0I00000KT1n7","value":"term"},{"text":"","value":""}]
This study deployed anomaly detection AI techniques to derive models for predicting crops at risk and help farmers increase the yield by providing remote & timely access.
A leading impact of climate change is increased plant pests that ravage crops. Pests are becoming more destructive, threatening food security and the environment. FAO estimates about 40% of global annual crops are lost to pests. Plant diseases cost over $200 billion, and pests about $70 billion of the global economy.2
A team of participants explored and deployed anomaly detection AI techniques to derive models for predicting crops at risk/ no risk of disease from images of diseased and healthy crops and help farmers increase their yield by providing remote and timely recommendations.
The team built the anomaly detection model on four crops- Cotton, Rice, Grapes, and Maize/ Corn. The classification model helped classify the given crop image into an anomaly and the detection model helped the team identify the region with an anomaly. They formed a bounding box around the anomaly region that helped in application of pesticides or insecticides in specific areas only.
The team implemented an Object Detection algorithm on 14 anomaly classes of the 3,850 image samples received. They then chose the R-CNN object detection modelling technique as Fast R-CNN fixes the disadvantages of SPPnet while improving speed and accuracy.
One of the findings was a Mean Average Precision or mAP of approx 7.5 and overall detection accuracy of 30-60% during the inference phase with SSD MobileNet & EfficientDet tensorflow deep learning models.
Phase 1 deployment of the model showed an accuracy of over 70% in the first run, which can be further improved via hyperparameter tuning, providing more samples per class and better infrastructure.
The researchers concluded that if deployed on even 20% of crops in India, this project could save thousands of crores and minimize crop damage.
It has the potential to offer low-cost solutions to the farmers, give the farmers remote access, and reduce agriculture wastage.
The team deployed the techniques of SSD MobileNet V2 FPNLite 640x640, ResNet, EfficientDet D1 640x640, Classification Technique, VGG annotator, Faster RCNN
References:
1) Nagadevara V., Singh D.K., Sinha M., Barshilia I., Oberoi G.K., Gupta M., ‘Crop Anomaly Detection,’ 2022