The field of precision agriculture is witnessing significant advancements with the integration of deep learning techniques. Researchers are focusing on developing innovative solutions to address the challenges of crop recommendation, disease classification, and stress identification. The use of multimodal data, such as soil images and nutrient profiles, is becoming increasingly popular for accurate crop recommendations. Additionally, lightweight deep learning models are being designed for edge devices to enable real-time decision support in resource-constrained environments. Noteworthy papers in this area include: AgroSense, which achieves 98.0% accuracy in crop recommendation using a multimodal approach. STA-Net, which proposes a decoupled shape and texture attention network for lightweight plant disease classification, reaching 89.00% accuracy on the CCMT plant disease dataset.
Advances in Precision Agriculture through Deep Learning
Sources
AgroSense: An Integrated Deep Learning System for Crop Recommendation via Soil Image Analysis and Nutrient Profiling
STA-Net: A Decoupled Shape and Texture Attention Network for Lightweight Plant Disease Classification
Handling imbalance and few-sample size in ML based Onion disease classification
MRD-LiNet: A Novel Lightweight Hybrid CNN with Gradient-Guided Unlearning for Improved Drought Stress Identification
Improved Classification of Nitrogen Stress Severity in Plants Under Combined Stress Conditions Using Spatio-Temporal Deep Learning Framework
Lightweight Deep Unfolding Networks with Enhanced Robustness for Infrared Small Target Detection