Explainable Light-Weight Deep Learning Pipeline for Improved Drought Stress Identification
Aswini Kumar Patra, Lingaraj Sahoo
TL;DR
Problem addressed: early drought-stress detection in crops using non-invasive UAV imagery under real-field conditions. Approach: a lightweight transfer-learning pipeline with a pre-trained backbone, compact dense layers, and Grad-CAM explainability for drought-stress identification in RGB images. Contributions: DenseNet121 based classifier achieves 97% precision for stressed and 91% overall accuracy; Grad-CAM visualizations provide interpretable stress localization; demonstrated superior precision and accuracy compared with object-detection baselines. Impact: enables accurate, interpretable drought stress screening in the field and informs timely irrigation decisions.
Abstract
Early identification of drought stress in crops is vital for implementing effective mitigation measures and reducing yield loss. Non-invasive imaging techniques hold immense potential by capturing subtle physiological changes in plants under water deficit. Sensor based imaging data serves as a rich source of information for machine learning and deep learning algorithms, facilitating further analysis aimed at identifying drought stress. While these approaches yield favorable results, real-time field applications requires algorithms specifically designed for the complexities of natural agricultural conditions. Our work proposes a novel deep learning framework for classifying drought stress in potato crops captured by UAVs in natural settings. The novelty lies in the synergistic combination of a pre-trained network with carefully designed custom layers. This architecture leverages feature extraction capabilities of the pre-trained network while the custom layers enable targeted dimensionality reduction and enhanced regularization, ultimately leading to improved performance. A key innovation of our work involves the integration of Gradient-Class Activation Mapping (Grad-CAM), an explainability technique. Grad-CAM sheds light on the internal workings of the deep learning model, typically referred to as a black box. By visualizing the focus areas of the model within the images, Grad-CAM fosters interpretability and builds trust in the decision-making process of the model. Our proposed framework achieves superior performance, particularly with the DenseNet121 pre-trained network, reaching a precision of 97% to identify the stressed class with an overall accuracy of 91%. Comparative analysis of existing state-of-the-art object detection algorithms reveals the superiority of our approach in significantly higher precision and accuracy.