Exploring Physics-Informed Neural Networks for Crop Yield Loss Forecasting
This addresses food security challenges for farmers, policymakers, and industry by providing interpretable and physically consistent yield predictions, though it is an incremental improvement over existing hybrid approaches.
The paper tackles crop yield loss forecasting under extreme weather by proposing a physics-informed neural network that combines physical principles with machine learning, achieving an R² of up to 0.77 and matching or surpassing state-of-the-art models like RNNs and Transformers.
In response to climate change, assessing crop productivity under extreme weather conditions is essential to enhance food security. Crop simulation models, which align with physical processes, offer explainability but often perform poorly. Conversely, machine learning (ML) models for crop modeling are powerful and scalable yet operate as black boxes and lack adherence to crop growths physical principles. To bridge this gap, we propose a novel method that combines the strengths of both approaches by estimating the water use and the crop sensitivity to water scarcity at the pixel level. This approach enables yield loss estimation grounded in physical principles by sequentially solving the equation for crop yield response to water scarcity, using an enhanced loss function. Leveraging Sentinel-2 satellite imagery, climate data, simulated water use data, and pixel-level yield data, our model demonstrates high accuracy, achieving an R2 of up to 0.77, matching or surpassing state-of-the-art models like RNNs and Transformers. Additionally, it provides interpretable and physical consistent outputs, supporting industry, policymakers, and farmers in adapting to extreme weather conditions.