Efficient physics-informed transfer learning to quantify biochemical traits of winter wheat from UAV multispectral imagery

• PITL with fine-tuning processes enhance model performance for LAI, LCC and CCC estimation from UAV multispectral data. • PITL DNN achieve higher performance in prediction accuracy and computational efficiency compared to 1D CNN and LSTM in the PITL framework. • These findings provide a practical approach for biochemical traits inversion in various spatial–temporal scenarios. Accurate and efficient estimation of biochemical traits, including leaf index area (LAI), leaf chlorophyll content (LCC) and canopy chlorophyll content (CCC), is crucial for crop growth monitoring in agricultural management. Recent advancements in unmanned aerial vehicle (UAV) multispectral remote sensing have enabled fast and cost-effective measurements of these traits. However, traditional statistical regression models trained on specific datasets lack scalability and transferability across practical field conditions without retraining. This study proposed an efficient physics-informed transfer learning model (PITL) for winter wheat biochemical traits estimation from UAV multispectral data. The PITL integrates the strengths of physical radiative transfer simulations and deep neural network architectures through transfer learning to improve the estimation of biochemical traits from UAV multispectral data. The PITL was tested with convolutional neural network (CNN), deep neural network (DNN), and long short-term memory (LSTM) architectures. Results indicated that PITL DNN had better accuracy than PITL CNN and PITL LSTM models in predicting LAI (R 2 =0.94, RMSE = 0.32 m 2 /m 2 ), LCC (R 2 =0.81, RMSE = 5.20 μg/cm 2 ) and CCC (R 2 =0.928, RMSE = 0.2 g/m 2 ). Moreover, PITL DNN demonstrated higher capability in computational efficiency, making it suitable for processing large volumes of UAV multispectral data in crop growth monitoring applications. Furthermore, PITL's integration of radiative transfer knowledge with labeled field data yielded higher predictive accuracy compared to physically-based inversion model, pure data-driven deep neural network approaches, and hybrid models. This study highlighted the performance of PITL DNN in accurately and efficiently quantifing biochemical traits from UAV multispectral data, thereby providing timely and accurate information for guiding crop growth monitoring applications.