Estimating crop leaf protein content using hyperspectral remote sensing and pretrained and LCC-assisted LPCNet deep learning model

Jibo Yue, Guangfu Gao, Yiguang Fan, Yang Liu, Haikuan Feng,
Estimating crop leaf protein content using hyperspectral remote sensing and pretrained and LCC-assisted LPCNet deep learning model,
Computers and Electronics in Agriculture,
Volume 239, Part C,
2025,
111064,
ISSN 0168-1699,
https://doi.org/10.1016/j.compag.2025.111064.
(https://www.sciencedirect.com/science/article/pii/S0168169925011706)
Abstract: Leaf protein content (LPC) is a critical physiological parameter for assessing crop nitrogen status, optimizing fertilization strategies, and predicting crop yield. Although hyperspectral remote sensing offers a nondestructive alternative, it still faces challenges such as overlapping protein and water absorption spectral features. This study presents a “physics-constrained + data-driven” hybrid modeling framework, LPCNet, for remote sensing–based LPC estimation. The core innovations of LPCNet include (1) leveraging the physics-based PROSPECT-PRO and SAIL radiative transfer models to generate a simulated spectra dataset, addressing the challenges of small sample sizes and distribution bias in field measurements through pretraining and transfer learning; (2) incorporating leaf chlorophyll content (LCC) as an auxiliary training target within a multitask learning framework, which exploits the strong absorption features of LCC in the visible–near infrared (VNIR) range to enhance the ability of the model to interpret weak LPC absorption signals in the shortwave infrared (SWIR) range; and (3) employing a multiscale convolutional network with a feature fusion mechanism to explicitly model the complex nonlinear relationships between spectral reflectance and LPC. This study utilized field-measured data from three growing seasons of wheat and potato to develop and validate the LPCNet model. The results demonstrate the following: (1) the LPCNet model pretrained with a simulated spectra dataset notably outperforms nonpretrained models; (2) the pretrained and LCC-assisted strategy further improves LPC-estimation accuracy to RMSE = 0.000100 g/cm2 (R2 = 0.866), showing a substantial advantage over traditional RF (R2 = 0.760, RMSE = 0.000134 g/cm2). This study proposes a hybrid deep learning modeling framework utilizing hyperspectral remote sensing for high-precision monitoring of crop LPC.
Keywords: Hyperspectral; PROSAIL; LPC; Transfer learning