Leaf Spectral Reflectance Prediction Using Multi-Head Attention Neural Networks

2026-05-31

AI Summary

This study addresses the limitations of existing generic radiative transfer models, such as PROSPECT-PRO, in accurately capturing the relationship between leaf spectral reflectance and biochemical-structural traits for specific crops like grapevine. To overcome this, the authors propose a grapevine-specific neural network model that incorporates 16 physiological, biochemical, and structural features and introduces a multi-head attention mechanism into leaf spectral modeling for the first time. The model is trained and evaluated using stratified five-fold cross-validation. Experimental results demonstrate that the proposed approach achieves an average R² of 0.84 and a normalized root mean square error (NRMSE) of 1.52% across the full spectral range, significantly outperforming PROSPECT-PRO in the near-infrared and shortwave infrared regions. These findings validate the efficacy and generalization potential of species-specific, data-driven modeling for leaf optical properties.

Abstract

Accurate modeling of leaf spectral reflectance from physiological and biochemical traits is essential for advancing remote sensing applications in plant science and precision agriculture. Widely used radiative transfer models, such as PROSPECT-PRO, rely on generalized trait-reflectance relationships developed from a wide range of species, which may not fully capture the spectral behavior of specific crops like grapevines. In this study, we developed a trait-to-spectra prediction model using a multi-head attention neural network trained on a grapevine-specific dataset that includes 16 leaf traits measured across multiple varieties, growth stages, and years. The model was evaluated using stratified 5-fold cross-validation and achieved an average coefficient of determination (R^2) of 0.84 and normalized root mean squared error (NRMSE) of 1.52 percent, demonstrating high accuracy and generalizability. When compared to PROSPECT-PRO in forward mode, the neural network exhibited lower mean absolute error (MAE), especially in the near-infrared (NIR) and shortwave-infrared (SWIR) regions. These results emphasize the importance of species-specific modeling approaches and show that integrating biochemical and structural traits into data-driven architectures can significantly improve spectral prediction. The proposed model provides a robust framework for generating accurate leaf-level reflectance data, with potential applications in canopy trait retrieval, vineyard monitoring, and remote sensing-driven crop management.

Problem

• leaf spectral reflectance
• species-specific modeling
• radiative transfer models
• precision agriculture
• remote sensing

Innovation

• multi-head attention
• leaf spectral reflectance
• species-specific modeling
• neural networks
• precision agriculture