PNNL

Abstract

Accurate and reliable prediction of leaf traits is crucial for understanding plant adaptations to environmental variation, monitoring terrestrial ecosystems, and enhancing comprehension of functional diversity and ecosystem functioning. Currently, various approaches (e.g., statistical, physical, and machine learning models) have been developed to estimate leaf traits through hyperspectral remote sensing and leaf spectroscopy. However, the absence of high-performing, transferable, and stable models across various domains of space, plant functional types (PFTs) and seasons hinder our ability to quantify and comprehend spatiotemporal variations in leaf traits. This study proposes robust and highly transferable models for better predicting leaf traits with hyperspectral reflectance. Initially, three datasets were assembled, pairing common leaf traits (i.e., chlorophyll, carotenoids, leaf mass per area, equivalent water thickness) with leaf spectra measurements, spanning diverse geographic locations, PFTs, and seasons. We then developed transfer learning-based hybrid models that incorporated the domain knowledge of radiative transfer models (RTMs) through pretraining processes and were well-constrained by fine-tuning with field measurements. Through comparison with other state-of-the-art statistical models (PLSR and GPR) and pure physical models, we found that the proposed transfer learning models achieved better predictive performance compared to other statistical models and pure RTMs and also exhibited relatively higher transferability than statistical models with higher R2 values with range of 0.01 to 0.79, lower NRMSE with range of 0.06% to 33.25% in model performance and higher R2 values range from 0.04 to 0.32, lower NRMSE range from 0.08% to 30.81% in model transferability. The findings underscore that transfer learning models through integrating domain knowledge from RTMs and limited observations, can harness the advantages of both RTMs and statistical models and serve as a promising approach for effectively predicting leaf traits.