Inferring Plant Acclimation and Improving Model Generalizability With Differentiable Physics-Informed Machine Learning of Photosynthesis

Net photosynthesis (A_N) is a key component of the global carbon cycle influencing climate feedback over decadal scales. Although plant acclimation to environmental changes can modify A_N, traditional vegetation models in Earth system models (ESMs) often rely on plant functional type (PFT)-specific parameterizations or simplified acclimation assumptions limiting generalizability across time, space, and PFTs. In this study, we developed a differentiable photosynthesis model to learn the environmental dependencies ofV_c,max25 (maximum carboxylation rate at 25°C, representing photosynthetic capacity), as this genre of hybrid physics-informed machine learning can seamlessly train neural networks and process-based equations together. Compared to PFT-specific parameterization of V_c,max25, learning the environment dependencies of key photosynthetic parameters improved model spatiotemporal generalizability. Applying environmental acclimation to V_c,max25 led to substantial variations in global mean A_N indicating the need to address acclimation in ESMs. The model effectively captured multivariate observations (V_c,max25, A_N, and stomatal conductance (g_s)) simultaneously with multivariate constraints, improving generalization across space and PFTs. It also learned sensible acclimation relationships of V_c,max25 to different environmental conditions. The model explained more than 54%, 57%, and 62% of the variance of A_N, g_s, and V_c,max25, respectively, presenting a first global-scale spatial test benchmark of A_N and g_s. These results highlight the potential for differentiable modeling to enhance process-based modules in ESMs and effectively leverage information from large, multivariate data sets.