Abstract
Net photosynthesis (AN) is a key component of the global carbon cycle influencing climate feedback over decadal scales. Although plant acclimation to environmental changes can modify AN, 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 ofVc,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 Vc,max25, learning the environment dependencies of key photosynthetic parameters improved model spatiotemporal generalizability. Applying environmental acclimation to Vc,max25 led to substantial variations in global mean AN indicating the need to address acclimation in ESMs. The model effectively captured multivariate observations (Vc,max25, AN, and stomatal conductance (gs)) simultaneously with multivariate constraints, improving generalization across space and PFTs. It also learned sensible acclimation relationships of Vc,max25 to different environmental conditions. The model explained more than 54%, 57%, and 62% of the variance of AN, gs, and Vc,max25, respectively, presenting a first global-scale spatial test benchmark of AN and gs. These results highlight the potential for differentiable modeling to enhance process-based modules in ESMs and effectively leverage information from large, multivariate data sets.
