Modeling Terrestrial Net Ecosystem Exchange Based on Deep Learning in China

In estimating the global carbon cycle, the net ecosystem exchange (NEE) is crucial. The understanding of the mechanism of interaction between NEE and various environmental factors of ecosystems has been very limited, and the interactions between the factors are intricate and complex, which leads to difficulties in accurately estimating NEE. In this study, we propose the A-DMLP (attention-deep multilayer perceptron)-deep learning model for NEE simulation as well as an interpretability study using the SHapley Additive exPlanations (SHAP) model. The attention mechanism was introduced into the deep multilayer perceptual machine, and the important information in the original input data was extracted using the attention mechanism. Good results were obtained on nine eddy covariance sites in China. The model was also compared with the random forest, long short-term memory, deep neural network, and convolutional neural networks (1D) models to distinguish it from previous shallow machine learning models to estimate NEE, and the results show that deep learning models have great potential in NEE modeling. The SHAP method was used to investigate the relationship between the input features of the A-DMLP model and the simulated NEE, and to enhance the interpretability of the model. The results show that the normalized difference vegetation index, the enhanced vegetation index, and the leaf area index play a dominant role at most sites. This study provides new ideas and methods for analyzing the intricate relationship between NEE and environmental factors by introducing the SHAP interpretable model. These advancements are crucial in achieving carbon reduction targets.