Transfer Learning in Junction With a Light Use Efficiency Model for Estimating Grassland Gross Primary Production

It is significant to simulate grassland gross primary production (GPP) to understand the terrestrial carbon budget over Inner Mongolia (IMG), China. Nevertheless, there is not sufficient in situ GPP data over this region. In this study, we proposed a novel model-based transfer learning (MTL) approach with generative adversarial networks-long short-term memory (GAN-LSTM) and light use efficiency (LUE) models to derive grassland GPP over IMG, China. We first used 25 grassland eddy covariance sites over the conterminous United States to establish the GAN-LSTM model and then fine-tuned it with six sites over IMG to estimate water constraints that were embedded into the LUE model to predict GPP. We then compared it with instance-based transfer learning and nontransfer learning approaches. Against the six IMG EC sites, the GPP estimates of MTL-LUE outperformed the other approaches with a lower root-mean-square error median (1.35 g C m⁻² d⁻¹) and a higher Kling-Gupta efficiency of 0.54. An innovation of this approach is that MTL-LUE mitigates the effect of limited training samples on the machine learning-based LUE hybrid model for GPP estimates over IMG.