Correction to a Simple Biosphere Model 2 (SiB2) Simulation of Energy and Carbon Dioxide Fluxes over a Wheat Cropland in East China Using the Random Forest Model

Modeling the heat and carbon dioxide (CO2) exchanges in agroecosystems is critical for better understanding water cycling, improving crop production, even mitigating climate change, agricultural regions. While previous studies mainly focused on simulations of energy CO2 fluxes North China Plain, their corrections, driving forces East are less understood. In this study, dynamic variations were simulated by a standalone version Simple Biosphere 2 (SiB2) model subsequently corrected using Random Forest (RF) machine learning model, based measurements from 1 January to 31 May 2015–2017 eastern China. Through validation with direct measurements, it was found that SiB2 overestimated sensible flux (H) latent (LE), but underestimated soil (G0) (Fc). Thus, RF used correct results modeled SiB2. The showed disturbances temperature, net radiation, G0 output SiB2, Fc key factors modulating H, LE, G0, Fc. performed well significantly reduced biases higher R2 values 0.99, 0.87, 0.75, 0.71, respectively. models combine physical mechanisms mathematical correction enable both meaning accuracy.