Forecasting Carbon Emissions from Planting Industry in China Based on BO-LightGBM and SHAP

Abstract

In order to address the carbon emissions generated by the plantation industry in China, this study used panel data from 30 provinces between 2012 and 2022 to predict and analyse the carbon emissions from the plantation industry through the LightGBM algorithm and SHAP. In addition, the hyper-parameters of the LightGBM regression model were optimised through a Bayesian optimisation algorithm and a five-fold cross-validation was applied to check the robustness of the machine learning regression model results. Finally, the SHAP model was used to analyse in depth the key factors affecting carbon emissions in the plantation industry and to explore ways to promote carbon emission reduction in China's plantation industry. The results show that agriculture-related financial expenditure, the number of agricultural high-tech enterprises and the number of rural professional cooperatives have negative effects and non-linear characteristics on carbon emissions from China's plantation industry. The LightGBM regression prediction model optimised by Bayesian algorithm outperforms the benchmark machine learning algorithm, and the R² mean value of the five-fold cross-validation is 0.982. The results of this study can provide scientific basis and technical support for promoting the sustainable development of Chinese agriculture.