Study on the Migration Pattern of Organic Carbon in Slope Farmland in the Southeast of Heilongjiang Province

¹ Harbin Center for Integrated Natural Resources Survey, China Geological Survey, Harbin, Heilongjiang, China
² Observation and Research Station of Earth Critical Zone in Black Soil, Ministry of Natural Resources, Harbin, Heilongjiang, China
³ Yantai Center of Coastal Zone Geological Survery, China Geological Survey, Yantai, Shandong, China

^* Corresponding author: yuxingchen@mail.cgs.gov.cn, awanghongfeng@mail.cgs.gov.cn, bwjiuyi@mail.cgs.gov.cn, czhaojing01@mail.cgs.gov.cn, dfuguomeng@mail.cgs.gov.cn, eshaoze@mail.cgs.gov.cn

Abstract

This study addresses the issue of soil organic carbon (SOC) migration in slope farmland in the southeastern part of Heilongjiang Province by constructing a machine learning-based predictive model for organic carbon migration. Based on multi-year monitoring data, a three-tier model architecture consisting of a data layer, a computational layer, and an application layer was established, and an improved random forest algorithm was used to dynamically simulate the organic carbon migration process. The model integrates terrain, meteorological, and soil characteristic parameters to achieve accurate predictions of organic carbon fluxes at different spatial and temporal scales. The results indicate that the model exhibits good predictive ability under different slope gradients and rainfall conditions, providing a scientific basis for regional soil and water conservation and farmland quality improvement.