Enhancing soil organic carbon prediction by unraveling the role of crop residue coverage using interpretable machine learning

TY - JOUR

T1 - Enhancing soil organic carbon prediction by unraveling the role of crop residue coverage using interpretable machine learning

AU - Dong, Yi

AU - Wang, Xinting

AU - Wang, Sheng

AU - Li, Baoguo

AU - Liu, Junming

AU - Huang, Jianxi

AU - Li, Xuecao

AU - Zeng, Yelu

AU - Su, Wei

N1 - Publisher Copyright: © 2025 The Author(s)

PY - 2025/3

Y1 - 2025/3

N2 - Accurate regional mapping of soil organic carbon (SOC) in croplands is essential for assessing soil carbon sequestration potential. However, accurate SOC mapping of cropland at a regional scale is challenging due to numerous natural and anthropogenic management factors. The impact of covered crop residue remains undervalued when mapping surface SOC, despite the significant impact of crop residue coverage (CRC) on SOC. In particular, the agricultural management practice of returning crop residues to the soil significantly alters the spatio temporal patterns of SOC in northeast China. Given these issues, we used the Shapley Additive exPlanations (SHAP) approach to interpret the influence of natural and anthropogenic factors on SOC estimation using the random forest model. Our results show the high SHAP values of air temperature, CRC, and clay content due to their significant influence on SOC estimation. Interestingly, our analysis showed a significant increase in SHAP values when the CRC reached 0.30, which refers to the CRC threshold of conservation tillage. Furthermore, our results revealed that integrating crop residue coverage significantly improved the accuracy of SOC mapping as the Lin Concordance Correlation Coefficient (LCCC) increased from 0.75 to 0.83 and the root mean squared error (RMSE) decreased from 6.70 g kg−1 to 5.60 g kg−1. This study provides actionable insights for optimizing CRC management practices for SOC sequestration in Northeast China.

AB - Accurate regional mapping of soil organic carbon (SOC) in croplands is essential for assessing soil carbon sequestration potential. However, accurate SOC mapping of cropland at a regional scale is challenging due to numerous natural and anthropogenic management factors. The impact of covered crop residue remains undervalued when mapping surface SOC, despite the significant impact of crop residue coverage (CRC) on SOC. In particular, the agricultural management practice of returning crop residues to the soil significantly alters the spatio temporal patterns of SOC in northeast China. Given these issues, we used the Shapley Additive exPlanations (SHAP) approach to interpret the influence of natural and anthropogenic factors on SOC estimation using the random forest model. Our results show the high SHAP values of air temperature, CRC, and clay content due to their significant influence on SOC estimation. Interestingly, our analysis showed a significant increase in SHAP values when the CRC reached 0.30, which refers to the CRC threshold of conservation tillage. Furthermore, our results revealed that integrating crop residue coverage significantly improved the accuracy of SOC mapping as the Lin Concordance Correlation Coefficient (LCCC) increased from 0.75 to 0.83 and the root mean squared error (RMSE) decreased from 6.70 g kg−1 to 5.60 g kg−1. This study provides actionable insights for optimizing CRC management practices for SOC sequestration in Northeast China.

KW - Crop residue coverage

KW - Explainable machine learning

KW - Shapley additive explanation

KW - Soil organic carbon

UR - http://www.scopus.com/inward/record.url?scp=85218338237&partnerID=8YFLogxK

U2 - 10.1016/j.geoderma.2025.117225

DO - 10.1016/j.geoderma.2025.117225

M3 - Journal article

AN - SCOPUS:85218338237

SN - 0016-7061

VL - 455

JO - Geoderma

JF - Geoderma

M1 - 117225

ER -