Mapping and understanding the regional farmland SOC distribution in southern China using a Bayesian spatial model

Information on the spatial distribution of soil organic carbon (SOC) in regional farmland is crucial for improving management and production. Mapping SOC in farmlands is challenging due to the strong variation of SOC caused by the influence of natural and anthropogenic activities. Additionally, curr...

Full description

Saved in:
Bibliographic Details
Main Authors: Bifeng Hu, Yibo Geng, Hanjie Ni, Zhou Shi, Zheng Wang, Nan Wang, Jipeng Luo, Modian Xie, Qian Zou, Thomas Optiz, Hongyi Li
Format: Article
Language:English
Published: Elsevier 2025-08-01
Series:Geoderma
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S0016706125002873
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849684139444273152
author Bifeng Hu
Yibo Geng
Hanjie Ni
Zhou Shi
Zheng Wang
Nan Wang
Jipeng Luo
Modian Xie
Qian Zou
Thomas Optiz
Hongyi Li
author_facet Bifeng Hu
Yibo Geng
Hanjie Ni
Zhou Shi
Zheng Wang
Nan Wang
Jipeng Luo
Modian Xie
Qian Zou
Thomas Optiz
Hongyi Li
author_sort Bifeng Hu
collection DOAJ
description Information on the spatial distribution of soil organic carbon (SOC) in regional farmland is crucial for improving management and production. Mapping SOC in farmlands is challenging due to the strong variation of SOC caused by the influence of natural and anthropogenic activities. Additionally, currently widely used predictive models usually suffer from a lack of model interpretability. To fill these gaps, here we use a Bayesian spatial model termed Integrated Nested Laplace Approximation with the Stochastic Partial Differential Equation (INLA-SPDE) to produce the fine scale SOC map in the farmland of Jiangxi Province, south China based on an extensive soil survey dataset (n = 16,050). The competitive adaptive reweighted sampling algorithm − partial least square (CARS-PLS) algorithm is adopted to select the most related covariates from the original covariates pool. Then, the performance of Random Forest (RF), Geographically Weighted Regression (GWR), and Ordinary Kriging (OK) was compared with INLA-SPDE. Finally, an interpretable machine learning model, the SHapley Additive exPlanation (SHAP), is used to quantify the environmental covariates’ contribution to mapping SOC, as well as mapping spatial varying primary covariates for predicting SOC in the study area. We find that INLA-SPDE was able to handle a large data and performed much better than OK and GWR with an improvement of 38.89 % and 117.39 % in R2, respectively. It also outperforms RF. Overall, amount of straw return, mean annual precipitation, mean annual solar radiation are the most important covariates for mapping SOC. Locally, soil management are the most important covariates for mapping SOC in 50.52 % regions of the study area, followed by climate factors (22.06 %), soil properties (17.09 %), terrain (6.38 %), lithology (2.21 %) and biota factors (1.72 %). Our study demonstrates the advantages of INLA-SPDE on mapping SOC compared with geostatistical and RF for SOC mapping and provides valuable implications for interpreting the results of digital soil mapping.
format Article
id doaj-art-4fdffc3dd0ae4494b4f0c731823e47a7
institution DOAJ
issn 1872-6259
language English
publishDate 2025-08-01
publisher Elsevier
record_format Article
series Geoderma
spelling doaj-art-4fdffc3dd0ae4494b4f0c731823e47a72025-08-20T03:23:34ZengElsevierGeoderma1872-62592025-08-0146011744610.1016/j.geoderma.2025.117446Mapping and understanding the regional farmland SOC distribution in southern China using a Bayesian spatial modelBifeng Hu0Yibo Geng1Hanjie Ni2Zhou Shi3Zheng Wang4Nan Wang5Jipeng Luo6Modian Xie7Qian Zou8Thomas Optiz9Hongyi Li10Department of Land Resource Management, School of Public Administration, Jiangxi University of Finance and Economics, Nanchang 330013, China; Key Laboratory of Data Science in Finance and Economics of Jiangxi Province, Jiangxi University of Finance and Economics, Nanchang 330013, ChinaDepartment of Land Resource Management, School of Public Administration, Jiangxi University of Finance and Economics, Nanchang 330013, ChinaDepartment of Land Resource Management, School of Public Administration, Jiangxi University of Finance and Economics, Nanchang 330013, ChinaInstitute of Agricultural Remote Sensing and Information Technology Application, Zhejiang University, Hangzhou 310058, ChinaInstitute of Agricultural Remote Sensing and Information Technology Application, Zhejiang University, Hangzhou 310058, ChinaDepartment of Earth System Science, Ministry of Education Key Laboratory for Earth System Modeling, Institute for Global Change Studies, Tsinghua University, 100084 Beijing, ChinaDepartment of Biology, Indiana University, Bloomington, IN, USASchool of Information Management and Mathematics, Jiangxi University of Finance and Economics, Nanchang 330013, ChinaDepartment of Land Resource Management, School of Public Administration, Jiangxi University of Finance and Economics, Nanchang 330013, ChinaINRAE, Biostatistics and Spatial Processes, 228 route de l’Aérodrome, Avignon 84914, FranceDepartment of Land Resource Management, School of Public Administration, Jiangxi University of Finance and Economics, Nanchang 330013, China; Key Laboratory of Data Science in Finance and Economics of Jiangxi Province, Jiangxi University of Finance and Economics, Nanchang 330013, China; Corresponding author at: Department of Land Resource Management, School of Public Administration, Jiangxi University of Finance and Economics, Nanchang 330013, China.Information on the spatial distribution of soil organic carbon (SOC) in regional farmland is crucial for improving management and production. Mapping SOC in farmlands is challenging due to the strong variation of SOC caused by the influence of natural and anthropogenic activities. Additionally, currently widely used predictive models usually suffer from a lack of model interpretability. To fill these gaps, here we use a Bayesian spatial model termed Integrated Nested Laplace Approximation with the Stochastic Partial Differential Equation (INLA-SPDE) to produce the fine scale SOC map in the farmland of Jiangxi Province, south China based on an extensive soil survey dataset (n = 16,050). The competitive adaptive reweighted sampling algorithm − partial least square (CARS-PLS) algorithm is adopted to select the most related covariates from the original covariates pool. Then, the performance of Random Forest (RF), Geographically Weighted Regression (GWR), and Ordinary Kriging (OK) was compared with INLA-SPDE. Finally, an interpretable machine learning model, the SHapley Additive exPlanation (SHAP), is used to quantify the environmental covariates’ contribution to mapping SOC, as well as mapping spatial varying primary covariates for predicting SOC in the study area. We find that INLA-SPDE was able to handle a large data and performed much better than OK and GWR with an improvement of 38.89 % and 117.39 % in R2, respectively. It also outperforms RF. Overall, amount of straw return, mean annual precipitation, mean annual solar radiation are the most important covariates for mapping SOC. Locally, soil management are the most important covariates for mapping SOC in 50.52 % regions of the study area, followed by climate factors (22.06 %), soil properties (17.09 %), terrain (6.38 %), lithology (2.21 %) and biota factors (1.72 %). Our study demonstrates the advantages of INLA-SPDE on mapping SOC compared with geostatistical and RF for SOC mapping and provides valuable implications for interpreting the results of digital soil mapping.http://www.sciencedirect.com/science/article/pii/S0016706125002873Soil organic carbonFarmlandINLA-SPDEInterpretable machine learning model
spellingShingle Bifeng Hu
Yibo Geng
Hanjie Ni
Zhou Shi
Zheng Wang
Nan Wang
Jipeng Luo
Modian Xie
Qian Zou
Thomas Optiz
Hongyi Li
Mapping and understanding the regional farmland SOC distribution in southern China using a Bayesian spatial model
Geoderma
Soil organic carbon
Farmland
INLA-SPDE
Interpretable machine learning model
title Mapping and understanding the regional farmland SOC distribution in southern China using a Bayesian spatial model
title_full Mapping and understanding the regional farmland SOC distribution in southern China using a Bayesian spatial model
title_fullStr Mapping and understanding the regional farmland SOC distribution in southern China using a Bayesian spatial model
title_full_unstemmed Mapping and understanding the regional farmland SOC distribution in southern China using a Bayesian spatial model
title_short Mapping and understanding the regional farmland SOC distribution in southern China using a Bayesian spatial model
title_sort mapping and understanding the regional farmland soc distribution in southern china using a bayesian spatial model
topic Soil organic carbon
Farmland
INLA-SPDE
Interpretable machine learning model
url http://www.sciencedirect.com/science/article/pii/S0016706125002873
work_keys_str_mv AT bifenghu mappingandunderstandingtheregionalfarmlandsocdistributioninsouthernchinausingabayesianspatialmodel
AT yibogeng mappingandunderstandingtheregionalfarmlandsocdistributioninsouthernchinausingabayesianspatialmodel
AT hanjieni mappingandunderstandingtheregionalfarmlandsocdistributioninsouthernchinausingabayesianspatialmodel
AT zhoushi mappingandunderstandingtheregionalfarmlandsocdistributioninsouthernchinausingabayesianspatialmodel
AT zhengwang mappingandunderstandingtheregionalfarmlandsocdistributioninsouthernchinausingabayesianspatialmodel
AT nanwang mappingandunderstandingtheregionalfarmlandsocdistributioninsouthernchinausingabayesianspatialmodel
AT jipengluo mappingandunderstandingtheregionalfarmlandsocdistributioninsouthernchinausingabayesianspatialmodel
AT modianxie mappingandunderstandingtheregionalfarmlandsocdistributioninsouthernchinausingabayesianspatialmodel
AT qianzou mappingandunderstandingtheregionalfarmlandsocdistributioninsouthernchinausingabayesianspatialmodel
AT thomasoptiz mappingandunderstandingtheregionalfarmlandsocdistributioninsouthernchinausingabayesianspatialmodel
AT hongyili mappingandunderstandingtheregionalfarmlandsocdistributioninsouthernchinausingabayesianspatialmodel