Mapping forest aboveground carbon stock of combined stratified sampling and RFRK model with mean annual temperature and precipitation

Abstract Accurately estimating forest aboveground carbon stock (ACS) is essential for achieving carbon neutrality. At present, most non-parametric models still have errors in estimating carbon stock in regions. Given the autocorrelation inherent in spatial interpolation, combining non-parametric mod...

Full description

Saved in:
Bibliographic Details
Main Authors: Min Peng, Mingrui Xu, Jialong Zhang, Bo Qiu, Chenkai Teng, Chaoqing Chen
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-02338-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850128023155638272
author Min Peng
Mingrui Xu
Jialong Zhang
Bo Qiu
Chenkai Teng
Chaoqing Chen
author_facet Min Peng
Mingrui Xu
Jialong Zhang
Bo Qiu
Chenkai Teng
Chaoqing Chen
author_sort Min Peng
collection DOAJ
description Abstract Accurately estimating forest aboveground carbon stock (ACS) is essential for achieving carbon neutrality. At present, most non-parametric models still have errors in estimating carbon stock in regions. Given the autocorrelation inherent in spatial interpolation, combining non-parametric models with spatial interpolation offers significant potential. In this study, we combined the random forest (RF) with the ordinary kriging and co-kriging of the mean annual temperature, precipitation, slope, and elevation to establish the random forest residual kriging (RFRK) model. Meanwhile, we also developed the multiple linear regression residual kriging (MLRRK) model and the random forest residual kriging (RFRK) model. Finally, we selected the optimal model for the estimation and mapping of the ACS. The results indicate that: (1) the model achieves an R2 of 0.871, P of 90.4%, and RMSE of 3.948 t/hm2; (2) the RFCK model with mean annual precipitation (RFCKpre) outperforms the one with mean annual temperature (RFCKtem), while the RFOK model exhibits the lowest accuracy; (3) the RFCKpre exponential model has the highest accuracy, with the highest R2 of 0.63 and RI (0.23), the lowest RMSE of 9.3 and SSR (41,612). These findings suggest that the RFRKpre model has improved the accuracy of estimating the ACS of regional forests.
format Article
id doaj-art-ba8e501511404658aa5c1d378cd82a2d
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-ba8e501511404658aa5c1d378cd82a2d2025-08-20T02:33:31ZengNature PortfolioScientific Reports2045-23222025-05-0115111610.1038/s41598-025-02338-8Mapping forest aboveground carbon stock of combined stratified sampling and RFRK model with mean annual temperature and precipitationMin Peng0Mingrui Xu1Jialong Zhang2Bo Qiu3Chenkai Teng4Chaoqing Chen5The Key Laboratory of Forest Resources Conservation and Utilization in the Southwest Mountains of China Ministry of Education; Key Laboratory of National Forestry and Grassland Administration On Biodiversity Conservation in Southwest China; Yunnan Provincial Key Laboratory for Conservation and Utilization of In-Forest Resource, Southwest Forestry UniversityCollege of Soil and Water Conservation, Southwest Forestry UniversityThe Key Laboratory of Forest Resources Conservation and Utilization in the Southwest Mountains of China Ministry of Education; Key Laboratory of National Forestry and Grassland Administration On Biodiversity Conservation in Southwest China; Yunnan Provincial Key Laboratory for Conservation and Utilization of In-Forest Resource, Southwest Forestry UniversityThe Key Laboratory of Forest Resources Conservation and Utilization in the Southwest Mountains of China Ministry of Education; Key Laboratory of National Forestry and Grassland Administration On Biodiversity Conservation in Southwest China; Yunnan Provincial Key Laboratory for Conservation and Utilization of In-Forest Resource, Southwest Forestry UniversityThe Key Laboratory of Forest Resources Conservation and Utilization in the Southwest Mountains of China Ministry of Education; Key Laboratory of National Forestry and Grassland Administration On Biodiversity Conservation in Southwest China; Yunnan Provincial Key Laboratory for Conservation and Utilization of In-Forest Resource, Southwest Forestry UniversityCollege of Soil and Water Conservation, Southwest Forestry UniversityAbstract Accurately estimating forest aboveground carbon stock (ACS) is essential for achieving carbon neutrality. At present, most non-parametric models still have errors in estimating carbon stock in regions. Given the autocorrelation inherent in spatial interpolation, combining non-parametric models with spatial interpolation offers significant potential. In this study, we combined the random forest (RF) with the ordinary kriging and co-kriging of the mean annual temperature, precipitation, slope, and elevation to establish the random forest residual kriging (RFRK) model. Meanwhile, we also developed the multiple linear regression residual kriging (MLRRK) model and the random forest residual kriging (RFRK) model. Finally, we selected the optimal model for the estimation and mapping of the ACS. The results indicate that: (1) the model achieves an R2 of 0.871, P of 90.4%, and RMSE of 3.948 t/hm2; (2) the RFCK model with mean annual precipitation (RFCKpre) outperforms the one with mean annual temperature (RFCKtem), while the RFOK model exhibits the lowest accuracy; (3) the RFCKpre exponential model has the highest accuracy, with the highest R2 of 0.63 and RI (0.23), the lowest RMSE of 9.3 and SSR (41,612). These findings suggest that the RFRKpre model has improved the accuracy of estimating the ACS of regional forests.https://doi.org/10.1038/s41598-025-02338-8Random forest residual krigingForest aboveground carbon stockMappingStratified sampling
spellingShingle Min Peng
Mingrui Xu
Jialong Zhang
Bo Qiu
Chenkai Teng
Chaoqing Chen
Mapping forest aboveground carbon stock of combined stratified sampling and RFRK model with mean annual temperature and precipitation
Scientific Reports
Random forest residual kriging
Forest aboveground carbon stock
Mapping
Stratified sampling
title Mapping forest aboveground carbon stock of combined stratified sampling and RFRK model with mean annual temperature and precipitation
title_full Mapping forest aboveground carbon stock of combined stratified sampling and RFRK model with mean annual temperature and precipitation
title_fullStr Mapping forest aboveground carbon stock of combined stratified sampling and RFRK model with mean annual temperature and precipitation
title_full_unstemmed Mapping forest aboveground carbon stock of combined stratified sampling and RFRK model with mean annual temperature and precipitation
title_short Mapping forest aboveground carbon stock of combined stratified sampling and RFRK model with mean annual temperature and precipitation
title_sort mapping forest aboveground carbon stock of combined stratified sampling and rfrk model with mean annual temperature and precipitation
topic Random forest residual kriging
Forest aboveground carbon stock
Mapping
Stratified sampling
url https://doi.org/10.1038/s41598-025-02338-8
work_keys_str_mv AT minpeng mappingforestabovegroundcarbonstockofcombinedstratifiedsamplingandrfrkmodelwithmeanannualtemperatureandprecipitation
AT mingruixu mappingforestabovegroundcarbonstockofcombinedstratifiedsamplingandrfrkmodelwithmeanannualtemperatureandprecipitation
AT jialongzhang mappingforestabovegroundcarbonstockofcombinedstratifiedsamplingandrfrkmodelwithmeanannualtemperatureandprecipitation
AT boqiu mappingforestabovegroundcarbonstockofcombinedstratifiedsamplingandrfrkmodelwithmeanannualtemperatureandprecipitation
AT chenkaiteng mappingforestabovegroundcarbonstockofcombinedstratifiedsamplingandrfrkmodelwithmeanannualtemperatureandprecipitation
AT chaoqingchen mappingforestabovegroundcarbonstockofcombinedstratifiedsamplingandrfrkmodelwithmeanannualtemperatureandprecipitation