{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:27:53Z","timestamp":1784136473611,"version":"3.55.0"},"reference-count":34,"publisher":"MDPI AG","issue":"22","license":[{"start":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T00:00:00Z","timestamp":1668988800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41971057"],"award-info":[{"award-number":["41971057"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In the last two decades, machine learning (ML) methods have been widely used in digital soil mapping (DSM), but the regression kriging (RK) model which combines the advantages of the ML and kriging methods has rarely been used in DSM. In addition, due to the limitation of a single-model structure, many ML methods have poor prediction accuracy in undulating terrain areas. In this study, we collected the SOC content of 115 soil samples in a hilly farming area with continuous undulating terrain. According to the theory of soil-forming factors in pedogenesis, we selected 10 topographic indices, 7 vegetation indices, and 2 soil indices as environmental covariates, and according to the law of geographical similarity, we used ML and RK methods to mine the relationship between SOC and environmental covariates to predict the SOC content. Four ensemble models\u2014random forest (RF), Cubist, stochastic gradient boosting (SGB), and Bayesian regularized neural networks (BRNNs)\u2014were used to fit the trend of SOC content, and the simple kriging (SK) method was used to interpolate the residuals of the ensemble models, and then the SOC and residual were superimposed to obtain the RK prediction result. Moreover, the 115 samples were divided into calibration and validation sets at a ratio of 80%, and the tenfold cross-validation method was used to fit the optimal parameters of the model. From the results of four ensemble models: RF performed best in the calibration set (R2c = 0.834) but poorly in the validation set (R2v = 0.362); Cubist had good accuracy and stability in both the calibration and validation sets (R2c = 0.693 and R2v = 0.445); SGB performed poorly (R2c = 0.430 and R2v = 0.336); and BRNN had the lowest accuracy (R2c = 0.323 and R2v = 0.282). The results showed that the R2 of the four RK models in the validation set were 0.718, 0.674, 0.724, and 0.625, respectively. Compared with the ensemble models without superimposed residuals, the prediction accuracy was improved by 0.356, 0.229, 0.388, and 0.343, respectively. In conclusion, Cubist has high prediction accuracy and generalization ability in areas with complex topography, and the RK model can make full use of trends and spatial structural factors that are not easy to mine by ML models, which can effectively improve the prediction accuracy. This provides a reference for soil survey and digital mapping in complex terrain areas.<\/jats:p>","DOI":"10.3390\/s22228997","type":"journal-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T04:39:59Z","timestamp":1669005599000},"page":"8997","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":45,"title":["Digital Mapping of Soil Organic Carbon Based on Machine Learning and Regression Kriging"],"prefix":"10.3390","volume":"22","author":[{"given":"Changda","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Resources and Environmental Sciences, Nanjing Agricultural University, No. 1 Weigang, Xuanwu District, Nanjing 210095, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchen","family":"Wei","sequence":"additional","affiliation":[{"name":"College of Resources and Environmental Sciences, Zijingang Campus, Zhejiang University, 866 Yuhangtang Road, Xihu District, Hangzhou 310058, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0617-1789","authenticated-orcid":false,"given":"Fubin","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Resources and Environmental Sciences, Nanjing Agricultural University, No. 1 Weigang, Xuanwu District, Nanjing 210095, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Resources and Environmental Sciences, Nanjing Agricultural University, No. 1 Weigang, Xuanwu District, Nanjing 210095, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Fang","sequence":"additional","affiliation":[{"name":"College of Resources and Environmental Sciences, Nanjing Agricultural University, No. 1 Weigang, Xuanwu District, Nanjing 210095, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0287-8197","authenticated-orcid":false,"given":"Zhaofu","family":"Li","sequence":"additional","affiliation":[{"name":"College of Resources and Environmental Sciences, Nanjing Agricultural University, No. 1 Weigang, Xuanwu District, Nanjing 210095, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianjun","family":"Pan","sequence":"additional","affiliation":[{"name":"College of Resources and Environmental Sciences, Nanjing Agricultural University, No. 1 Weigang, Xuanwu District, Nanjing 210095, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,11,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.geoderma.2018.07.026","article-title":"Soil organic carbon storage as a key function of soils\u2014A review of drivers and indicators at various scales","volume":"333","author":"Wiesmeier","year":"2019","journal-title":"Geoderma"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.geoderma.2016.12.008","article-title":"Digital soil mapping of soil carbon at the farm scale: A spatial downscaling approach in consideration of measured and uncertain data","volume":"290","author":"Malone","year":"2017","journal-title":"Geoderma"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"2871","DOI":"10.1016\/S2095-3119(17)61762-3","article-title":"Recent progress and future prospect of digital soil mapping: A review","volume":"16","author":"Zhang","year":"2017","journal-title":"J. Integr. Agric."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"115567","DOI":"10.1016\/j.geoderma.2021.115567","article-title":"Digital mapping of GlobalSoilMap soil properties at a broad scale: A review","volume":"409","author":"Chen","year":"2022","journal-title":"Geoderma"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1080\/19475683.2022.2026467","article-title":"How is the Third Law of Geography different?","volume":"28","author":"Zhu","year":"2022","journal-title":"Ann. GIS"},{"key":"ref_6","unstructured":"FAO (2022). A Primer on Soil Analys Is Using Visible and Near-Infrared (vis-NIR) and Mid-Infrared (MIR) Spectroscopy, FAO."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1097\/00010694-194111000-00009","article-title":"Factors of soil formation: A system of quantitative pedology\/Hans Jenny","volume":"42","author":"Jenny","year":"1941","journal-title":"Soil Sci."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/S0016-7061(03)00223-4","article-title":"On digital soil mapping","volume":"117","author":"McBratney","year":"2003","journal-title":"Geoderma"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"234","DOI":"10.2307\/143141","article-title":"A Computer Movie Simulating Urban Growth in the Detroit Region","volume":"46","author":"Tobler","year":"1970","journal-title":"Econ. Geogr."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1040","DOI":"10.2136\/sssaj1981.03615995004500060007x","article-title":"BlGGAR, Spatial Variability of Field-Measured Infiltration Rate","volume":"45","author":"Vieira","year":"1981","journal-title":"Soil Sci. Soc. Am. J."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"429","DOI":"10.1016\/j.catena.2016.07.045","article-title":"Lithology and soil relationships for soil modelling and mapping","volume":"147","author":"Gray","year":"2016","journal-title":"Catena"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"115638","DOI":"10.1016\/j.geoderma.2021.115638","article-title":"Complex hydrological knowledge to support digital soil mapping","volume":"409","author":"Mello","year":"2022","journal-title":"Geoderma"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"106024","DOI":"10.1016\/j.catena.2022.106024","article-title":"High-resolution agriculture soil property maps from digital soil mapping methods, Czech Republic","volume":"212","year":"2022","journal-title":"Catena"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"138244","DOI":"10.1016\/j.scitotenv.2020.138244","article-title":"High-resolution digital mapping of soil organic carbon and soil total nitrogen using DEM derivatives, Sentinel-1 and Sentinel-2 data based on machine learning algorithms","volume":"729","author":"Zhou","year":"2020","journal-title":"Sci. Total Environ."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1016\/j.geoderma.2018.09.006","article-title":"Digital mapping of soil properties using multiple machine learning in a semi-arid region, central Iran","volume":"338","author":"Zeraatpisheh","year":"2019","journal-title":"Geoderma"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Hengl, T., de Jesus, J.M., Heuvelink, G.B.M., Gonzalez, M.R., Kilibarda, M., Blagotic, A., Shangguan, W., Wright, M.N., Geng, X., and Bauer-Marschallinger, B. (2017). SoilGrids250m: Global gridded soil information based on machine learning. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0169748"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.geoderma.2009.12.025","article-title":"Using data mining to model and interpret soil diffuse reflectance spectra","volume":"158","author":"Rossel","year":"2010","journal-title":"Geoderma"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.geoderma.2018.08.011","article-title":"National digital soil map of organic matter in topsoil and its associated uncertainty in 1980\u2019s China","volume":"335","author":"Liang","year":"2019","journal-title":"Geoderma"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/0304-3800(95)00161-1","article-title":"Automated soil inference under fuzzy logic","volume":"90","author":"Zhu","year":"1996","journal-title":"Ecol. Model."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.geomorph.2007.02.006","article-title":"A new method of surface modeling and its application to DEM construction","volume":"91","author":"Yue","year":"2007","journal-title":"Geomorphology"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2205","DOI":"10.1080\/01431161003668982","article-title":"High-accuracy surface modelling and its application to DEM generation","volume":"31","author":"Yue","year":"2010","journal-title":"Int. J. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/j.geoderma.2009.01.020","article-title":"Surface modelling of soil pH","volume":"150","author":"Shi","year":"2009","journal-title":"Geoderma"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"75","DOI":"10.1016\/j.geoderma.2003.08.018","article-title":"A generic framework for spatial prediction of soil variables based on regression-kriging","volume":"120","author":"Hengl","year":"2004","journal-title":"Geoderma"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/j.geoderma.2015.08.037","article-title":"Comparing regression-based digital soil mapping and multiple-point geostatistics for the spatial extrapolation of soil data","volume":"262","author":"Malone","year":"2016","journal-title":"Geoderma"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"104289","DOI":"10.1016\/j.still.2019.06.006","article-title":"Some practical aspects of predicting texture data in digital soil mapping","volume":"194","author":"Minasny","year":"2019","journal-title":"Soil Tillage Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1080\/02571862.2019.1570566","article-title":"High-resolution digital soil mapping of multiple soil properties: An alternative to the traditional field survey?","volume":"36","author":"Flynn","year":"2019","journal-title":"S. Afr. J. Plant Soil"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Immitzer, M., Vuolo, F., and Atzberger, C. (2016). First Experience with Sentinel-2 Data for Crop and Tree Species Classifications in Central Europe. Remote Sens., 8.","DOI":"10.3390\/rs8030166"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1006\/ijhc.1987.0321","article-title":"Simplifying decision trees","volume":"51","author":"Quinlan","year":"1999","journal-title":"Int. J. Hum.-Comput. Stud."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1016\/j.scitotenv.2014.02.010","article-title":"Soil erodibility in Europe: A high-resolution dataset based on LUCAS","volume":"479\u2013480","author":"Panagos","year":"2014","journal-title":"Sci. Total Environ."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2953","DOI":"10.1111\/gcb.12569","article-title":"Baseline map of organic carbon in Australian soil to support national carbon accounting and monitoring under climate change","volume":"20","author":"Webster","year":"2014","journal-title":"Glob. Chang. Biol."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/S0167-9473(01)00065-2","article-title":"Stochastic gradient boosting","volume":"38","author":"Friedman","year":"2002","journal-title":"Comput. Stat. Data Anal."},{"key":"ref_33","first-page":"12","article-title":"Landslide susceptibility assessment in the Hoa Binh province of Vietnam: A comparison of the Levenberg\u2013Marquardt and Bayesian regularized neural networks","volume":"171\u2013172","author":"Pradhan","year":"2012","journal-title":"Geomorphology"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1301","DOI":"10.1016\/j.cageo.2007.05.001","article-title":"About regression-kriging: From equations to case studies","volume":"33","author":"Hengl","year":"2007","journal-title":"Comput. Geosci."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8997\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T01:22:39Z","timestamp":1760145759000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/22\/8997"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,21]]},"references-count":34,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2022,11]]}},"alternative-id":["s22228997"],"URL":"https:\/\/doi.org\/10.3390\/s22228997","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,21]]}}}