EUVIMEDEUVIMED entdecken
Crossref

Mapping long-term soil organic carbon stocks across the conterminous United States with machine learning

Hannah J Rubin, Xinxin Zhang, Joshua S Fu, T Edward Yu

Environmental Research · 2026-09 · 306 · 125271

DOI: 10.1016/j.envres.2026.125271 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environmental Research, 2026-09. Verfasst von Hannah J Rubin und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Civil and Environmental Engineering, University of Tennessee, Knoxville, TN, 37996, USA. Hauptthemen laut MEDLINE: Carbon, Machine Learning, Soil, Environmental Monitoring. Die Arbeit nennt 86 Literaturangaben. Gefördert von: Federal Aviation Administration.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Soil organic carbon (SOC) is a critical component of the global carbon cycle, but existing estimates of SOC stocks across the conterminous United States (CONUS) vary widely for the top 30 cm, hindering efforts to assess carbon sequestration potential and inform climate mitigation strategies. We compiled and harmonized SOC measurements from five major databases spanning 1984-2022 across diverse environmental conditions. Using a parsimonious set of environmental covariates, we compared the performance of linear regression and three machine learning algorithms for predicting SOC stocks. Random Forest demonstrated the best validation performance (R2 = 0.47, root mean squared error (RMSE) = 0.95 kg/m2) and was used to generate nationally consistent annual 30 m SOC stock maps from 1990 to 2022. Our analysis estimates total CONUS SOC stocks at 60.4 Pg C, with agricultural soils, forested soils, and shrubland and grassland soils representing the three dominant pools. Comparison of predicted and observed annual SOC across U.S. Department of Agriculture Economic Research Service (USDA ERS) farm resource regions showed that annual means calculated from long-term observations were more variable than model predictions. This pattern indicates that apparent annual SOC trends are strongly influenced by the spatial and temporal distribution of available observations. These results demonstrate that the maps are most useful for evaluating broad spatial patterns, regional and land cover differences, and the limits of interpreting annual SOC change from heterogeneous long-term observations. This framework provides a complementary resource to existing SOC products for carbon accounting, land use planning, biofuel life cycle assessment, and prioritizing future SOC monitoring.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CarbonMachine LearningSoilEnvironmental MonitoringUnited StatesCarbon Sequestration

Stichwörter der Autor:innen

Digital soil mappingLand use changeMachine learningRemote sensingSoil organic carbon

Substanzen

CarbonSoil

Autor:innen und Institutionen

  • Department of Civil and Environmental Engineering, University of Tennessee, Knoxville, TN, 37996, USA.
  • Department of Civil and Environmental Engineering, University of Tennessee, Knoxville, TN, 37996, USA; Computational Sciences and Engineering Division, Oak Ridge National Laboratory, Oak Ridge, TN, 37831, USA. Electroni…
  • Department of Agricultural and Resource Economics, University of Tennessee, Knoxville, TN, 37996, USA.

Förderung

  • Federal Aviation Administration

Zitieren

APA

Rubin, H. J., Zhang, X., Fu, J. S., & Yu, T. E. (2026). Mapping long-term soil organic carbon stocks across the conterminous United States with machine learning. Environmental Research, 306, 125271. https://doi.org/10.1016/j.envres.2026.125271

Vancouver

Rubin HJ, Zhang X, Fu JS, Yu TE. Mapping long-term soil organic carbon stocks across the conterminous United States with machine learning. Environmental Research. 2026;306:125271. doi:10.1016/j.envres.2026.125271

BibTeX
@article{Rubin2026,
  author = {Rubin, Hannah J and Zhang, Xinxin and Fu, Joshua S and Yu, T Edward},
  title = {Mapping long-term soil organic carbon stocks across the conterminous United States with machine learning},
  journal = {Environmental Research},
  year = {2026},
  volume = {306},
  pages = {125271},
  doi = {10.1016/j.envres.2026.125271}
}
Kostenlos starten →