Work

A Machine Learning‐Based High‐Resolution Inventory of Soil Inorganic Carbon Across the Contiguous United States

Year: 2026

Type: article

Abstract: Soil inorganic carbon (SIC) is critical for carbon sequestration, infiltration, and climate modeling, yet quantifying its precise spatial distribution at continental scales remains challengings. We introduce a high‐resolution (30 m) CONUS SIC map using machine learning (ML) models trained on the ISRIC World Soil Information Service (WoSIS) database. Integrating point‐based soil data with high resolution climate and land surface variables enhances predictions and reduces uncertainty in unsampled areas over previous polygon‐based inventories. Our SIC Random Forest Regression (RFR) yielded an Root Mean Square Error (RMSE) of 15 kg/m 2 , and the multi‐class classifier had an accuracy of 0.56. Our model estimates that CONUS soils store 77 ± 1.8 Pg of SIC in the top 1 m, a significant increase in SIC storage over prior inventories. We distinguish two SIC storage types: lithogenic carbonates persisting in humid regions and pedogenic carbonates, which characteristically form in arid soils.

Source: Geophysical Research Letters

DOI: 10.1029/2025gl120355

Authors: Zahra Ghahremani, David Huber, Arash Modaresi Rad, Mike J. Johnson, Jennifer Pierce

Institutions: Boise State University, Agricultural Research Service, United States Department of Agriculture, The University of Texas at El Paso

Language: English

Topic: Soil Geostatistics and Mapping

Subfield: Environmental Engineering

Field: Environmental Science

Domain: Physical Sciences

SDGs: Climate action, Life on land

Open Access status: gold

Estimated APC paid: $3,190