Proto-OKN Theme 1: Digging in to Soil Carbon with USDA: A Knowledge Graph Informing Soil Carbon Modeling

Award ID: 2333834

This project aims to construct a Soil Organic Carbon Knowledge Graph (SOCKG) to address the demand for accurate soil carbon data. Accurate soil carbon data is essential for quantifying carbon credits and encouraging sustainable farming practices that mitigate greenhouse gas emissions. The developed knowledge graph will support better policy decisions, enhanced carbon valuation accuracy, risk reduction, and increased financial gains from soil carbon management and participation in carbon markets. The collaboration between the University of Texas at Arlington (UTA) and the USDA Agricultural Research Service (ARS) include the UTA leading technical development with their expertise in data management, data science, and semantic technologies, while the USDA-ARS providing domain knowledge and strategic guidance to ensure real-world applicability and policy impact. SOCKG equips policymakers, land administrators, environmental NGOs, advocacy groups, educators, and realtors with precise data and insights on soil carbon stocks, fluxes, and dynamics, enabling them to make informed decisions regarding climate change mitigation, policy formulation, land use planning, educational teaching, and real estate development. Carbon sequestration in agricultural soils is an essential strategy in combating global climate change and an important component of the growing voluntary carbon markets. It offers incentives to farmers to adopt sustainable practices that increase soil carbon levels, thus providing environmental, economic benefits and diversifying their farming ventures. However, the complexity and diversity of soil carbon data, combined with environmental factors and land use, make accurate modeling a challenge. The SOCKG addresses this challenge by amalgamating and aligning different data sources, facilitating wider-scale research and more effective carbon sequestration strategies. By using advanced querying techniques and machine learning models, SOCKG significantly benefits soil carbon researchers, aiding them in predicting soil carbon stocks and addressing the uncertainty in soil organic carbon-related studies. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Jemin George