Arizona Stadium | University of Arizona
Arizona Stadium | University of Arizona
The University of Arizona has received a $610,166 grant from the Department of Energy as part of an $8 million initiative aimed at enhancing climate models. The university's project is one of 13 selected nationwide and seeks to improve understanding of how soil microbes impact climate change. This research could address significant uncertainties in current global climate projections.
Researchers from the University's Department of Hydrology and Atmospheric Sciences will integrate biological and environmental data with artificial intelligence to advance the Department of Energy's Energy Exascale Earth System Model (E3SM). E3SM is a sophisticated climate model designed to simulate Earth's climate system with high resolution and advanced physics. The University of Arizona project aims to refine projections regarding soil's influence on global climate.
"This project represents a significant step forward in climate science," said Yang Song, assistant professor of hydrology and atmospheric sciences and principal investigator for the project. "By integrating detailed biological and environmental data and AI into E3SM, we're opening new frontiers in understanding and predicting climate change."
The research focuses on the complex role soil microbes play in the global carbon cycle and greenhouse gas emissions. These microscopic communities have historically been difficult to study due to their size and complexity.
Song explained that microbial communities are the main drivers controlling greenhouse gas emissions from soil. Recent biotechnological advancements have made it easier to understand their roles. Using cutting-edge genomics data, Song's team plans to track microbial functions and their responses to changing climates, aiming to reduce uncertainties in soil carbon-climate feedback.
The team has already developed AI models to analyze microbial community distribution across the U.S. They plan to extend these models globally, integrating them with Earth system models. "We're extending our machine learning model to a global scale and integrating it with the Earth system model," Song said.
Findings from this project could potentially inform future reports by the Intergovernmental Panel on Climate Change. Improved models may help scientists better predict how soil carbon responds to climate change, influencing atmospheric carbon dioxide concentration.
"Besides providing insights about the role soil microbial communities have on soil biogeochemistry, the findings can help make workable plans to improve our climate models," Song added.