Machine Learning Methods to Determine Arctic Methane Emissions
Methane has more than 80 times the warming power of carbon dioxide over the first 20 years after it reaches the atmosphere. Arctic lakes are important sources of increasing methane emissions as they are experiencing more prolonged ice-free periods and more available carbon from permafrost thaw. In spite of this importance, their contribution to increased global atmospheric methane is not well understood. Spring release of methane trapped in bubbles and below the ice (ice-out bubbling) is one of the key processes of methane emission from the Arctic lakes. Current estimates of the emission fluxes vary by almost a factor of four from 7 to 26 Tg per year, largely due to the existing uncertainties in estimation of lake areas and thaw period from satellite data. This large uncertainty is a serious bottleneck in better understanding the impacts of the thawing Arctic on global warming and prevents us from properly envisioning and implementing climate adaptation and mitigation strategies. Associate Professor Ardeshir Ebtehaj (Civil, Environmental, and Geo- Engineering; MSI PI) and Dr. Michael Steinbach (College of Science and Engineering; MSI PI) are working on a project called “Advancing data science foundation for shrinking the uncertainties in bottom-up estimates of methane emission from Arctic lakes,” that aims to provide initial results showing that advances in machine learning fundamentals can shrink the existing uncertainties and help us to better understanding the impacts of the thawing Arctic on global warming.
This project received a DSI Seed Grant. The Seed Grant program is intended to promote, catalyze, accelerate, and advance U of M-based data science research so that U of M faculty and staff are well prepared to compete for longer term external funding opportunities.
The program was updated in Summer 2024 to include three focus areas: Foundational Data Sciences; Digital Health and Personalized Health Care Delivery; and Agriculture and the Environment (new focus area). This project falls under the Global Food and Environment research areas of the MnDRIVE initiative and the Foundational Data Sciences focus area.
The types of awards are Rapid Response Grants and new types, Awards for DSI Faculty Fellowship and Data Sets (Data as an Asset).
