Harnessing Machine Learning to Investigate Climate Change Impacts on Renewable Energy Systems in the United States

As the climate crisis intensifies, switching to renewable energy remains a critical piece of the solution to ensure rapid decarbonization. However, renewable energy generation is highly reliant on the ambient environmental conditions, making it difficult to estimate the long-term generation—a task that is likely to get more difficult under climate change. Accounting for the impact of climate change is particularly difficult, as there remains uncertainty related to the magnitude of climate change within the mid- and long-term in addition to the relatively unknown impacts of climate change on generation of renewable energy technologies. In this work, we aim to fill this gap by leveraging machine learning to investigate the impact of climate change on state-level renewable energy generation across the US. Using data from the Energy Information Administration (EIA), we project the solar, wind, and hydropower generation across multiple US states under two key climate change scenarios. Our goal is to answer two key questions: (1) How will climate change impact renewable energy generation; and (2) Do these impacts differ across states? To answer these questions, we leveraged several machine learning techniques, as well as an ensemble of models, to first model the observed relationship between renewable energy generation and the surrounding weather and climate. Then, we used those same models to project the changes to the system, given the most recent IPCC climate change scenarios. Here, we will present the results from the projection analysis across multiple US states, including the states of California, New York, Florida, and Georgia, which contain some of the largest electric utilities in the country. The results indicate significant changes across different states and seasons, which could impact grid management and planning. Ultimately, the results will provide critical insights into the sustainability of renewable energy technologies over the long-term, given the reality of climate change.