DOE seeks information on AI uses for climate change mitigation, grid resilience

The Department of Energy is seeking information on a variety of artificial intelligence-related topics regarding the White House’s AI executive order, which calls on the agency to leverage the technology’s potential on everything from mitigating climate change risks to securing electric power.

In a document scheduled to post Friday on the Federal Register, the DOE said it is looking for information that will aid the agency in delivering its public report on AI, due within 180 days of the executive order’s issuance. The order called on the DOE’s report to detail the potential AI could have to “improve planning, permitting, investment, and operations for electric grid infrastructure and to enable the provision of clean, affordable, reliable, resilient, and secure electric power to all Americans.”

The request for information features a lengthy callout for responses on how AI can be used to “strengthen the nation’s resilience against climate change, including opportunities to help predict, prepare for, and mitigate climate-driven risk.”

The “non-exhaustive list of topics” it seeks comments on include the forecasting of extreme climate-driven events such as hurricanes and wildfires, projections on long-term climate impacts on resource levels, and how to improve and expedite numerical weather prediction models.

AI’s potential to “improve the security and reliability of grid infrastructure and operations and their resilience to disruptions” is another callout in DOE’s RFI, which welcomes contributions from private actors, public-private partnerships and all levels of government.

The DOE said it is interested specifically in how AI can improve grid reliability through predictive maintenance for utilities, more efficient load and supply balance, and better demand management for technologies like EV charging and smart devices, and improved flexibility of power systems models and related connected software. 

On the topic of grid resiliency, the DOE is interested in the effects of climate hazards on electricity infrastructure, climate mapping for resilience and adaptation outputs, and AI-enabled threat detection and “real-time self-healing infrastructure.” 

Finally, the DOE wants to know how AI can “improve planning, permitting, and investment in the grid and related clean energy infrastructure.” Leveraging the technology to expedite siting and permitting, improve project planning, validate and monitor current projects, and enhance the compatibility of datasets are among the uses of interest to the agency.

The DOE will solicit information for 30 days following Friday’s publication. Comments can be submitted electronically or mailed to the agency’s Washington, D.C. headquarters.