Skip to content

AI for Decarbonized, Climate-Resilient, and Equitable Energy Infrastructure and Services

 

Precourt Pioneering Project

Awarded in the area of Artificial Intelligence (AI) to solve critical challenges in energy, climate, and integrated energy systems.

Background

The electricity grid is undergoing a transformation with
the addition of renewable power, natural gas generation,
heat pumps for residential heating, electric vehicles, and
adoption 
of information technology to understand when
and how we use this power. These changes 
are highlighting
the interrelation of the power grid, natural gas, transportation,
information, 
and the inequality of access by communities
to these infrastructures. This inequality is 
highlighted by
the issues faced when the grid and power infrastructure
lack resilience against 
extreme weather events.


Project Goals

This project is aimed at answering three major questions to achieve the goals of decarbonization, equity and resilience, from the neighborhood to the national level.

1. How do we build a decarbonized energy system that serves all people and is resilient to climate change and extreme events?
2. How do we assess climate risks and population vulnerability?
3. How do we adapt?


Approach and Timeline

Machine learning will be used to optimize four criteria simultaneously: decarbonization, equity, affordability, and resilience to the impacts of climate change, including extreme weather events. Using a spatially aware approach the researchers will consider contextual features such as hotspots where extreme weather events are likely to occur, the impacts to infrastructure, and to people and services. The tools created will be made publicly available, and the information will be provided to grid operators, planners, policymakers, and others across the U.S. and world.

In year 1, the team will build the extreme event scenario analysis and forecasting modules; the key metrics of the Access Atlas, including algorithms for vulnerability detection; complete mapping work in Energy Atlas; and begin work on the management module by investigating optimal reserve management strategies.

In year 2, the team will build and make publicly available: Access Atlas, Grid Risk Atlas; Energy Atlas; and Pre-post grid adaptation management.


 

Team Members

Ram Rajagopal is an expert in power systems and machine learning. He has published >300 papers in data-driven analytics of power systems and smart grid. Directs the Stanford Global Projects Center and the Sustainable Systems Lab. Has led large DOE projects, including Powernet, an ARPA-e NODES program

Prof. Arun Majumdar is an expert in power systems and energy policy. He was the founding director of the Advanced Research Projects Agency - Energy (ARPA-E) under the Department of Energy.

Andrew Ng is VP & Chief Scientist of Baidu; Co-Chairman and Co-Founder of Coursera; and an Adjunct Professor at Stanford University.  In 2011 he led the development of Stanford University’s main MOOC (Massive Open Online Courses) platform and also taught an online Machine Learning class that was offered to over 100,000 students, leading to the founding of Coursera.

Prof. Ines Azevedo research focuses on sustainable, realistically feasible and equitable energy systems. Her work uses quantitative models to understand the effects of policies and decisions on environmental, climate, economic and air pollution related outcomes, with an emphasis on incorporating distributional and environmental justice issues.