Skip to content

MESMERIZE: Macro-Energy System Model with Equity, Realism and Insight in Zero Emissions 

Precourt Pioneering Project

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

Background

The Stanford Energy and Climate AI Hub  will provide a one-stop
gateway for Stanford-generated models, advanced computational
algorithms, curated data sets, and data products. The Climate/Energy
AI Hub will be used as a platform to develop the next generation of
interdisciplinary models needed to identify the most cost effective
and equitable climate and energy solutions for net zero emissions
over the coming decades. The key question that will be asked is
“What are realistic and implementable pathways for sustainable
and deeply decarbonized energy systems that include features
of real policies, people’s decisions and behaviors and account
for environmental justice?”.


Project Goal

The Stanford Energy & Climate AI Hub aims to put Stanford at the forefront of decarbonization and environmental justice research. The researchers will develop MESMERIZE: A Macro-Energy System Model with Equity, Realism and Insight in Zero Emissions. The model will provide reliable information about the most effective pathways, costs, benefits, and societal and environmental impacts for deployment of effective and equitable energy solutions.


Tasks and Timeline

A collaboration suite for energy and climate systems models and data will be developed. This people and policy centered computational hub will help identify solutions for energy and climate change mitigation.

The project will involve two key efforts:

• Develop and support an interdisciplinary simulation and optimization modeling platform to determine the most effective technological, financial, and equitable climate and energy solutions that describe real decisions and behaviors from people/agents as the world drives toward net zero emissions over the coming decades.

• Provide resources for modeling and decision making to others. Provide a gateway for Stanford-generated models, advanced computational algorithms, curated data sets, and data products to the broader community inside and outside of Stanford.


 

Team Members

Professor Azevedo’s research focuses on the transition to sustainable energy system and in assessing the distributional and environmental justice aspects associated with decarbonization transitions. She has developed several models to estimate the operations and emissions of the U.S. power sector and coupled those with air quality models.

Sally Benson has developed capacity expansion and operation models of the grid under climate goals, namely with an application to California. She is also developing computational tools for quantifying Scope 3 emissions and developing machine learning (ML) models for CO2 storage.

Adam Brandt works on optimization questions applied to energy systems. He has recently started an effort using ML to perform temporal for electricity capacity expansion models as well as using ML to predict solar output using camera images.

Ram Rajagopal is using state of the art clustering and data analysis techniques to understand load patterns, vehicle charging patters, and other energy related data.

John Weyant brings decades of expertise on Integrated Assessment Models for Climate Change. John also has a deep knowledge of California and international policy design and interaction.

Jacques de Chalendar has used ML techniques to estimate the carbon intensity of imports across the U.S. grid, providing consumption-based emissions estimates for the power sector. He is also responsible for the unique data tool for energy systems assessment for the Stanford Campus.