Shortcomings in both climate science and computing capacities limit the accuracy of climate projections needed for optimal adaptation and resilience to climate change. Our team sees tremendous promise in developing a convergent approach integrating machine learning and climate simulations that can substantially reduce uncertainty in climate projections through 2050. This ambitious endeavor engages our nation’s top climate research laboratories (e.g., NCAR and NASA GISS) with major computing organizations (e.g., Google) and a diverse array of stakeholders, from companies to community organizations, that can benefit from more accurate projections.

Ameliorating this critical shortcoming is a worthy and necessary venture for our nation and the world, and could improve life for generations to come. Such ambitious goals are only achievable through a large-scale and long-term effort covering research, education, and knowledge transfer, such as provided by the National Science Foundation Science and Technology Center (STC).