Building a Climate Machine (CliMa): High Performance Computing, Heterogeneous Computing, and Machine Learning
The Climate Machine (https://clima.caltech.edu/) is a new Earth system model that leverages recent advances in the computational and data sciences to learn directly from a wealth of Earth observations from space and the ground. The Climate Machine will harness more data than ever before, providing a new level of accuracy to predictions of droughts, heat waves, and rainfall extremes.
Students working on this project can choose from a wide variety of interesting projects ranging from computer graphics visualizations of climate data, High Performance Computing (supercomputing) problems related to scaling computation on large, distributed networks of both graphics processing units and central processing units, and machine learning for creating highly accurate simulations. This project has been designed entirely with the Julia programming language (https://julialang.org/), which provides the power and flexibility to solve each issue presented here.
Students working on this project will have the opportunity to work with the fundamentals of the Julia ecosystem and also with a large collaboration spanning institutions like MIT, CalTech, and the Naval Postgraduate School (NPS).