My DOE ECRP work was recently featured in an article on the Department of Energy’s ASCR Discovery website. This article describes all of the machine learning work the recent early-career honorees are doing, including my own that couples machine learning with topological analysis.
Images were generated using TTK.
These compare data from a recent climate simulation, CMIP6, CMCC-CM2-VHR4 highresSST-present, which I accessed through the Earth System Grid Federation (ESGF). I show two time stamps that compare the average near-surface air temperature for the month of January in both 1950 and 2010. The data is then segmented using the join tree, a topological structure that builds a hierarchy of the level sets associated with coldest positions.
We acknowledge the World Climate Research Programme, which, through its Working Group on Coupled Modelling, coordinated and promoted CMIP6. We thank the climate modeling groups for producing and making available their model output, the Earth System Grid Federation (ESGF) for archiving the data and providing access, and the multiple funding agencies who support CMIP6 and ESGF.