Exascale Deep Learning for Climate Analytics ( TF Dev Summit 19)

Climate change will have fundamental socioeconomic impact and it is imperative for us to understand it better. This talk will show how TensorFlow was utilized on the worlds fastest supercomputer in order to extract pixel level segmentation masks of extreme weather phenomena in climate simulation data, thereby enabling climate scientists to perform highfidelity, fine grained geospatial analyses of the effects of climate change. Speaker: Thorsten Kurth, Lawrence Berkeley National Library See the revamp