Axel Timmermann, Application of deep convolutional neural networks for detecting extreme weather in climate datasets

Abstract:

Detecting extreme events in large datasets is a major challenge in climate science research. Current algorithms for extreme event detection are build upon human expertise in defining events based on subjective thresholds of relevant physical variables. Often, multiple competing methods produce vastly different results on the same dataset. Accurate characterization of extreme events in climate simulations and observational data archives is critical for understanding the trends and potential impacts of such events in a climate change content. This study presents the first application of Deep Learning techniques as alternative methodology for climate extreme events detection. Deep neural networks are able to learn high-level representations of a broad class of patterns from labeled data. In this work, we developed deep Convolutional Neural Network (CNN) classification system and demonstrated the usefulness of Deep Learning technique for tackling climate pattern detection problems. Coupled with Bayesian based hyper-parameter optimization scheme, our deep CNN system achieves 89\%-99\% of accuracy in detecting extreme events (Tropical Cyclones, Atmospheric Rivers and Weather Fronts

Bio:

Axel Timmermann is a German climate physicist and oceanographer with an interest in climate dynamics, human migration, dynamical systems’ analysis, ice-sheet modeling and sea level. He served a co-author of the IPCC Third Assessment Report[1] and a lead author of IPCC Fifth Assessment Report.[2] His research has been cited over 18,000 times and has an h-index of 70 and i10-index of 161.[3] In 2017, he became a Distinguished Professor at Pusan National University and the founding Director of the Institute for Basic Science Center for Climate Physics. In December 2018, the Center began to utilize a 1.43-petaflop Cray XC50 supercomputer, named Aleph, for climate physics research.