ML for Earth System Modelling and Analytics workshop 2021


DKRZ/HZG/GERICS co-organize a workshop, supported by Helmholtz AI, to facilitate knowledge exchange and discussion about the state of the art and future directions of applying ML methods in Earth System modelling, analytics, and impact research.

To overcome limitations in computing and data analytics related to Earth System science, the uptake of artificial intelligence (AI) and machine learning (ML) methodologies is currently being explored. Multiple initiatives are now emerging to tackle open challenges such as subscale parametrization, detection of patterns and in-situ analysis, adoption of ML for alternative process models, or dedicated fast prediction systems to address specific end-user needs.

Following the first workshop held in February 2020, this second workshop will provide an update on the state of the art in applying and extending AI/ML techniques in topics relevant to Earth System science, from integrating ML with models to deriving new insights from observational data, to extending AI/ML to impact models and approaches. We call for contributions to the sessions, offering presentation and lightning talk slots for those interested in submitting an abstract (abstract submission is now closed). Contributions are welcome from all participants, from updates on ongoing research activities and future plans to technical insights worthwhile to share.

The workshop will take place on the afternoons of May 03/04, 2021, from about 14:30-18:00 CEST. The workshop will be an exclusively online event. The workshop is co-organized by DKRZ, HZG and GERICS with support from Helmholtz AI.

Workshop co-organizers:
Laurens Bouwer (GERICS), Christopher Kadow (DKRZ), Tobias Weigel (DKRZ/Helmholtz AI), Eduardo Zorita (HZG)

    • 2:30 PM 2:45 PM
      Welcome, logistics 15m
    • 2:45 PM 3:15 PM
      Keynote 1: Leveraging Artificial Intelligence and Big data across the disaster risk management cycle; opportunities and challenges for the Red Cross 30m
      Speaker: Marc van den Homberg (510/Netherlands Red Cross)
    • 3:15 PM 3:20 PM
      Short break 5m
    • 3:20 PM 4:45 PM
      Parallel sessions day 1: Earth System Modelling
      Convener: Christopher Kadow (DKRZ)
      • 3:20 PM
        An ML Perspective on Closed Loop Tuning in Earth Science Simulators 15m
        Speaker: David Greenberg (Hereon)
      • 3:35 PM
        A machine learning-based air quality forecast system for Pacific Northwest 15m
        Speaker: Kai Fan (CASUS/HZDR)
      • 3:50 PM
        Near-surface temperature forecasting by deep learning 15m
        Speaker: Bing Gong (Juelich Supercomputing Center)
      • 4:05 PM
        Using machine learning techniques to classify ENSO events 15m
        Speaker: Nicola Maher (U. Colorado, Boulder/MPI for Meteorology)
      • 4:20 PM
        The Frontiers of Deep Learning for the Earth System Sciences 15m
        Speaker: David Hall (NVIDIA)
    • 3:20 PM 4:45 PM
      Parallel sessions day 1: Extreme Events and Impacts
      Convener: Laurens Bouwer (GERICS)
      • 3:20 PM
        Machine learning model of the plasmasphere to forecast satellite charging caused by solar storms 15m
        Speaker: Stefano Bianco (GFZ Potsdam)
      • 3:35 PM
        Denoising seismic data using a ResNeXt-50-based convolutional autoencoder 15m
        Speaker: Jan Walda (University of Hamburg)
      • 3:50 PM
        Artificial Intelligence for flood analysis: first results from the AI4Flood project 15m
        Speaker: Shagun Garg (GFZ Potsdam)
      • 4:05 PM
        Automated Damage Assessment 15m
        Speaker: Jacopo Margutti (Netherlands Red Cross)
      • 4:20 PM
        Supervised Machine Learning to investigate Heat Waves and Myocardial Infarctions in Augsburg, Germany 15m
        Speaker: Lennart Marien (GERICS)
    • 4:45 PM 5:00 PM
      Break 15m
    • 5:00 PM 5:15 PM
      Neural Earth System Modelling 15m
      Speaker: Christopher Irrgang (GFZ Potsdam)
    • 5:15 PM 6:00 PM
      Discussion (co-chaired by C. Kadow & L. Bouwer) 45m
    • 2:30 PM 3:10 PM
      Lightning talks
      Convener: Tobias Weigel (DKRZ)
    • 3:10 PM 3:40 PM
      Lightning talks: Lightning talks interaction session
    • 3:40 PM 3:45 PM
      Short break 5m
    • 3:45 PM 5:15 PM
      Parallel sessions day 2: Earth System Modelling
      Conveners: Christopher Kadow (DKRZ), Eduardo Zorita (Hereon)
      • 3:45 PM
        3D bias correction with deep learning in the Integrated Forecasting System 15m
        Speaker: Thorsten Kurth (NVIDIA)
      • 4:00 PM
        Building an Earth System Model emulator for local monthly temperature 15m
        Speaker: Shruthi Nath (Climate Analytics/ETH Zürich)
      • 4:15 PM
        Machine learning based post-processing of 2-m air temperature model output – a multi-model approach 15m
        Speaker: Gabriel Stachura (Institute of Meteorology and Water Management (Poland))
      • 4:30 PM
        Lossy Compression of Climate Data using Convolutional Autoencoders 15m
        Speaker: Silke Donayre Holtz (KIT)
      • 4:45 PM
        Building a versioned pipeline for ML-based quality control of environmental sensor data 15m
        Speaker: Julius Polz (KIT)
    • 3:45 PM 5:15 PM
      Parallel sessions day 2: Remote sensing and marine ecosystems
      Convener: Tobias Weigel (DKRZ)
      • 3:45 PM
        Quantifying the impact of bedrock uncertainty on ice sheet model simulations by Gaussian Process modelling 15m
        Speaker: Andreas Wernecke (MPI for Meteorology)
      • 4:00 PM
        Remote Sensing of Global Ocean Wind Speed using GNSS Reflectometry and AI 15m
        Speaker: Milad Asgarimehr (GFZ Potsdam)
      • 4:15 PM
        Approximation of a marine ecosystem model using artificial neural networks 15m
        Speaker: Markus Pfeil (Kiel University)
      • 4:30 PM
        Artificial Intelligence for Cold Regions (AI-CORE) - a Pilot to bridge Data Analytics and Infrastructure Development 15m
        Speaker: Long Duc Phan (AWI)
    • 5:15 PM 5:30 PM
      Break 15m
    • 5:30 PM 6:00 PM
      Keynote 2: A mile wide and a pixel deep: Integrating computer vision and satellite imagery for coupled-natural human system modeling 30m
      Speaker: Kelly Caylor (UCSB)
    • 6:00 PM 6:10 PM
      Wrap-up 10m