Our workshop proposal AI for Earth sciences seeks to bring cutting edge geoscientific and planetary challenges to the fore for the machine learning and deep learning communities. We seek machine learning interest from major areas encompassed by Earth sciences which include, atmospheric physics, hydrologic sciences, cryosphere science, oceanography, geology, planetary sciences, space weather, volcanism, seismology, geo-health (i.e. water, land, air pollution, environmental epidemics), biosphere, and biogeosciences. We also seek interest in AI applied to energy for renewable energy meteorology, thermodynamics and heat transfer problems. We call for papers demonstrating novel machine learning techniques in remote sensing for meteorology and geosciences, generative Earth system modeling, and transfer learning from geophysics and numerical simulations and uncertainty in Earth science learning representations. We also seek theoretical developments in interpretable machine learning in meteorology and geoscientific models, hybrid models with Earth science knowledge guided machine learning, representation learning from graphs and manifolds in spatiotemporal models and dimensionality reduction in Earth sciences. In addition, we seek Earth science applications from vision, robotics, multi-agent systems and reinforcement learning. New labelled benchmark datasets and generative visualizations of the Earth are also of particular interest. A new area of interest is in integrated assessment models and human-centered AI for Earth.
AI4Earth Areas of Interest:
- Atmospheric Science
- Hydro and Cryospheres
- Solid Earth
- Theoretical Advances
- Remote Sensing
- Energy in the Earth system
- Extreme weather & climate
- Geo-health
- Biosphere & Biogeosciences
- Planetary sciences
- Benchmark datasets
- People-Earth
| Link to Gather.Town for Casual Conversation (Break) | |
| Introduction and opening remarks (Introduction) | |
| Sensors and Sampling (Session Introduction) | |
| Yogesh Girdhar - Enabling Vision Guided Interactive Exploration in Bandwidth Limited Environments (Sensing and Sampling - Session Keynote) | |
| Eyes in the sky without boots on the ground: Using satellites and machine learning to monitor agriculture and food security during COVID-19 (Sensors and Sampling - Invited Talk) | |
| Autonomous Robot Manipulation for Planetary Science: Mars Sample Return, Climbing Lava Tubes (Sensing and Sampling - Invited Talk) | |
| DeepFish: A realistic fish‑habitat dataset to evaluate algorithms for underwater visual analysis (Sensors and Sampling - Invited Talk) | |
| Automatic three‐dimensional mapping for tree diameter measurements in inventory operations (Sensors and Sampling - Invited Talk) | |
| Q/A and Discussion for Sensing & Sampling Session (Q/A and Discussion) | |
| Ecology (Session Introduction) | |
| Dan Morris (Keynote) | |
| Giulio De Leo (Ecology - Session Keynote) | |
| Graph Learning for Inverse Landscape Genetics (Regular Talk - Ecology Session) | |
| Segmentation of Soil Degradation Sites in Swiss Alpine Grasslands with Deep Learning (Regular Talk - Ecology Session) | |
| Novel application of Convolutional Neural Networks for the meta-modeling of large-scale spatial data (Lightning Talk - Ecology Session) | |
| Understanding Climate Impacts on Vegetation with Gaussian Processes in Granger Causality (Lightning Talk - Ecology Session) | |
| Interpreting the Impact of Weather on Crop Yield Using Attention (Lightning Talk - Ecology Session) | |
| Q/A and Discussion for Ecology Session (Q/A and Discussion) | |
| Water (Session Introduction) | |
| Pierre Gentine (Water - Session Keynote) | |
| A Machine Learner's Guide to Streamflow Prediction (Spotlight Talk - Water Session) | |
| A Deep Learning Architecture for Conservative Dynamical Systems: Application to Rainfall-Runoff Modeling (Spotlight Talk - Water Session) | |
| Dynamic Hydrology Maps from Satellite-LiDAR Fusion (Spotlight Talk - Water Session) | |
| Efficient Reservoir Management through Deep Reinforcement Learning (Regular Talk - Water Session) | |
| Q/A and Discussion for Water Session (Q/A and Discussion) | |
| Milind Tambe (Keynote) | |
| Q/A and Discussion | |
| Atmosphere (Session Introduction) | |
| Michael Pritchard (Atmosphere - Session Keynote) | |
| Elizabeth Barnes (Atmosphere - Session Keynote) | |
| Spatio-temporal segmentation and tracking of weather patterns with light-weight Neural Networks (Spotlight Talk - Atmosphere Session) | |
| Leveraging Lightning with Convolutional Recurrent AutoEncoder and ROCKET for Severe Weather Detection (Spotlight Talk - Atmosphere Session) | |
| Towards Data-Driven Physics-Informed Global Precipitation Forecasting from Satellite Imagery (Lightning Talk - Atmosphere Session) | |
| Q/A and Discussion for Atmosphere Session (Q/A and Discussion) | |
| Simulations, Physics-guided, and ML Theory (Session Introduction) | |
| Stephan Mandt (Simulations, Physics-guided, and ML Theory - Session Keynote) | |
| Rose Yu (Simulations, Physics-guided, and ML Theory - Session Keynote) | |
| Generating Synthetic Multispectral Satellite Imagery from Sentinel-2 (Regular Talk - ML Theory) | |
| Multiresolution Tensor Learning for Efficient and Interpretable Spatiotemporal Analysis (Regular Talk - ML Theory) | |
| Climate-StyleGAN : Modeling Turbulent ClimateDynamics Using Style-GAN (Regular Talk - ML Theory) | |
| Interpretable Deep Generative Spatio-Temporal Point Processes (Lightning Talk - ML Theory) | |
| Completing physics-based model by learning hidden dynamics through data assimilation (Lightning Talk - ML Theory Session) | |
| Q/A and Discussion for ML Theory Session (Q/A and Discussion) | |
| People-Earth (Session Introduction) | |
| Q/A and Panel Discussion for People-Earth with Dan Kammen and Milind Tambe (Q/A and Panel Discussion) | |
| Solid Earth (Session Introduction) | |
| Soft Attention Convolutional Neural Networks for Rare Event Detection in Sequences (Spotlight Talk - Solid Earth Session) | |
| An End-to-End Earthquake Monitoring Method for Joint Earthquake Detection and Association using Deep Learning (Regular Talk - Solid Earth) | |
| Single-Station Earthquake Location Using Deep Neural Networks (Regular Talk - Solid Earth) | |
| Framework for automatic globally optimal well log correlation (Lightning Talk - Solid Earth Session) | |
| Q/A and Discussion for Solid Earth (Q/A and Discussion) | |
| Benchmark Datasets (Session Introduction) | |
| Stephan Rasp (Benchmark Datasets - Session Keynote) | |
| RainBench: Enabling Data-Driven Precipitation Forecasting on a Global Scale (Spotlight Talk - Benchmark Datasets) | |
| WildfireDB: A Spatio-Temporal Dataset Combining Wildfire Occurrence with Relevant Covariates (Spotlight Talk - Benchmark Datasets Session) | |
| LandCoverNet: A global benchmark land cover classification training dataset (Regular Talk - Benchmark Datasets Session) | |
| Applying Machine Learning to Crowd-sourced Data from Earthquake Detective (Regular Talk - Benchmark Datasets Session) | |
| An Active Learning Pipeline to Detect Hurricane Washover in Post-Storm Aerial Images (Lightning Talk - Benchmark Datasets Session) | |
| Developing High Quality Training Samples for Deep Learning Based Local Climate Classification in Korea (Lightning Talk - Benchmark Datasets Session) | |
| Q/A and Discussion for Benchmark Datasets (Q/A and Discussion) | |
| Posters (Posters - Break (On Demand Pre-recorded Not Livestreamed)) | |
| Workshop Closing Remarks | |
| Towards Automated Satellite Conjunction Management with Bayesian Deep Learning (Poster - Sensing and Sampling Session) | |
| Semantic Segmentation of Medium-Resolution Satellite Imagery using Conditional Generative Adversarial Networks (Poster - ML Theory) | |
| Spectral Unmixing With Multinomial Mixture Kernel and Wasserstein Generative Adversarial Loss (Poster - Sensing and Sampling Session) | |
| Temporally Weighting Machine Learning Models for High-Impact Severe Hail Prediction (Poster - Atmosphere Session) | |
| Bias correction of global climate model using machine learning algorithms to determine meteorological variables in different tropical climates of Indonesia (Poster - Atmosphere Session) | |
| Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery (Poster - Sensing and Sampling Session) | |
| Optimising Placement of Pollution Sensors in Windy Environments (Poster - Atmosphere Session) | |
| Predicting Streamflow By Using BiLSTM with Attention from heterogeneous spatiotemporal remote sensing products (Poster - Water Session) | |
| Integrating data assimilation with structurally equivariant spatial transformers: Physically consistent data-driven models for weather forecasting (Poster - Atmosphere Session) | |
| Inductive Predictions of Extreme Hydrologic Events in The Wabash River Watershed (Poster - Water Session) | |
| A Comparison of Data-Driven Models for Predicting Stream Water Temperature (Poster - Water Session) | |
| Domain Adaptive Shake-shake Residual Network for Corn Disease Recognition (Poster - Sensing and Sampling Session) | |
| MonarchNet: Differentiating Monarch Butterflies from Those with Similar Appearances (Poster - Benchmark Datasets Session) | |
| Unsupervised Regionalization of Particle-resolved Aerosol Mixing State Indices on the Global Scale (Poster - Atmosphere Session) | |
| Nowcasting Solar Irradiance Over Oahu (Poster - Atmosphere Session) | |