Workshop: AI for Earth Sciences
Karthik Mukkavilli, Johanna Hansen, Natasha Dudek, Tom Beucler, Kelly Kochanski, Mayur Mudigonda, Karthik Kashinath, Amy McGovern, Paul D Miller, Chad Frischmann, Pierre Gentine, Gregory Dudek, Aaron Courville, Daniel Kammen, Vipin Kumar
Sat, Dec 12th @ 14:45 GMT – Sun, Dec 13th @ 05:00 GMT
Abstract: 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
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
Video
Chat
Chat is not available.
Schedule
14:45 – 14:55 GMT
Introduction and opening remarks
Karthik Mukkavilli
AI for Earth Sciences, Workshop Founder & Chair, S. Karthik Mukkavilli
14:55 – 14:58 GMT
Sensors and Sampling
Johanna Hansen
Sensors and Sampling, Session Chair, Johanna Hansen
14:58 – 15:22 GMT
Yogesh Girdhar - Enabling Vision Guided Interactive Exploration in Bandwidth Limited Environments
Yogesh A Girdhar
WARPLab's research focuses on both the science and systems of exploration robots in extreme, communication starved environments such as the deep sea. It aims to develop robotics and machine learning-based techniques to enable search, discovery, and mapping of natural phenomena that are difficult to observe and study due to various physical and information-theoretic challenges. WARPLab is headed by Yogesh Girdhar, and is part of the Deep Submergence Laboratory (DSL), and the Applied Ocean Physics & Engineering (AOPE) department at Woods Hole Oceanographic Institution.
15:22 – 15:35 GMT
Eyes in the sky without boots on the ground: Using satellites and machine learning to monitor agriculture and food security during COVID-19
Hannah Kerner
Talk Title: "Eyes in the sky without boots on the ground: Using satellites and machine learning to monitor agriculture and food security during COVID-19" Hannah Kerner is an Assistant Research Professor at the University of Maryland, College Park. Her research focuses on developing machine learning solutions for remote sensing applications in agricultural monitoring, food security, and Earth/planetary science. She is the Machine Learning Lead and U.S. Domestic Co-Lead for NASA Harvest, NASA’s food security initiative run out of the University of Maryland.
15:35 – 15:58 GMT
Autonomous Robot Manipulation for Planetary Science: Mars Sample Return, Climbing Lava Tubes
Renaud Detry
Talk Title: Autonomous Robot Manipulation for Planetary Science: Mars Sample Return, Climbing Lava Tubes This talk will highlight work at NASA on robotic missions from a machine vision perspective. The discussion will focus on the science questions that NASA hopes to answer through returned samples from Mars and the challenges imposed on robotic systems used for scientific data collection. Related Papers: http://renaud-detry.net/publications/Pham-2020-AEROCONF.pdf https://www.liebertpub.com/doi/10.1089/ast.2019.2177 Renaud Detry is the group leader for the Perception Systems group at NASA's Jet Propulsion Laboratory (JPL). Detry earned his Master's and Ph.D. degrees in computer engineering and robot learning from ULiege in 2006 and 2010. He served as a postdoc at KTH and ULiege between 2011 and 2015, before joining the Robotics and Mobility Section at JPL in 2016. His research interests are perception and learning for manipulation, robot grasping, and mobility, for terrestrial and planetary applications. At JPL, Detry leads the machine-vision team of the Mars Sample Return surface mission, and he leads and contributes to a variety of research projects related to industrial robot manipulation, orbital image understanding, in-space assembly, and autonomous wheeled or legged mobility for Mars, Europa, and Enceladus.
15:58 – 16:06 GMT
DeepFish: A realistic fish‑habitat dataset to evaluate algorithms for underwater visual analysis
Alzayat Saleh, Issam Hadj Laradji, David Vázquez
Visual analysis of complex fish habitats is an important step towards sustainable fisheries for human consumption and environmental protection. Deep Learning methods have shown great promise for scene analysis when trained on large-scale datasets. However, current datasets for fish analysis tend to focus on the classification task within constrained, plain environments which do not capture the complexity of underwater fish habitats. To address this limitation, we present DeepFish as a benchmark suite with a large-scale dataset to train and test methods for several computer vision tasks. The dataset consists of approximately 40 thousand images collected underwater from 20 habitats in the marine-environments of tropical Australia. The dataset originally contained only classification labels. Thus, we collected point-level and segmentation labels to have a more comprehensive fish analysis benchmark. These labels enable models to learn to automatically monitor fish count, identify their locations, and estimate their sizes. Our experiments provide an in-depth analysis of the dataset characteristics, and the performance evaluation of several state-of-the-art approaches based on our benchmark. Although models pre-trained on ImageNet have successfully performed on this benchmark, there is still room for improvement. Therefore, this benchmark serves as a testbed to motivate further development in this challenging domain of underwater computer vision.
16:06 – 16:20 GMT
Automatic three‐dimensional mapping for tree diameter measurements in inventory operations
Jean-François Tremblay
Forestry is a major industry in many parts of the world, yet this potential domain of application area has been overlooked by the robotics community. For instance, forest inventory, a cornerstone of efficient and sustainable forestry, is still traditionally performed manually by qualified professionals. The lack of automation in this particular task, consisting chiefly of measuring tree attributes, limits its speed, and, therefore, the area that can be economically covered. To this effect, we propose to use recent advancements in three‐dimensional mapping approaches in forests to automatically measure tree diameters from mobile robot observations. While previous studies showed the potential for such technology, they lacked a rigorous analysis of diameter estimation methods in challenging and large‐scale forest environments. Here, we validated multiple diameter estimation methods, including two novel ones, in a new publicly‐available dataset which includes four different forest sites, 11 trajectories, totaling 1458 tree observations, and 14,000 m2. From our extensive validation, we concluded that our mapping method is usable in the context of automated forest inventory, with our best diameter estimation method yielding a root mean square error of 3.45 cm for our whole dataset and 2.04 cm in ideal conditions consisting of mature forest with well‐spaced trees. Furthermore, we release this dataset to the public (https://norlab.ulaval.ca/research/montmorencydataset), to spur further research in robotic forest inventories. Finally, stemming from this large‐scale experiment, we provide recommendations for future deployments of mobile robots in a forestry context. Jean-François is a Ph.D. student at McGill’s Mobile Robotics Lab, under the supervision of prof. Dave Meger. He is interested in model-based RL for mobile robot navigation in unstructured environments such as forests, tundra or underwater. Previously he was a masters student at the Northern Robotics Laboratory (Norlab), working on lidar mapping and perception for forestry applications.
16:20 – 16:55 GMT
Q/A and Discussion for Sensing & Sampling Session
Johanna Hansen, Yogesh A Girdhar, Hannah Kerner, Renaud Detry
Moderated by Johanna Hansen
17:00 – 17:25 GMT
Dan Morris
D. Morris
Program Director of Microsoft AI for Earth
17:25 – 17:55 GMT
Giulio De Leo
Giulio De Leo
Talk Title (tentative): ML and control of parasitic diseases of poverty in tropical and subtropical countries, with a special focus on schistosomiasis Professor at Stanford University Senior Fellow at Stanford Woods Institute for the Environment
18:05 – 18:15 GMT
Segmentation of Soil Degradation Sites in Swiss Alpine Grasslands with Deep Learning
Maxim Samarin
18:15 – 18:20 GMT
Novel application of Convolutional Neural Networks for the meta-modeling of large-scale spatial data
Kiri A. Stern
18:20 – 18:25 GMT
Understanding Climate Impacts on Vegetation with Gaussian Processes in Granger Causality
Miguel Morata Dolz
18:25 – 18:30 GMT
Interpreting the Impact of Weather on Crop Yield Using Attention
Tryambak Gangopadhyay
18:30 – 18:55 GMT
Q/A and Discussion for Ecology Session
Natasha Dudek, D. Morris, Giulio De Leo
Moderated by Natasha Dudek
19:25 – 19:40 GMT
A Machine Learner's Guide to Streamflow Prediction
Martin Gauch
Long Oral (15m)
19:40 – 19:55 GMT
A Deep Learning Architecture for Conservative Dynamical Systems: Application to Rainfall-Runoff Modeling
Grey Nearing
Long Talk (15m)
19:55 – 20:10 GMT
Dynamic Hydrology Maps from Satellite-LiDAR Fusion
Gonzalo Mateo-García
Long Talk (15m)
20:10 – 20:20 GMT
Efficient Reservoir Management through Deep Reinforcement Learning
Xinrun Wang
20:20 – 20:45 GMT
Q/A and Discussion for Water Session
Karthik Mukkavilli, Pierre Gentine, Grey Nearing
Moderated by S. Karthik Mukkavilli
20:45 – 21:15 GMT
Milind Tambe
Milind Tambe
Prof Milind Tambe Director, Center for Research on Computation & Society Gordon McKay Professor of Computer Science Harvard John A. Paulson School of Engineering and Applied Sciences Mail: Maxwell Dworkin 125, 33 Oxford Street, Cambridge, MA 02138 Director for AI for Social Good Google India Research Center teamcore.seas.harvard.edu/tambe
21:15 – 21:25 GMT
Q/A and Discussion
Karthik Mukkavilli, Mayur Mudigonda, Milind Tambe
21:55 – 22:20 GMT
Elizabeth Barnes
Elizabeth A. Barnes
Identifying Opportunities for Skillful Weather Prediction with Interpretable Neural Networks
22:20 – 22:35 GMT
Spatio-temporal segmentation and tracking of weather patterns with light-weight Neural Networks
Lukas Kapp-Schwoerer
Long Talk (15m)
22:35 – 22:50 GMT
Leveraging Lightning with Convolutional Recurrent AutoEncoder and ROCKET for Severe Weather Detection
Nadia Ahmed
Long Talk (15m)
22:50 – 22:55 GMT
Towards Data-Driven Physics-Informed Global Precipitation Forecasting from Satellite Imagery
Valentina Zantedeschi, Valentina Zantedeschi
22:55 – 23:25 GMT
Q/A and Discussion for Atmosphere Session
Tom Beucler, Mike Pritchard, Elizabeth A. Barnes
23:25 – 23:30 GMT
Simulations, Physics-guided, and ML Theory
Karthik Kashinath
By Karthik Kashinath
00:20 – 00:30 GMT
Generating Synthetic Multispectral Satellite Imagery from Sentinel-2
Hamed Alemohammad
00:30 – 00:40 GMT
Multiresolution Tensor Learning for Efficient and Interpretable Spatiotemporal Analysis
Raechel Walker
00:40 – 00:50 GMT
Climate-StyleGAN : Modeling Turbulent ClimateDynamics Using Style-GAN
Rishabh Gupta
00:50 – 00:55 GMT
Interpretable Deep Generative Spatio-Temporal Point Processes
Shixiang Zhu
00:55 – 01:00 GMT
Completing physics-based model by learning hidden dynamics through data assimilation
Arthur Filoche
01:00 – 01:20 GMT
Q/A and Discussion for ML Theory Session
Karthik Kashinath, Mayur Mudigonda, Stephan Mandt, Rose Yu
Moderated by Karthik Kashinath and Mayur Mudigonda
01:25 – 02:00 GMT
Q/A and Panel Discussion for People-Earth with Dan Kammen and Milind Tambe
Mayur Mudigonda, Daniel Kammen, Milind Tambe
02:05 – 02:20 GMT
Soft Attention Convolutional Neural Networks for Rare Event Detection in Sequences
Mandar Kulkarni
02:20 – 02:30 GMT
An End-to-End Earthquake Monitoring Method for Joint Earthquake Detection and Association using Deep Learning
Weiqiang Zhu
02:30 – 02:40 GMT
Single-Station Earthquake Location Using Deep Neural Networks
Charles Mousavi
02:40 – 02:45 GMT
Framework for automatic globally optimal well log correlation
Oleh Datskiv
02:45 – 03:00 GMT
Q/A and Discussion for Solid Earth
Kelly Kochanski
03:30 – 03:45 GMT
RainBench: Enabling Data-Driven Precipitation Forecasting on a Global Scale
Catherine Tong
Long Talk (15m)
03:45 – 04:00 GMT
WildfireDB: A Spatio-Temporal Dataset Combining Wildfire Occurrence with Relevant Covariates
Samriddhi Singla, Tina Diao
Long Talk (15m)
04:00 – 04:10 GMT
LandCoverNet: A global benchmark land cover classification training dataset
Hamed Alemohammad
04:10 – 04:20 GMT
Applying Machine Learning to Crowd-sourced Data from Earthquake Detective
Omkar Ranadive
04:20 – 04:25 GMT
An Active Learning Pipeline to Detect Hurricane Washover in Post-Storm Aerial Images
Evan Goldstein
04:25 – 04:30 GMT
Developing High Quality Training Samples for Deep Learning Based Local Climate Classification in Korea
Minho Kim
04:30 – 04:55 GMT
Q/A and Discussion for Benchmark Datasets
Karthik Kashinath
04:55 – 05:00 GMT
Workshop Closing Remarks
Karthik Mukkavilli
05:00 – 05:00 GMT
Predicting Streamflow By Using BiLSTM with Attention from heterogeneous spatiotemporal remote sensing products
Udit Bhatia - IITGN
05:00 – 05:00 GMT
Spectral Unmixing With Multinomial Mixture Kernel and Wasserstein Generative Adversarial Loss
Savas Ozkan
05:00 – 05:00 GMT
Unsupervised Regionalization of Particle-resolved Aerosol Mixing State Indices on the Global Scale
Zhonghua Zheng
05:00 – 05:00 GMT
Bias correction of global climate model using machine learning algorithms to determine meteorological variables in different tropical climates of Indonesia
Juan Nathaniel
05:00 – 05:00 GMT
A Comparison of Data-Driven Models for Predicting Stream Water Temperature
Helen Weierbach
05:00 – 05:00 GMT
MonarchNet: Differentiating Monarch Butterflies from Those with Similar Appearances
Thomas Chen
05:00 – 05:00 GMT
Integrating data assimilation with structurally equivariant spatial transformers: Physically consistent data-driven models for weather forecasting
Ashesh Chattopadhyay
05:00 – 05:00 GMT
Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery
Thomas Chen
05:00 – 05:00 GMT
Semantic Segmentation of Medium-Resolution Satellite Imagery using Conditional Generative Adversarial Networks
Hamed Alemohammad
05:00 – 05:00 GMT
Towards Automated Satellite Conjunction Management with Bayesian Deep Learning
Francesco Pinto
05:00 – 05:00 GMT
Optimising Placement of Pollution Sensors in Windy Environments
Sigrid Passano Hellan
05:00 – 05:00 GMT
Temporally Weighting Machine Learning Models for High-Impact Severe Hail Prediction
Amanda Burke
05:00 – 05:00 GMT
Inductive Predictions of Extreme Hydrologic Events in The Wabash River Watershed
Nicholas Majeske
05:00 – 05:00 GMT
Domain Adaptive Shake-shake Residual Network for Corn Disease Recognition
Yuan Fang