LEAP @ AGU22 FALL MEETING
American Geophysical Union (AGU) 2022 Fall Meeting: Key Research From LEAP
Below is a guide to notable presentations and other events from LEAP colleagues at the Dec. 12-16, 2022, meeting of the American Geophysical Union, the world’s largest gathering of earth and space scientists. The meeting will take place in Chicago, IL, and online across the globe.
Presentations are listed in chronological order.
This list will be updated as additional information is gathered.
Times listed are U.S. Central.
(Note: If you call up an abstract, the time displayed may default to your own local time if you attend remotely.)
9:00 – 12:30 || McCormick Place – Poster Hall, Hall A || C12C-0583
- DAVID PORTER (LDEO)
Connecting the Subglacial Environment of the Amundsen Sea Embayment Glaciers to Ice Sheet Models Using a Combination of Aerogeophysical Data and Statistical Methods
9:00 – 12:30 || McCormick Place – Poster Hall, Hall A || A12N-1291
- KARA LAMB (Columbia)
Unsupervised Learning of Microphysical Process Rates Using Generative Machine Learning Models - With LEAP colleagues: Hugh Morrison, Marcus van Lier-Walqui
14:45 – 18:15 || McCormick Place – Poster Hall, Hall A || OS15B-0788
- ANDREW FAGERHEIM (Columbia)
Analysis of the Vertical Structure of Lateral Eddy Stirring Using Argo Profiles - With LEAP colleagues: Ryan Abernathey, Dhruv Balwada, Julius Busecke
15:55 – 16:05 || McCormick Place – S405b || B15B-08
- YU HUANG (Columbia)
Estimating the Land-Atmosphere Coupling Strength at Daily Scale in the Radiation and Moisture Pathways Using PCMCI and XGBoosting - With LEAP colleague: Pierre Gentine
17:00 – 17:10 || McCormick Place – S105bc || NG16A-02
- MOHAMED AZIZ BHOURI (Columbia)
Bayesian Machine Learning Method for Simultaneous Parameter Inference and Model Closure of Dynamical Systems: Application to Two-Scale Lorenz ’96 System - With LEAP colleague: Pierre Gentine
17:09 – 17:20 || McCormick Place – S503ab || GC16C-03
- MARIA MOLINA (NCAR)
Defying Chaos Theory: Using Machine Learning to Extend Earth System Prediction (Invited) - With LEAP colleague: Katie Dagon
17:10 – 17:20 || McCormick Place – S105bc || NG16A-03
- FERNANDO IGLESIAS-SUAREZ (German Aerospace Center DLR)
Machine Learning-Based Causally Informed Atmospheric Parametrizations for Climate Models - With LEAP colleagues: Pierre Gentine, Mike Pritchard
17:12 – 17:22 || McCormick Place – E271ab || A16D-03
- RYAN ANSELM (Columbia)
Machine Learning Optimal Prognostic Moments For Single-category Cloud Microphysics Parameterizations - With LEAP colleagues: Kara Lamb, Hugh Morrison, Marcus van Lier-Walqui
17:15 – 17:25 || McCormick Place – S403b || B16D-04
- JIANGONG LIU (Columbia)
Learning to Learn Ecological Processes in Tropical Forests - With LEAP colleague: Pierre Gentine
17:20 – 17:30 || McCormick Place – S105bc || NG16A-04
- MIKE PRITCHARD (NVIDIA)
NVIDIA’s Earth-2: The “Hop, Skip, Tune, Leap” Strategy For Accelerated Km-scale Hybrid ML-Physics Climate Prediction
17:53 – 18:04 || McCormick Place – S503ab || GC16C-07
- GUNNAR BEHRENS (German Aerospace Center DLR/Columbia)
Non-Linear Dimensionality Reduction with a Variational Encoder Decoder to Understand Convective Processes in Climate Models - With LEAP colleagues: Pierre Gentine, Mike Pritchard
18:04 – 18:15 || McCormick Place – E450a || A16A-08
- KYLEEN LIAO (Saratoga High School)
Disentangling the Effects of Meteorological Variability and Wildfires on PM2.5 Concentrations in California using Machine Learning - With LEAP colleagues: Kara Lamb, Pierre Gentine
7:00 – 8:00 || McCormick Place – Regency Ballroom AB || Networking Event
- PIERRE GENTINE (Columbia)
James B. Macelwane Early Career and Student Breakfast - LEAP early career scientists are welcome to breakfast and conversation with Pierre and others about mentorship.
8:00 – 9:00 || Online Only || NG21A-01
- JERRY LIN (UC Irvine)
Confronting the Offline vs. Online Skill Dilemma via Prognostic Testing of Neural Network Convection Parameterizations at a Computationally Ambitious Scale - With LEAP colleagues: Mike Pritchard, Sungduk Yu
9:32 – 9:45 || McCormick Place – AGU Central Theater – Hall A || Invited Event
- PIERRE GENTINE (Columbia)
Our Changing Environment: From Individual Efforts to a Community-Driven Effort
9:00 – 12:30 || McCormick Place – Poster Hall, Hall A || A32J-1540
- SAVANNAH FERRETTI (UC Irvine)
Understanding the Monthly Variation in the Upstream Enhancement of Indian Summer Monsoon Precipitation Near the Western Ghats - With LEAP colleague: Mike Pritchard
14:45 – 18:15 || McCormick Place – Poster Hall, Hall A || A35K-1589
- MARCO GIOVANNI GIOMETTO (Columbia)
Reconstruction of 3D Turbulent Flow Fields From 2D Images Using Deep Learning - With LEAP colleagues: Pierre Gentine, Gurpreet Singh Hora, Carl Vondrick
16:05 – 16:15 || McCormick Place – S105d || OS35A-08
- GALEN McKINLEY (LDEO)
Physical Knowledge and Interpretability For Ocean pCO2: The pCO2-Residual Method
17:05 – 17:15 || McCormick Place – E270 || H36C-03
- PIERRE GENTINE (Columbia)
Let Me Autodiff This Thing: Similarities and Synergies Between Physical Models and Neural Networks (Invited)
17:05 – 17:15 || McCormick Place – S104a || NG36A-03
- SARA SHAMEKH (Columbia)
Implicit Learning of Convective Organization Explains Precipitation Stochasticity - With LEAP colleagues: Pierre Gentine, Kara Lamb
17:45 – 17:55 || McCormick Place – E258 || A36B-07
- KATIE DAGON (NCAR)
Machine Learning-Based Detection of Weather Fronts and Associated Extreme Precipitation in Historical and Future Climates - With LEAP colleague: Maria Molina
9:50 – 10:00 || McCormick Place – S502ab || B42A-06
- WEIWEI ZHAN (Columbia)
A Machine Learning-based Method to Partition CO2 Fluxes and Understand the Relationship Between Gross Primary Productivity and Solar-induced Chlorophyll Fluorescence - With LEAP colleague: Pierre Gentine
11:25 – 11:35 || McCormick Place – E353ab || A43C-03
- SARA SHAMEKH (Columbia)
Low-dimensional Representation of Turbulence Across Planetary Boundary Layer Regimes - With LEAP colleague: Pierre Gentine
14:45 – 18:15 || McCormick Place – Poster Hall, Hall A || NH45F-0497
- JATAN BUCH (Columbia/LDEO)
A Stochastic Machine Learning Model of Wildfire Activity in the Western United States - With LEAP colleague: Pierre Gentine
15:25 – 15:35 || McCormick Place – E258 || A45H-05
- MARIA MOLINA (NCAR)
Classification and Detection of Organized Convection using Deep Learning (Invited) - With LEAP colleagues: Katie Dagon, David John Gagne
9:00 – 12:30 || McCormick Place – Poster Hall, Hall A || B52F-0883
- JISU HAN (Columbia)
Optimality Based Physics Informed Neural Network For Stomatal Conductance Modeling Under Heat and Soil Water Stress - With LEAP colleague: Pierre Gentine
9:30 – 9:40 || McCormick Place – S501bcd || B52A-04
- JIANING FANG (Columbia)
EMC2: A Hybrid-Machine Learning Carbon Model for the Discovery of Unknown Functional Relationships in Terrestrial Carbon Cycles - With LEAP colleague: Pierre Gentine
15:04 – 15:12 || McCormick Place – S505ab || C55A-02
- RAF ANTWERPEN (Columbia)
Bidirectional Long Short-Term Memory Network to Attribute Greenland Ice Albedo Variability to Specific Drivers - With LEAP colleague: Pierre Gentine
15:59 – 16:09 || McCormick Place – E350 || A55D-08
- FRANCESCO IMMORIANO (Columbia)
Generating Accurate Climate Model Realizations - With LEAP colleague: Pierre Gentine
16:48 – 17:00 || McCormick Place – E253ab || A56G-01
- AMANDA FAY (LDEO)
Immediate and Long-lasting Impacts of the Mt. Pinatubo Eruption on Ocean Oxygen and Carbon Inventories Using the CESM-LENS (Invited) - With LEAP colleague: Galen McKinley
