Advances in Data Assimilation, Data Fusion, Machine Learning, Predictability, and Uncertainty Quantification in the Geosciences

Fletcher, Steven

NG001
Advances in Data Assimilation, Data Fusion, Machine Learning, Predictability, and Uncertainty Quantification in the Geosciences

Session ID#: 247483

Session Description:

Geophysical processes are typically sparsely observed and the relations between observed quantities and geophysical variables are often nonlinear, so that the statistics are non-Gaussian. Data assimilation (DA), data fusion, machine learning (ML), uncertainty quantification (UQ) and predictability are important areas of active research in geoscience. This interdisciplinary session focuses on new ideas and advanced techniques across geoscience that improve the robustness and the efficiency of computational methods for fusing models and data. Our session is broad in the application areas, and numerical methods of interest include variational and ensemble DA, Markov chain Monte Carlo, ensemble-based and adjoint sensitivity, observation impact and targeting, particle filters, deep/reinforcement learning, inversion techniques, deep/statistical/machine learning from scarce data, control variable transforms/pre-conditioning. We also welcome contributions to new computational infrastructure, e.g., the Joint Effort for Data assimilation Integration (JEDI).

Co-Sponsor(s):

A - Atmospheric Sciences
GC - Global Environmental Change
H - Hydrology
OS - Ocean Sciences

Index Terms:

0555 Neural networks, fuzzy logic, machine learning [COMPUTATIONAL GEOPHYSICS]
3315 Data assimilation [ATMOSPHERIC PROCESSES]
3336 Numerical approximations and analyses [ATMOSPHERIC PROCESSES]
4468 Probability distributions, heavy and fat-tailed [NONLINEAR GEOPHYSICS]

Primary Convener: Steven J Fletcher, Cooperative Institute for Research in the Atmosphere, Fort Collins, CO, United States

Conveners: Brian C Ancell, Texas Tech Univ-Geosciences, Lubbock, TX, United States, Matthias Morzfeld, Scripps Institution of Oceanography, University of California, San Diego, Institute of Geophysics and Planetary Physics, La Jolla, United States and Derek J Posselt, University of California, Joint Institute for Regional Earth System Science and Engineering, Los Angeles, United States

Integrating Supervised and Self-Supervised Deep Learning to Develop Gap-Free Daytime and Nighttime Land Surface Temperature at 100-M Resolution (1855271)

Taufiq Rashid, Auburn University, Auburn, United States and Di Tian, Auburn University, Department of Crop, Soil & Environmental Sciences, Auburn, United States

We Need Better Long-Term Hazard Models: Building an unbiased model for volcanism and faulting in Kyushu (Japan) (1859582)

Charles Connor, University of South Florida Tampa, Tampa, FL, United States, Laura Connor, University of South Florida, School of Geosciences, Tampa, FL, United States and Matthew Connor, Desperate Measures International, Lutz, United States

Controlled Latent Diffusion Models for 3D Rock Reconstruction (1860954)

Danilo de Freitas Naiff¹, Bernardo Schaeffer², Gustavo Pires³, Dragan Stojkovic⁴, Thomas Rapstine⁵ and Fabio Ramos², (1)Federal University of Rio de Janeiro, Department of Mechanical Engineering, Rio de Janeiro, Brazil, (2)Federal University of Rio de Janeiro, Institute of Mathematics, Rio de Janeiro, Brazil, (3)Federal University of Rio de Janeiro, Institute of Geosciences, Rio de Janeiro, Brazil, (4)ExxonMobil Technology and Engineering Company, Spring, Texas, United States, (5)ExxonMobil Upstream Company, Spring, Texas, United States

Explanation and Optimizing Multi-model Blending Algorithm Using Random Variables Theory (1867657)

Wang Yu¹, Dai Kan¹, Cao Yong¹, Shen Yue² and Zeng Xiaoqing¹, (1)National Meteorological Center, China Meteorological Administration, Beijing, China, (2)CMATC China Meteorological Administration Training Center, Beijing, China

Can the Generative AI Shark Eat the Entire Data Assimilation System? (1870413)

Matthias Morzfeld, Scripps Institution of Oceanography, La Jolla, CA, United States and Daniel Hodyss, US Naval Research Laboratory, District of Columbia, D.C., UNITED STATES

Seismic Image Denoising via Diffusion Model by Signal Fitting (1872438)

Yawen Zhang and Shengchang Chen Prof, Zhejiang University, School of Earth Sciences, Hangzhou, China

Localizing High-Dimensional Covariance Estimates with Hierarchical Rank Structure (Invited) (1873505)

Robin Armstrong, Cornell University, Center for Applied Mathematics, Ithaca, NY, United States, Anil Damle, Cornell University, Department of Computer Science, Ithaca, NY, United States and Samuel Otto, Cornell University, Sibley School of Mechanical and Aerospace Engineering, Ithaca, NY, United States

Implementing an update of aerosol initial states for Community Multiscale Air Quality (CMAQ) model simulation through kriging method (1877313)

Taehoo Choi¹, Chul H. Song², Jinhyeok Yu³, Soon-Young Park⁴ and Dogyeong Lee², (1)GIST Gwangju Institute of Science and Technology, Environment and Energy Engineering, Gwangju, Korea, Republic of (South), (2)GIST Gwangju Institute of Science and Technology, Environment and Energy Engineering, Gwangju, South Korea, (3)California Institute of Technology, Jet Propulsion Laboratory, Pasadena, United States, (4)Daegu National University of Education, Daegu, South Korea

Harnessing the Butterfly Effect: A Duality-Based Framework for the Efficient Control of Extreme Weather (1878401)

Takemasa Miyoshi, RIKEN, Wako, Japan

Model discovery on the fly using continuous data assimilation (1880247)

Jared Whitehead, Brigham Young University, Mathematics, Provo, UT, United States

Integrating ideas from nonlinear data assimilation into machine learning (1890632)

Peter Jan van Leeuwen, Colorado State University, Atmospheric Science, Fort Collins, United States

Ensemble Data Assimilation Methods for Applications with Mixed Probability Distributions (1892410)

Jeffrey L Anderson, National Center for Atmospheric Research, Boulder, CO, United States

Investigating Mechanisms of Meso-Convective Systems with Large Ensemble DA: Meteorological Informatics Approach (1906121)

Takuya T Kawabata, Meteorological Research Institute, Ibaraki, Japan and Le Duc: University of Tokyo, Akane Saya: Meteorological Research Institute, Pin Ying Wu: Kyoto University

Improving Extreme Rainfall Prediction over North-east India through Hybrid Ensemble Data Assimilation Technique (1910672)

Arundhati Kundu^1,2, Rekha B. Gogoi¹, Shyam S Kundu¹, Aniket Chakravorty¹, Abhay Srivastava¹, Rahul Mahanta^2,3, K. K. Sarma¹ and S. P. Aggarwal¹, (1)North Eastern Space Applications Centre, Department of Space, Shillong, India, (2)Cotton University, Department of Physics, Guwahati, India, (3)Cotton University, Centre for Cloud and Climate Change Research, Guwahati, India

Physically Consistent Global Atmospheric Data Assimilation with Machine Learning in Latent Space (1913488)

Hang Fan^1,2, Lei Bai², Ben Fei³, Yi Xiao⁴, Yongquan Qu⁵ and Pierre Gentine⁶, (1)Columbia University, New York, United States, (2)Shanghai Artificial Intelligence Laboratory, Shanghai, China, (3)The Chinese University of Hong Kong, Hong Kong, China, (4)Tsinghua University, Beijing, China, (5)Columbia University of New York, New York, United States, (6)Columbia University, Department of Earth and Environmental Engineering, New York, United States

Seismic Low-Frequency Extrapolation via Physics-Aware Conditional Diffusion Models (1926576)

Hamad Alswaidan¹, Ivan Deiana¹ and Biondo Leonardo Biondi², (1)Stanford University, Stanford, CA, United States, (2)Stanford University, Geophysics, Stanford, CA, United States

Nonlinear GenAI-Based Ensemble Data Assimilation Methods Applied to Convective-Scale Cloud Microphysical Parameter Estimation (1937239)

Derek J Posselt, NASA Jet Propulsion Laboratory, Pasadena, CA, United States and Hristo Chipilski, Florida State University, Department of Scientific Computing, Tallahassee, United States

Towards Developing Coupled Land-Atmosphere Data Assimilation for Improved S2S-Scale Predictability with the DOE E3SM Model (1937672)

Zhaoxia Pu¹, Shixuan Zhang², Brett M Raczka³, Dongze Xu⁴, Jeffrey L Anderson³ and Ruby Leung², (1)University of Utah, Department of Atmospheric Sciences, Salt Lake City, UT, United States, (2)Pacific Northwest National Laboratory, Richland, United States, (3)NCAR, Boulder, United States, (4)University of Utah, Department of Atmospheric Sciences, Salt Lake City, United States

Bayesian Hierarchical Network Model for Disaggregation of Spring Seasonal Streamflow (1939509)

Catalina Jerez, University of Colorado Boulder, Civil, Environmental, and Architectural Engineering, Boulder, United States; Cooperative Institute for Research in Environmental Sciences, Boulder, United States, Balaji Rajagopalan, Univ Colorado, Civil, Environmental, and Architectural Engineering and Cooperative Institute for Research in Environmental Sciences, Boulder, United States and Upmanu Lall, Arizona State University, Water Institute, Tempe, United States

Advancing Predictability of Extreme Weather through Data Assimilation and Machine Learning (Invited) (1950071)

Steven J Greybush, Pennsylvania State University Main Campus, Meteorology and Atmospheric Science, University Park, United States

Applying a lognormal based 1DVAR retrieval to improve moisture values over the Mediterranean Region in the NVAP-M data set. (1951571)

Steven J Fletcher, Cooperative Institute for Research in the Atmosphere, Fort Collins, CO, United States, John Michael Forsythe, Cooperative Institute for Research in the Atmosphere, Colorado State University, Fort Collins, United States, Thomas H Vonder Haar, Colorado State University, Atmospheric Science, Fort Collins, CO, United States and Shuyan Liu, University of MD- College Park, College Park, MD, United States

Adapting a Neuro-Physical Inverter to Field Data: A Physics-Coupled Machine Learning Framework for Subsurface Resistivity Estimation in a Blind Geothermal System (1958243)

Jae Deok Kim^1,2, Sai Ravela³ and Rob L Evans², (1)Massachusetts Institute of Technology, Earth, Atmospheric and Planetary Sciences, Cambridge, United States, (2)Woods Hole Oceanographic Institution, Woods Hole, MA, United States, (3)Massachusetts Institute of Technology, Department of Earth, Atmospheric and Planetary Sciences (EAPS), Cambridge, United States

Multiple Solutions to Geophysical Inverse Problems via Tracking Flights Across a Deeply Incised Model Landscape (1962706)

Mark Edward Everett, Texas A&M University College Station, Geology and Geophysics, College Station, TX, United States

AQcGAN - A Deep Conditional Generative Adversarial Network for Emulating and Extending Global Atmospheric Composition Forecasts (1968119)

Jennifer A. Sleeman¹, Viral Shah^2,3, Patricia Castellanos⁴, Christoph Keller⁵, Christopher James Ribaudo⁶, Adeline Hillier⁶, Caroline Tang¹, Collin Kofroth⁶, Alex Chen⁷, Pam Wales^2,8, Jules Kouatchou^8,9, Ravi Govindaraju^8,10, Katherine Breen^8,11 and K. Emma Knowland¹², (1)Johns Hopkins University Applied Physics Laboratory, Laurel, MD, United States, (2)Morgan State University, GESTAR II, Baltimore, United States, (3)NASA Goddard Space Flight Center, Global Modeling and Assimilation Office, Greenbelt, MD, United States, (4)NASA Goddard Space Flight Center, Global Modeling and Assimilation Office (Code 610.1), Greenbelt, United States, (5)Swiss Re, Washington, United States, (6)Johns Hopkins University Applied Physics Laboratory, Laurel, United States, (7)Johns Hopkins Applied Physics Laboratory, Laurel, United States, (8)NASA Goddard Space Flight Center, Global Modeling and Assimilation Office, Greenbelt, United States, (9)Science Systems and Applications, Inc., Lanham, United States, (10)Science Systems and Applications, Inc., Lanham, MD, United States, (11)Morgan State University, Baltimore, United States, (12)NASA Headquarters, Washington, DC, United States

Data Assimilation for CONTIGO: Collaboration for Observational and Numerical Thermosphere with Integrated Geospace Orbits (1971118)

Nat Mathews¹, Katherine Garcia-Sage², Jeff Klenzing², Peter W Schuck³ and Eftyhia Zesta², (1)University of Maryland College Park, Astronomy, College Park, United States, (2)NASA Goddard Space Flight Center, Greenbelt, MD, United States, (3)NASA GSFC, Silver Spring, United States

Adaptive Ensemble Smoother – Multiple Data Assimilation (ES-MDA) (1974037)

Kyle Ivey and Matthias Morzfeld, Scripps Institution of Oceanography, University of California, San Diego, Institute of Geophysics and Planetary Physics, La Jolla, United States

An Approach to Improving the 4DEnVar-Initialized Deterministic Prediction Skill in a Global NWP System (1985638)

Shujun Zhu¹, Bin Wang¹, Lin Zhang², Juanjuan Liu¹, Yongzhu Liu² and Jiandong Gong², (1)Institute of Atmospheric Physics, Chinese Academy of Sciences, Beijing, China, (2)CMA Earth System Modeling and Prediction Centre, China Meteorological Administration, Beijing, China

High-resolution wind fields for operational methane monitoring at oil and gas sites by integrating physics-based simulations, field observations, and scientific machine learning (1987932)

Arash Fathi, ExxonMobil Houston, Houston, TX, United States, Ehsan Kharazmi, Brown University, Providence, United States, Erin Menezes, MIT, Boston, United States, George Em Karniadakis, The Division of Applied Mathematics, Brown University, Providence, RI, United States and Anantha Sundaram, ExxonMobil Technology & Engineering Company, Annandale, United States

Machine learning-based temporal tracking of volcanic umbrella clouds properties from spaceborne sensors: The 2022 Hunga and 2024 Ruang Eruptions (1991688)

Ashok Gupta, Vanderbilt University, Departent of Earth and Environmental Sciences, Nashville, United States and Ralf Bennartz, Vanderbilt University, Department of Earth and Environmental Sciences, Nashville, TN, United States

Quantifying Information and Inferential Power in Incomplete Volcanic Eruption Records (1994785)

Chris Harper, University of Oregon, Eugene, OR, United States and Leif Karlstrom, University of Oregon, Department of Earth Sciences, Eugene, OR, United States

“A Skill-Optimized Reanalysis Ensemble with Cloud and Aerosol Integration for Assessing Spatiotemporal Trends in Precipitable Water over South and Southeast Asia” (1995346)

Jennifer Daluz, Air Force Institute of Technology, Department of Engineering Physics, Dayton, United States and Kyle Fitch, Air Force Institute of Technology, Department of Engineering Physics, Bellbrook, OH, United States

Learning Enhanced Ensemble Filters (2000239)

Bohan Chen¹, Eviatar Bach², Ricardo Baptista³, Edoardo Calvello⁴ and Andrew Stuart¹, (1)California Institute of Technology, Pasadena, CA, United States, (2)Laboratoire de Météorologie Dynamique ENS, Paris, France, (3)California Institute of Technology, Pasadena, United States, (4)California Institute of Technology, Computing and Mathematical Science Department, Pasadena, United States

Applying Machine Learning on Reflection Seismic and Well Logging Data to Identify Gas- and Brine-Saturated Reservoir Zones (2001708)

Mohamed Hamdallah^1,2 and William Harbert¹, (1)University of Pittsburgh, Pittsburgh, United States, (2)Aswan University, Aswan, Egypt

GeoAttnUNet: A 3D Attention U-Net for CO₂ Plume Detection in Carbon Storage Sites (2001771)

Javed Ali¹, William KUMAR Mohanty¹ and Sudeshna Sarkar², (1)Indian Institute of Technology Kharagpur, Department of Geology and Geophysics, Kharagpur, India, (2)Indian Institute of Technology Kharagpur, Department of Computer Science & Engineering, Kharagpur, India

See more of: Nonlinear Geophysics

<< Previous Session Proposal | Next Session Proposal >>

NG001 Advances in Data Assimilation, Data Fusion, Machine Learning, Predictability, and Uncertainty Quantification in the Geosciences

Session Description:

Co-Sponsor(s):

Index Terms:

NG001
Advances in Data Assimilation, Data Fusion, Machine Learning, Predictability, and Uncertainty Quantification in the Geosciences