The deadline to submit a session, town hall, or pre-conference workshop proposal for AGU25 has passed. Please search for and review proposed sessions below. Please note this site is frozen as of 4/29/25 and will not reflect any changes to proposals made after this date.


Conveners will be contacted by the AGU25 Program Committee with any requests for mergers or edits to proposals. Conveners will be notified of the acceptance of their proposal in mid-June.


Abstract submissions will also open in mid-June and the deadline for abstract submissions is 30 July, 2025.


Please visit the AGU25 website for more information or please contact AGU with any questions.

Session Proposal: Data-driven methods for quantifying atmospheric composition: Advances in computation and statistical learning (AGU25)

A048
Data-driven methods for quantifying atmospheric composition: Advances in computation and statistical learning

Session ID#: 248333

Session Description:
Statistical learning and advanced computational methods are increasingly being applied to problems in atmospheric chemistry. These methodological advances combined with increasing satellite and in-situ observations provide new opportunities to improve model predictions and our understanding of atmospheric processes. This session aims to provide a forum for research on data-driven techniques for understanding the sources and concentrations of air pollutants (NOx, SOx, CO, O3, PM2.5, etc.) and greenhouse gasses (CO2, CH4, N2O, etc.). We encourage submissions on both the application of data-driven methods for interpreting new atmospheric composition datasets and the development of new methods in machine learning, statistical inference, data assimilation, and cloud computing.
Index Terms:

0305 Aerosols and particles [ATMOSPHERIC COMPOSITION AND STRUCTURE]
0345 Pollution: urban and regional [ATMOSPHERIC COMPOSITION AND STRUCTURE]
0365 Troposphere: composition and chemistry [ATMOSPHERIC COMPOSITION AND STRUCTURE]
0368 Troposphere: constituent transport and chemistry [ATMOSPHERIC COMPOSITION AND STRUCTURE]
Primary Convener:  Zhen Qu, North Carolina State University Raleigh, Raleigh, NC, United States
Conveners:  Daniel J. Varon, Harvard University, School of Engineering and Applied Sciences, Cambridge, United States, Makoto Kelp, Stanford University, Stanford, United States and Sam Silva, University of Southern California, Earth Sciences, Civil and Environmental Engineering, Los Angeles, United States
 
Unraveling Chemical and Meteorological Effects on Ground-level Ozone Pollution Using Machine Learning (1847683)
Zhiyuan Li, Sun Yat-Sen University, Guangzhou, China
 
Toward a learnable Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI) based on the Multi-Head Self-Attention algorithm (1847896)
Zihan Xia1, Chun Zhao2, Zining Yang1, Qiuyan Du2 and Jiawang Feng2, (1)University of Science and Technology of China, Hefei, China, (2)University of Science and Technology of China, School of Earth and Space Sciences, Hefei, China
 
Smoke and Health Impacts of O3 from Wildfires in the United States (2008–2024) Using Generalized Additive Models (1855829)
Haebum Lee, University of Washington Bothell Campus, Bothell, United States and Dan A Jaffe, Univ of WA-Sci & Technology, School of STEM, Bothell, United States
 
Incorporating Geophysical a Priori Information into a Deep Learning Model for Nitrogen Dioxide Estimation (1880362)
Yu Yan, Washington University in St Louis, St. Louis, MO, United States, Siyuan Shen, Washington University in St. Louis, Department of Energy, Environmental & Chemical Engineering, St. Louis, United States and Randall Martin, Washington University in St. Louis, Department of Energy, Environmental, & Chemical Engineering, St. Louis, United States
 
Enhancing Estimation of Daily 1-km Resolution Fine Particulate Matter Concentrations for North America with Deep Learning from Geophysical A Priori Information (1880837)
Siyuan Shen, Washington University in St Louis, St. Louis, MO, United States, Aaron van Donkelaar, Washington University in St. Louis, Department of Energy, Environmental & Chemical Engineering, St. Louis, United States, Nathan Jacobs, Washington University in St. Louis, Department of Computer Science and Engineering, St Louis, MO, United States, Chi Li, Washington University in St. Louis, Energy, Environmental, and Chemical Engineering, St. Louis, United States and Randall Martin, Washington University in St. Louis, Department of Energy, Environmental, & Chemical Engineering, St. Louis, United States
 
Combining first principles with graph theory to automatically identify important pathways in atmospheric chemical mechanisms (1886831)
Obin Sturm, University of Southern California, Earth Sciences, Los Angeles, United States, Emma C. Ware, University of California Davis, Land, Air and Water Resources, Davis, CA, United States, Emy Li, University of Southern California, Los Angeles, CA, United States and Sam Silva, University of Southern California, Earth Sciences, Civil and Environmental Engineering, Los Angeles, United States
 
Data Driven Discovery of Atmospheric Chemical Reaction Mechanisms (1890553)
Daniel Getter1, Obin Sturm1 and Sam James Silva2, (1)University of Southern California, Earth Sciences, Los Angeles, United States, (2)University of Southern California, Earth Sciences & Civil and Environmental Engineering, Los Angeles, CA, United States
 
The EACH project: Artificial Intelligence Emulating Atmospheric Chemistry (1891630)
Klaus Klingmueller1, Timothy Butler2, Sergey Gromov1, Oriol Jorba3, Leon Kuhn1, Isidre Mas Magre3, Alessio Melli3, Camille Mouchel-Vallon3, Hervé Petetin3, Rolf Sander1, Martijn Schaap2, Markus Thürkow2, Johannes Lelieveld1,4 and Andrea Pozzer1,4, (1)Max Planck Institute for Chemistry, Atmospheric Chemistry, Mainz, Germany, (2)Freie Universität Berlin, Institute of Meteorology, Berlin, Germany, (3)Barcelona Supercomputing Center, Earth Sciences, Barcelona, Spain, (4)The Cyprus Institute, Climate and Atmosphere Research Center, Nicosia, Cyprus
 
A Non-Parametric Statistical Approach for Assessing Surface Air Quality Impacts of the 2025 LA Fires (1893617)
Brian Schlaff, University of Southern California, Earth Sciences, Los Angeles, CA, United States, Sam Silva, University of Southern California, Earth Sciences, Civil and Environmental Engineering, Los Angeles, United States, Yan Lu, University of Southern California, Civil and Environmental Engineering, Los Angeles, United States and Jiachen Zhang, University of Southern California, Department of Civil and Environmental Engineering, Los Angeles, United States
 
Spatiotemporal Estimation of Particulate Matter in the Pacific Northwest using Machine Learning with Emphasis on Wildfire Smoke (1898817)
Abu Ubayeda Ibnal Zarrah1, MD Jahidul Islam1 and Jun Meng2, (1)Washington State University, Civil and Environmental Engineering, Pullman, United States, (2)Washington State University, Civil and Environmental Engineering, Pullman, WA, United States
 
Towards Accelerated CO2 Inversion Modeling for Understanding Uncertainties through Multicore Processing and a Reusable Code Base (1899321)
Sequoia Andrade1, Ryan Giordano1, Naomi Asimow2 and Ronald C Cohen3, (1)University of California Berkeley, Department of Statistics, Berkeley, United States, (2)University of California Berkeley, Department of Earth and Planetary Science, Berkeley, United States, (3)University of California, Berkeley, Department of Chemistry, Berkeley, United States
 
Fine-tuning an Earth system foundation model to constrain the atmospheric oxidative capacity and methane lifetime (1902498)
Eliot Kim1, Eric Mei2 and Alexander J Turner2, (1)University of Washington Seattle Campus, Department of Atmospheric and Climate Science, Seattle, United States, (2)University of Washington, Department of Atmospheric and Climate Science, Seattle, United States
 
Tracking Global Shift in PM2.5 Chemical Composition over Decade under Climate Change and Stringent Emission Policies (1903884)
Zhige Wang1, Qingyang Xiao1, Yuexuanzi Wang1, Changpei He1, Guannan Geng2 and Qiang Zhang1, (1)Tsinghua University, Beijing, China, (2)School of Environment, Tsinghua University, Beijing, China
 
Atmospheric Chemical Modeling and Machine Learning using the EarthSciML framework (Invited) (1912222)
Christopher Tessum1, Hamidreza Emamipour1, Lin Guo1, Jialin Liu2, Manho Park3 and Xiaokai Yang1, (1)University of Illinois at Urbana Champaign, Urbana, United States, (2)University of Illinois at Urbana Champaign, Champaign, United States, (3)University of Illinois Urbana-Champaign, Civil and Environmental Engineering, Urbana, United States
 
Atmospheric chemistry surrogate modeling with sparse identification of mass action dynamics: Toward 3D online integration (1913925)
Xiaokai Yang, Lin Guo and Christopher Tessum, University of Illinois at Urbana Champaign, Urbana, United States
 
Guaranteeing Positivity and Mass Conservation in Machine Learning Models of Atmospheric Chemistry (1927655)
Beatriz Rodriguez1, Obin Sturm2, Daniel Getter2 and Sam Silva3, (1)University of Southern California, Los Angeles, CA, United States, (2)University of Southern California, Earth Sciences, Los Angeles, United States, (3)University of Southern California, Earth Sciences, Civil and Environmental Engineering, Los Angeles, United States
 
A Decline in Summertime Lower Tropospheric Ozone across Northern Hemisphere Midlatitudes during the 1980s–1990s: Insights from Trajectory-mapped Ozonesonde dataset for the Stratosphere and Troposphere (TOST) (1927927)
Zhou Zang1, Jane Liu1, David Walter Tarasick2 and Jingming Chen1, (1)University of Toronto, Department of Geography and Planning, Toronto, ON, Canada, (2)Environment and Climate Change Canada, Air Quality Research Division, Toronto, ON, Canada
 
Combining matched-filter and bayesian estimation algorithms to reduce bias in methane point-source retrievals (1929687)
Jinsol Kim, Daniel Cusworth and Riley Duren, Carbon Mapper, Pasadena, United States
 
Physics-Informed Neural Networks for Atmospheric Transport Modeling of Methane on Oil and Gas Sites (1931965)
Meng Jia, Andy Holmberg, Samy Wu Fung and Dorit Hammerling, Colorado School of Mines, Applied Mathematics and Statistics, Golden, United States
 
Mapping and Explaining the Global Variability of Power Plant Plume Detectability from Space (1936449)
Ruizhe Huang, Massachusetts Institute of Technology, Mechanical Engineering, Cambridge, MA, United States and Sherrie Wang, Massachusetts Institute of Technology, Institute for Data, Systems, and Society, Cambridge, United States; Massachusetts Institute of Technology, Mechanical Engineering, Cambridge, United States
 
Resolving Model Discrepancies in Ozone Formation Analysis Using Process-Informed Machine Learning (1937476)
Qihua HU, Seoul National University, Seoul, Korea, Republic of (South), Hwajin Kim, Seoul National University, Seoul, South Korea and Joost A de Gouw, University of Colorado Boulder, Department of Chemistry, Boulder, United States
 
GEOS-Chem-hyd: Enabling Source-Oriented Sensitivity Analysis with GEOS-Chem (1945899)
Samuel Akinjole, Drexel University, Philadelphia, PA, United States and Shannon Capps, Drexel University, Civil, Architectural, and Environmental Engineering, Philadelphia, PA, United States
 
AOD Retrieval using Physics-Informed Neural Network (PINN) and its Evaluation Against Traditional Physics based Model (1951856)
Rohit Kumar Singh, Indian Institute of Technology Kharagpur, Centre for Ocean, River, Atmosphere and Land Sciences (CORAL), Kharagpur, India and A.N.V. Satyanarayana, Indian Institute of Technology Kharagpur, Centre for Ocean, River, Atmosphere and Land Sciences, Kharagpur, India
 
Probing the Learned Embeddings of a Transformer-Based Air Quality Foundation Model (1957948)
Jason Hu1, Makoto Kelp1, Ivan Higuera-Mendieta2, Obin Sturm3 and Marshall Burke1, (1)Stanford University, Stanford, United States, (2)Stanford University, Stanford, CA, United States, (3)University of Southern California, Earth Sciences, Los Angeles, United States
 
Automated Detection of Methane Plumes in Tanager Hyperspectral Imagery Using SpecTF, a Transformer-based Deep Learning Algorithm (1958067)
Patrick R Sullivan1, Daniel Cusworth1, Jake Lee2 and Riley Duren1, (1)Carbon Mapper, Pasadena, United States, (2)NASA Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States
 
Assessing the Impact of Crop Residue Burning, Meteorological Factors, and Long-Range Transport on Urban PM2.5 in South Asia (1958917)
Amir Wagle, Saint Louis University, Department of Earth, Environmental and Geospatial Science, Saint Louis, United States and Benjamin de Foy, Saint Louis University, Earth and Atmospheric Sciences, Saint Louis, United States
 
Orders-of-magnitude speedup of advection in chemical transport modeling without spatial coarsening using mass-balanced learned solver (1968408)
Manho Park, University of Illinois Urbana-Champaign, Civil and Environmental Engineering, Urbana, United States, Christopher Rackauckas, Massachusetts Institute of Technology, Cambridge, United States and Christopher Tessum, University of Illinois at Urbana Champaign, Urbana, United States
 
Toward Satellite Informed Estimates of Wildfire-Ozone Chemistry (1969899)
Joseph Palmo, Massachusetts Institute of Technology, Department of Civil and Environmental Engineering, Cambridge, United States, Arlene M Fiore, Massachusetts Institute of Technology, Department of Earth, Atmospheric, and Planetary Sciences, Cambridge, United States, Qindan Zhu, Massachusetts Institute of Technology, Department of Earth, Atmospheric and Planetary Sciences, Cambridge, United States, Joshua Laughner, Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States, Colette L Heald, ETH Swiss Federal Institute of Technology Zurich, Department of Environmental Systems Science, Zurich, Switzerland and The FIREX-AQ Team
 
Constraining the Global Methane Sink through Joint Assimilation of CH4 and CO (1971606)
Mohammad Amin Mirrezaei1, Benjamin Gaubert2, Ivan Ortega3, Kathryn McKain4, Lori Bruhwiler4, Youmi Oh5, Alfonso Saiz-Lopez6, Rafael P. Fernandez7, Louisa K Emmons8 and Avelino F Arellano Jr1, (1)University of Arizona, Department of Hydrology and Atmospheric Sciences, Tucson, AZ, United States, (2)National Center for Atmospheric Research (NCAR), Atmospheric Chemistry Observations & Modeling Laboratory (ACOM), Boulder,CO, United States, (3)NSF National Center for Atmospheric Research (NSF NCAR), Atmospheric Chemistry Observations & Modeling Laboratory (ACOM), Boulder, CO, United States, (4)NOAA, Global Monitoring Laboratory, Boulder, United States, (5)NOAA Global Monitoring Laboratory, Boulder, United States, (6)Spanish National Research Council, Department of Atmospheric Chemistry and Climate, Institute of Physical Chemistry Rocasolano (CSIC), Madrid, Spain, (7)National Research Council (ICB-CONICET), Institute for Interdisciplinary Science, Mendoza, Argentina, (8)NSF National Center for Atmospheric Research (NSF NCAR), Atmospheric Chemistry Observations & Modeling Laboratory (ACOM), Boulder, United States
 
Hybrid Deep Learning Framework for Forecasting Ground-Level Ozone in Urban Areas (1981076)
Jithin Kanayankottupoyil1, Abdul Azeem Mohammed1 and Kuruvilla John2, (1)University of North Texas, Denton, United States, (2)University of North Texas, Department of Mechanical Engineering, Denton, United States
 
MALOPE: A Hybrid Machine Learning-Optimal Estimation Framework to Predict Column Concentrations and Retrieval Diagnostics of the TROPESS Atmospheric Composition Profiles (1987327)
Frank Werner1, Kevin W Bowman2, Seungwon Lee2, Joshua Laughner3, Vivienne Payne1 and James McDuffie4, (1)NASA Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States, (2)Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States, (3)NASA Jet Propulsion Laboratory, Pasadena, United States, (4)NASA Jet Propulsion Laboratory, Pasadena, CA, United States
 
Multi-model multi-constituent chemical (MOMO-Chem) data assimilation for city-to-global scale atmospheric composition and emission analysis (Invited) (1996885)
Kazuyuki Miyazaki1, Takashi Sekiya2, Kevin W Bowman1, Henk Eskes3, Pieter Rijsdijk4, Longtao Wu5, Jinhyeok Yu5 and Jinkyul Choi5, (1)Jet Propulsion Laboratory, California Institute of Technology, Pasadena, United States, (2)JAMSTEC Japan Agency for Marine-Earth Science and Technology, Research Institute for Global Change, Kanagawa, Japan, (3)Royal Netherlands Meteorological Institute, De Bilt, Netherlands, (4)SRON Netherlands Institute for Space Research, Leiden, Netherlands, (5)California Institute of Technology, Jet Propulsion Laboratory, Pasadena, United States
 
Characterizing Drivers of Organic Aerosol Using Data-Driven Hourly Models in Three California Cities (1998744)
Duncan Quevedo, University of California Berkeley, Civil and Environmental Engineering, Berkeley, United States, Roya Bahreini, University of California Riverside, Environmental Sciences, Riverside, United States, Don Collins, University of California Riverside, Chemical and Environmental Engineering, Riverside, United States and Cesunica Ivey, University of California Berkeley, Civil and Environmental Engineering Department, Berkeley, United States
See more of: Atmospheric Sciences
<< Previous Session Proposal | Next Session Proposal >>