A091
Spatiotemporal AI methods for analyzing aerosol, clouds and air pollution
Session ID#: 247346
Session Description:
Atmospheric factors such as aerosols, clouds, and air pollution play critical roles in shaping global weather and climate patterns. Accurate and comprehensive analysis of these components is essential for numerical weather prediction and daily life applications. With advancements in computational resources, Artificial Intelligence (AI) and sophisticated spatiotemporal methods are transforming the study of atmospheric processes.This session invites contributions that explore innovative AI techniques, machine learning models, spatiotemporal analysis, and data-driven approaches for examining satellite and ground-based observations, numerical simulations, and in situ measurements. We encourage discussions on novel methodologies aimed at improving air quality forecasting, understanding aerosol-cloud interactions, and assessing climate impacts. Studies employing deep learning, data fusion, and spatiotemporal modeling to advance our knowledge of atmospheric dynamics are particularly welcome. Join us to explore cutting-edge advancements and interdisciplinary applications in environmental research.
Index Terms:
0305 Aerosols and particles [ATMOSPHERIC COMPOSITION AND STRUCTURE]
0315 Biosphere/atmosphere interactions [ATMOSPHERIC COMPOSITION AND STRUCTURE]
0321 Cloud/radiation interaction [ATMOSPHERIC COMPOSITION AND STRUCTURE]
0345 Pollution: urban and regional [ATMOSPHERIC COMPOSITION AND STRUCTURE]
Primary Convener: Qian Liu, University of Missouri Columbia, Columbia, United States
Conveners: Manzhu Yu, Penn State University, State College, United States and Jeffrey D Wood, University of Missouri, School of Natural Resources, Columbia, United States
Calibrating Low-Cost Air Quality Sensors for High Accuracy PM2.5 Measurements Using Machine and Deep Learning, Enabling Monitoring of Air Quality for a Wider Range of Geographic Regions (1859636)
Sidh Jaddu, Thomas Jefferson High School for Science and Technology, Fairfax, VA, UNITED STATES, Seren Smith, George Mason University, Fairfax, United States and Chaowei Phil Yang, George Mason Univ., Fairfax, United States
Evaluation of Spatiotemporal Heterogeneity in PM2.5 Forecasting Using ST-Transformer: Western US as a Case Study (1883911)
Anusha Srirenganathan Malarvizhi, George Mason University Fairfax, Geography and Geoinfomation Science, Fairfax, VA, United States, Kaylee Smith, University of Michigan, Ann Arbor, United States and Samir Ahmed, George Mason University Fairfax, Geography and Geoinfomation Science, Fairfax, United States
Spatial and Temporal Patterns of Valley and Mountain Fog in the Czech Republic and their Potential Links to Aerosol Influence (2006–2021) (1891042)
Suruchi Suruchi1 and Iva Hůnová1,2, (1)Charles University, Prague, Czech Republic, Institute for Environmental Studies, Faculty of Science, Prague-6, Czech Republic, (2)Czech Hydrometeorological Institute, Prague, Czech Republic, Prague-4, Czech Republic
From Static to Dynamic: How Regular Retraining Improves Machine Learning Air Pollution Forecasts, illustrated with the NASA GEOS-CF use case. (1898223)
Noussair Lazrak1, Umair Ayub1, Kevin Cromar2, Carl Malings3, Christoph Keller4 and K. Emma Knowland5, (1)New York University, Marron Institute of Urban Management, New York, United States, (2)New York University, NYU Grossman School of Medicine, New York, United States, (3)NASA Global Modeling and Assimilation Office, Goddard Space Flight Center, Greenbelt, United States, (4)Swiss Re, Washington, United States, (5)Universities Space Research Association Columbia, Columbia, United States
Enhancing Low-Cost Sensor Reliability for Air Quality Monitoring using Deep Learning and Monte Carlo-based Uncertainty Quantification (1903651)
Sidh Jaddu, Thomas Jefferson High School for Science and Technology, Fairfax, VA, UNITED STATES, Kaylee Smith, University of Michigan, Ann Arbor, United States and Chaowei Phil Yang, George Mason Univ., Fairfax, United States
Satellite PM2.5 Retrieval Using Machine Learning Models – Maryland Case Studies (1928186)
Xiaowen Li1, Daniel Okon2, Fikewa Akindolire2, Gracelyn Ruth Arunachalam3, Elton Mawire4, Maximillian Unegbu5, Elainia Ross-Jones6, Temidayo Fapohunda2, Yingxi Rona Shi5,7 and Robert C Levy8, (1)Morgan State University, Climate Science, Baltimore, MD, United States, (2)Morgan State University, Baltimore, United States, (3)University of Maryland College Park, College Park, United States, (4)Alabama A & M University, Normal, United States, (5)University of Maryland Baltimore County, Baltimore, United States, (6)Baltimore City Neighbors High School, Baltimore, United States, (7)NASA Goddard Space Flight Center, Greenbelt, United States, (8)NASA/Goddard Space Flight Ctr, Greenbelt, United States
Machine Learning Approaches to Analyze and Predict Particulate Matter Concentrations in Delhi–NCR (1940185)
Dr Sarvan Kumar, Department of Earth and Planetary Sciences, VBS Purvanchal University, Jaunpur, Uttar Pradesh-222003, India, Jaunpur, India and Nabin Sharma, Department of Physics, SRM Institute of Science and Technology, Delhi-NCR Campus, Modinagar, Ghaziabad-201204, India, Ghaziabad, India
Evaluating PM2.5 Estimation Errors over South Korea: A Comparison between MPAS-CMAQ and WRF-CMAQ (1940997)
Seong-il Lee, Myongji University, Yongin-si, South Korea, JUN-TAE KIM, Myongji University, Yongin-si, Gyeonggi-do, SOUTH KOREA and Hyo-Jong Song, Myongji University, Dept. of Environmental Engineering and Energy, Seoul, South Korea
Hybrid Transfer Learning for PM2.5 Estimation in Regions with Sparse Ground-Based Data: A Scalable Framework (1945092)
Muhammad Jawad Hussain1, Myeongsu Seong2, Behjat Shahid3 and Heming Bai1, (1)Nantong University, Research Center for Intelligent Information Technology, Nantong, China, (2)Xi’an Jiaotong-Liverpool University, Department of Mechatronics and Robotics, Suzhou, China, (3)University of Central Punjab, Faculty of Media and Communication Studies, Lahore, Pakistan
Improving Real-Time Air Quality Forecasting through Bias-Correction and Machine Learning over Southeastern U.S. (1951755)
Yiyue Yang, Northeastern University, Boston, MA, United States, Khanh Do, Northeastern University, Boston, United States and Yang Zhang, Northeastern University, Department of Civil and Environmental Engineering, Boston, United States
Enhancing Spatiotemporal Continuity of TEMPO Tropospheric Nitrogen Dioxide via Gaussian Process Regression Gap-filling (1988803)
Hazem Mahmoud, NASA Langley Research Center ADNET, Atmospheric Science Data Center, Hampton, United States, Sarah Scott, NASA AMA, Hampton, United States, Alexander Radkevich, ADNET Systems, Bethesda, MD, United States, Elizabeth Joyner, NASA Langley Research Center, Hampton, VA, United States and Qian Tan, Bay Area Environmental Research Institute, San Jose, CA, United States
DustCast: An Ensemble Machine Learning Model for Monthly Atmospheric Dust Aerosol Forecasting Across the Arabian Peninsula. (1993592)
Christopher Ramos, Organization Not Listed, Washington, DC, United States, Brandi Gaertner, Pennsylvania State University Main Campus, Geography, University Park, PA, United States and Steven J Greybush, The University of Maryland, University Park, United States
