AS5.5 | Machine Learning and Other Novel Techniques in Atmospheric and Environmental Science: Application and Development
EDI
Machine Learning and Other Novel Techniques in Atmospheric and Environmental Science: Application and Development
Convener: Yafang Cheng | Co-conveners: Hao KongECSECS, Jintai Lin, Ruijing NiECSECS, Chaoqun MaECSECS
Orals
| Thu, 18 Apr, 14:00–18:00 (CEST)
 
Room E2
Posters on site
| Attendance Fri, 19 Apr, 10:45–12:30 (CEST) | Display Fri, 19 Apr, 08:30–12:30
 
Hall X5
Posters virtual
| Attendance Fri, 19 Apr, 14:00–15:45 (CEST) | Display Fri, 19 Apr, 08:30–18:00
 
vHall X5
Orals |
Thu, 14:00
Posters on site |
Fri, 10:45
Posters virtual
Fri, 14:00
The wave of the Information Technology revolution is propelling us into a new era of research on atmospheric environmental science. New techniques including Machine Learning (ML) are enabling a deeper understanding of the complex atmospheric and environmental systems, as well as the interactions between weather/climate, air quality, public health, and social-economics. At the same time, Cloud Computing, GPU Computing, and Digital Twin have greatly facilitated much faster and more accurate earth system modeling, especially the weather/climate and air quality modeling and forecasting. These cutting-edge techniques are therefore playing an increasingly important role in atmospheric environmental research and governance.

This session is open for submissions addressing the latest progress in new techniques applied to research on all aspects of atmospheric environmental sciences (e.g., weather/climate, air quality and their interactions with public health and social economic. The submissions include, but are not limited to,
- The application of ML and other techniques for
• data assimilation and historical data reconstruction
• faster and more accurate weather/climate modeling and forecasting, especially for extreme weather and climate change
• faster and more accurate air quality modeling and forecasting
• air pollution tracing and source attribution
• advanced understanding of the mechanisms of atmospheric chemistry and physics
• greater insight into the impacts of atmospheric environment on weather, climate, and health
- The adaption/development of ML and other techniques by proposing
• explainable AI (XAI)
• hybrid methods (e.g., hybrid ML, physics-integrated ML)
• transfer learning
• new algorithms
• advanced model frameworks

Session assets

Session materials Session summary

Orals: Thu, 18 Apr | Room E2

Chairpersons: Hang Su, Hao Kong, Ruijing Ni
14:00–14:05
5-minute convener introduction
AI for Weather
EGU24-7244
|
ECS
|
Highlight
|
On-site presentation
Typhoon precipitation forecasting based on Satellite Imagery Sequencing and Generative Adversarial Networks
Nan Yang and Xiaofeng Li
EGU24-1754
|
On-site presentation
Multitask Learning for Tornado Identification Using Doppler Radar Data
Jinyang Xie et al.
EGU24-20726
|
ECS
|
On-site presentation
Machine Learning Based Closure Optimization for the Unified Convection Parametrization 
Janaina Nascimento et al.
EGU24-13882
|
ECS
|
On-site presentation
Physics-Informed Diffusion Model and Sampling for Global Weather Forecasting
Sanghoon Choi and David Topping
EGU24-11381
|
solicited
|
Highlight
|
Virtual presentation
GraphCast: Learning skillful medium-range global weather forecasting
Alvaro Sanchez-Gonzalez and the GraphCast team from Google DeepMind
EGU24-2857
|
ECS
|
Highlight
|
On-site presentation
Coupling the Data-driven Weather Forecasting Model with 4D Variational Assimilation
Yi Xiao et al.
EGU24-12205
|
On-site presentation
Uncertainty Quantification for Deep Learning
Peter Jan van Leeuwen et al.
Coffee break
Chairpersons: Yafang Cheng, Hao Kong, Chaoqun Ma
16:15–16:20
5-minute convener introduction
AI for Climate
EGU24-2478
|
ECS
|
Highlight
|
On-site presentation
Multi-scale hybrid modeling of terrestrial evaporation
Akash Koppa et al.
EGU24-15874
|
solicited
|
Highlight
|
On-site presentation
Deep learning and Process Understanding for Data-Driven Earth System Science
Markus Reichstein et al.
AI for Environment
EGU24-13925
|
Highlight
|
Virtual presentation
Zero-shot learning of aerosol optical properties with graph neural networks
Kara Lamb and Pierre Gentine
EGU24-9208
|
On-site presentation
Combined machine learning model of aeolian dust and surface soil moisture
Klaus Klingmüller et al.

Posters on site: Fri, 19 Apr, 10:45–12:30 | Hall X5

Display time: Fri, 19 Apr 08:30–Fri, 19 Apr 12:30
Chairpersons: Hao Kong, Ruijing Ni, Chaoqun Ma
AI for Weather
EGU24-2320
|
Highlight
|
On-site presentation
AI/ML Augmented Hyper Local Weather Forecast
Hung-Lung Allen Huang
EGU24-20404
|
ECS
|
Highlight
|
On-site presentation
Automatic cloud detection in GHGSat satellite imagery
Jake Wilson et al.
EGU24-5678
|
On-site presentation
Preliminary Study on Minutely Sample Labeling Algorithm with Prior Knowledge Model 
(withdrawn)
Liang Leng et al.
AI for Climate
EGU24-15997
|
ECS
|
On-site presentation
Climate change in the alps: Comparing different climate models based on estimates of monthly data.
(withdrawn)
Kristofer Hasel et al.
EGU24-17782
|
ECS
|
On-site presentation
Variability among Machine Learning Explanations for Precipitation Forecasting in Köppen Climate Zones
Ali Ulvi Galip Senocak et al.
EGU24-13819
|
ECS
|
On-site presentation
Using XGBoost & SHAP feature importance to understand the drivers of the Southern Ocean cloud-radiation bias
(withdrawn)
Sonya Fiddes et al.
EGU24-1868
|
ECS
|
Highlight
|
On-site presentation
Utilizing convolutional neural networks for ground-based cloud observations
Markus Rosenberger et al.
EGU24-18552
|
ECS
|
On-site presentation
A novel automated framework to design optimal networks of atmospheric greenhouse gas stations
David Matajira-Rueda et al.
AI for Environment
EGU24-4501
|
ECS
|
On-site presentation
Unified Model of Forecasting Ozone
Zhenze Liu et al.
EGU24-21203
|
ECS
|
On-site presentation
Application of Three Machine Learning Models for a Severe Ozone Episode in Mexico City 
Mateen Ahmad et al.
EGU24-2504
|
On-site presentation
Estimation of daily NO2 with explainable machine learning model in China, 2007-2020
Yanchuan Shao et al.
EGU24-15297
|
ECS
|
On-site presentation
Identification and description of fire emission plumes from Sentinel-5p observations   
Daniel Kinalczyk et al.
EGU24-5695
|
On-site presentation
Innovative surface reflectance retrieval from UV satellites
Pascal Hedelt et al.
Special Highlight
EGU24-15026
|
Highlight
|
On-site presentation
Rapid verification visualization of atmospheric modeling relies on high-performance computing
(withdrawn)
Zhen Cheng

Posters virtual: Fri, 19 Apr, 14:00–15:45 | vHall X5

Display time: Fri, 19 Apr 08:30–Fri, 19 Apr 18:00
Chairpersons: Hao Kong, Ruijing Ni, Chaoqun Ma
AS5.5 AI for AS & ES
EGU24-2763
|
ECS
|
Virtual presentation
Study on the 3DVar emission inversion method combined with machine learning in CMAQ
Congwu Huang et al.
EGU24-5491
|
ECS
|
Virtual presentation
  PM2.5 concentration forecast using Hybrid models over Urban cities in India
Vyshnavi k k et al.
EGU24-150
|
ECS
|
Virtual presentation
Machine Learning Forecasting of Extreme Winds: A Study on the Mediterranean West Coast in the Valencian Community
Gustavo Hazel Guerrero-Navarro et al.