Artificial Intelligence for Atmospheric Sciences: A Research Roadmap
Not on the map. Why?
Abstract (arXiv)
Atmospheric sciences are crucial for understanding environmental phenomena ranging from air quality to extreme weather events, and climate change. Recent breakthroughs in sensing, communication, computing, and Artificial Intelligence (AI) have significantly advanced atmospheric sciences, enabling the generation of vast amounts of data through long-term Earth observations and providing powerful tools for analyzing atmospheric phenomena and predicting natural disasters. This paper contributes a critical interdisciplinary overview that bridges the fields of atmospheric science and computer science, highlighting the transformative potential of AI in atmospheric research. We identify key challenges associated with integrating AI into atmospheric research, including issues related to big data and infrastructure, and provide a detailed research roadmap that addresses both current and emerging challenges.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 29 of its 217 references that are in the map. First posted on arXiv 19 Jun 2025.
Builds on
29 of 217 references.
References · 29
- 2022Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's nextcited by 608
- 2023ClimaX: A foundation model for weather and climatecited by 337
- 2023SpectralGPT: Spectral Remote Sensing Foundation Modelcited by 252
- 2023Neural General Circulation Models for Weather and Climatecited by 239
- 2016Theory-guided Data Science: A New Paradigm for Scientific Discovery from Datacited by 171
- 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
- 2018Deep learning to represent sub-grid processes in climate modelscited by 156
- 2022Decentralized Federated Learning: Fundamentals, State of the Art, Frameworks, Trends, and Challengescited by 138
- 2022Self-supervised Learning in Remote Sensing: A Reviewcited by 137
- 2023Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulationcited by 61
- 2020Deep Learning for Post-Processing Ensemble Weather Forecastscited by 52
- 2023A New Learning Paradigm for Foundation Model-based Remote Sensing Change Detectioncited by 47
17 more
- 2021Will Artificial Intelligence supersede Earth System and Climate Models?cited by 37
- 2023Advancements in Generative AI: A Comprehensive Review of GANs, GPT, Autoencoders, Diffusion Model, and Transformerscited by 36
- 2023GeoGalactica: A Scientific Large Language Model in Geosciencecited by 33
- 2024Recent Advances in Generative AI and Large Language Models: Current Status, Challenges, and Perspectivescited by 30
- 2021Towards a Collective Agenda on AI for Earth Science Data Analysiscited by 27
- 2023Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Sciencecited by 27
- 2020Machine Learning Information Fusion in Earth Observation: A Comprehensive Review of Methods, Applications and Data Sourcescited by 19
- 2020A generative adversarial network approach to (ensemble) weather predictioncited by 18
- 2023There Are No Data Like More Data- Datasets for Deep Learning in Earth Observationcited by 16
- 2024Deep Learning for Satellite Image Time Series Analysis: A Reviewcited by 13
- 2019CubeSat Communications: Recent Advances and Future Challengescited by 10
- 2022AtmoDist: Self-supervised Representation Learning for Atmospheric Dynamicscited by 8
- 2024Modern Computing: Vision and Challengescited by 6
- 2022QFaaS: A Serverless Function-as-a-Service Framework for Quantum Computingcited by 5
- 2019Geospatial Big Data Handling with High Performance Computing: Current Approaches and Future Directionscited by 1
- 2023Earth Virtualization Engines -- A Technical Perspectivecited by 1
- 2024A2CI: A Cloud-based, Service-oriented Geospatial Cyberinfrastructure to Support Atmospheric Researchcited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 1.
2 papers.