Session Outline
| Atmospheric and Hydrospheric Sciences (A) | ||||
|---|---|---|---|---|
| Session Sub-category | Technology &Techniques (TT) | |||
| Session ID | A-TT49 | |||
| Title | Machine Learning Techniques in Weather, Climate, Ocean, Hydrology and Disease Predictions | |||
| Short Title | Machine learning for climate | |||
| Main Convener | Name | Venkata Ratnam Jayanthi | ||
| Affiliation | Application Laboratory, JAMSTEC | |||
| Co-Convener 1 | Name | Patrick Martineau | ||
| Affiliation | Japan Agency for Marine-Earth Science and Technology | |||
| Co-Convener 2 | Name | Takeshi Doi | ||
| Affiliation | JAMSTEC | |||
| Co-Convener 3 | Name | Swadhin Behera | ||
| Affiliation | Application Laboratory, JAMSTEC, 3173-25 Showa-machi, Yokohama 236-0001 | |||
| Session Language | E | |||
| Scope |
Recent advances in machine learning, particularly deep learning, have enabled transformative applications across diverse fields, including weather, climate, oceanography, hydrology, and disease prediction. Increasingly, these techniques are being employed to forecast high-impact extreme events such as malaria outbreaks, heatwaves, cold spells, floods, droughts, tropical cyclones, typhoons, and large-scale climate phenomena like El Nino and the Indian Ocean Dipole. Beyond prediction, machine learning is proving valuable in improving parameterization schemes within numerical models, reducing systematic biases, and enhancing horizontal resolution in forecasts. This session aims to bring together researchers advancing machine learning methodologies to improve prediction and understanding of weather, climate, oceans, hydrology, and tropical diseases. Discussions will emphasize both scientific progress and practical applications that support societal resilience, well-being, and informed decision-making.
|
|||
| Session Format | Orals and Posters session | |||