T3 S2 | Improving Hydrological Understanding Through Data-Driven Approaches
Session Details
| Moderator: |
Alexandra Nauditt & Lars Ribbe |
| Date/Time: | 10.10.2024, 11:30 – 13:00 |
| Location: | Margarete-Bieber-Saal |
Description
This session explores cutting-edge, data-driven approaches that deepen the understanding of hydrological systems and processes. Using advanced techniques such as machine learning, remote sensing, and geostatistical methods, the session explores applications ranging from glacier mass balance estimations to rainfall evaluation and runoff prediction in various regions of the world. By utilizing free open-source data, satellite imagery, and algorithms, these studies offer key insights into water resource management, climate resilience, and sustainable development. Attendees gain a comprehensive view of how technological innovation is transforming the way we monitor, model, and enhance water availability and management in diverse ecosystems.
The studies presented in this session (1) examine the use of satellite imagery and open-source data to estimate glacier mass balance, (2) use remote sensing and machine learning to estimate ecosystem productivity, (3) assess the accuracy of satellite rainfall estimates and their applications for improving hydrological modeling and water resource management, (4) apply machine learning and neural networks to analyze runoff factors in flood-prone regions, and (5) merging precipitation datasets through machine learning and geostatistical approaches to create a more accurate representation of rainfall patterns.
Speakers
| Time | ID | Name | Title |
| 11:30 - 11:35 | --- | Moderator | Welcome & Introduction |
| 11:35 - 11:50 | 82 | Ailin Sol Ortone Lois | Mass balance estimations of Patagonian glaciers using free open sources |
| 11:50 - 12:05 | 342 | Cindy Urgilés | Gross Primary Productivity estimation through remote sensing and machine learning techniques in the high Andean Region of Ecuador |
| 12:05 - 12:20 | 353 | Cristian Diaz Moscote | Evaluation of Satellite Rainfall Estimates in the Magdalena Grande Region, Northern Colombia |
| 12:20 - 12:35 | 376 | Asib Ahmed | Synergistic Approach with Machine Learning and Recurrent Neural Network to Identify Potential Factors of Runoff on a Spatiotemporal Basis for managing water resources in flood-prone region of Bangladesh |
| 12:35 - 12:50 | 509 | Bilal Ahmed Al-Saeedi | An optimized representation of precipitation in Jordan: Merging gridded precipitation products and ground-based measurements using machine learning and geostatistical approaches |
| 12:50 - 13:00 | --- | All | Group Discussion & Closing |