Details zur Publikation |
| Kategorie | Textpublikation |
| Referenztyp | Buchkapitel |
| DOI | 10.1109/OCEANS55160.2024.10754080 |
| Titel (primär) | AI-quifer - Using artificial intelligence to determine offshore groundwater occurrences that are key to coastal water management |
| Titel (sekundär) | Proceedings OCEANS 2024, Halifax, 23-26 September 2024 |
| Autor | Haffert, L.; Jegen, M.; Siebert, C.
; Rödiger, T.; Berndt, C. |
| Quelle | Oceans Conference Record (IEEE) |
| Erscheinungsjahr | 2024 |
| Department | CATHYD |
| Seite von | 1 |
| Seite bis | 5 |
| Sprache | englisch |
| Topic | T5 Future Landscapes |
| Keywords | Geology; Sea floor; Sea measurements; Training data; Process control; Predictive models; Data models; Reliability; Freshwater; Stress; Offshore freshened groundwater; machine learning; hydrogeological modelling |
| Abstract | The current stress on global freshwater supply highlights the importance to further investigate the presence of offshore freshened groundwater (OFG), a resource that is estimated to amount to 10 to 100 times the global volume of freshwater consumed over the last 100 years. In line with recent developments in terrestrial data-driven groundwater modelling, we propose that globally available geospatial data (e.g. Digital Elevation Models, global groundwater models, geological and seafloor information), in conjunction with climatic data, can be used to predict the largely hidden offshore occurrence of coastal freshwater aquifers. Specifically, we aim to derive a reliable machine learning method that will account for the complex underlying hydrological mechanism of offshore groundwater emplacement and preservation. Here we present the results of the first phase of the AI-quifer project; (1) the derivation of proxi attributes (indicators) that are representative of the hydrogeological processes controlling OFG, and (2) the preparation of geological cross sections (orthogonally to the coastline) to augment the ML training data and evaluate the behaviour and influence of hydraulic conditions on the development of OFG due to changing boundary conditions (transmission from glacial to interglacial or vice versa). |
| dauerhafte UFZ-Verlinkung | https://www.ufz.de/index.php?en=20939&ufzPublicationIdentifier=30271 |
| Haffert, L., Jegen, M., Siebert, C., Rödiger, T., Berndt, C. (2024): AI-quifer - Using artificial intelligence to determine offshore groundwater occurrences that are key to coastal water management Proceedings OCEANS 2024, Halifax, 23-26 September 2024 Oceans Conference Record (IEEE) Institute of Electrical and Electronics Engineers (IEEE), New York, NY, p. 1 - 5 10.1109/OCEANS55160.2024.10754080 |
|