HIDRA3: a deep-learning model for multipoint ensemble sea level forecasting in the presence of tide gauge sensor failures
<p>Accurate modeling of sea level and storm surge dynamics with several days of temporal horizons is essential for effective coastal flood responses and the protection of coastal communities and economies. The classical approach to this challenge involves computationally intensive ocean models...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2025-02-01
|
| Series: | Geoscientific Model Development |
| Online Access: | https://gmd.copernicus.org/articles/18/605/2025/gmd-18-605-2025.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540932926341120 |
|---|---|
| author | M. Rus M. Rus H. Mihanović M. Ličer M. Ličer M. Kristan |
| author_facet | M. Rus M. Rus H. Mihanović M. Ličer M. Ličer M. Kristan |
| author_sort | M. Rus |
| collection | DOAJ |
| description | <p>Accurate modeling of sea level and storm surge dynamics with several days of temporal horizons is essential for effective coastal flood responses and the protection of coastal communities and economies. The classical approach to this challenge involves computationally intensive ocean models that typically calculate sea levels relative to the geoid, which must then be correlated with local tide gauge observations of sea surface height (SSH). A recently proposed deep-learning model, HIDRA2 (HIgh-performance Deep tidal Residual estimation method using Atmospheric data, version 2), avoids numerical simulations while delivering competitive forecasts. Its forecast accuracy depends on the availability of a sufficiently long history of recorded SSH observations used in training. This makes HIDRA2 less reliable for locations with less abundant SSH training data. Furthermore, since the inference requires immediate past SSH measurements as input, forecasts cannot be made during temporary tide gauge failures. We address the aforementioned issues using a new architecture, HIDRA3, that considers observations from multiple locations, shares the geophysical encoder across the locations, and constructs a joint latent state that is decoded into forecasts at individual locations. The new architecture brings several benefits: (i) it improves training at locations with scarce historical SSH data, (ii) it enables predictions even at locations with sensor failures, and (iii) it reliably estimates prediction uncertainties. HIDRA3 is evaluated by jointly training on 11 tide gauge locations along the Adriatic. Results show that HIDRA3 outperforms HIDRA2 and the Mediterranean basin Nucleus for European Modelling of the Ocean (NEMO) setup of the Copernicus Marine Environment Monitoring Service (CMEMS) by <span class="inline-formula">∼</span> 15 % and <span class="inline-formula">∼</span> 13 % mean absolute error (MAE) reductions at high SSH values, creating a solid new state of the art. The forecasting skill does not deteriorate even in the case of simultaneous failure of multiple sensors in the basin or when predicting solely from the tide gauges far outside the Rossby radius of a failed sensor. Furthermore, HIDRA3 shows remarkable performance with substantially smaller amounts of training data compared with HIDRA2, making it appropriate for sea level forecasting in basins with high regional variability in the available tide gauge data.</p> |
| format | Article |
| id | doaj-art-3756d0a074e0473e9e9871c891ab6701 |
| institution | Kabale University |
| issn | 1991-959X 1991-9603 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | Geoscientific Model Development |
| spelling | doaj-art-3756d0a074e0473e9e9871c891ab67012025-02-04T11:44:10ZengCopernicus PublicationsGeoscientific Model Development1991-959X1991-96032025-02-011860562010.5194/gmd-18-605-2025HIDRA3: a deep-learning model for multipoint ensemble sea level forecasting in the presence of tide gauge sensor failuresM. Rus0M. Rus1H. Mihanović2M. Ličer3M. Ličer4M. Kristan5Office for Meteorology, Hydrology and Oceanography, Slovenian Environment Agency, Ljubljana, SloveniaVisual Cognitive Systems Lab, Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, SloveniaPhysical Oceanography Laboratory, Institute of Oceanography and Fisheries, Split, CroatiaOffice for Meteorology, Hydrology and Oceanography, Slovenian Environment Agency, Ljubljana, SloveniaMarine Biology Station, National Institute of Biology, Piran, SloveniaVisual Cognitive Systems Lab, Faculty of Computer and Information Science, University of Ljubljana, Ljubljana, Slovenia<p>Accurate modeling of sea level and storm surge dynamics with several days of temporal horizons is essential for effective coastal flood responses and the protection of coastal communities and economies. The classical approach to this challenge involves computationally intensive ocean models that typically calculate sea levels relative to the geoid, which must then be correlated with local tide gauge observations of sea surface height (SSH). A recently proposed deep-learning model, HIDRA2 (HIgh-performance Deep tidal Residual estimation method using Atmospheric data, version 2), avoids numerical simulations while delivering competitive forecasts. Its forecast accuracy depends on the availability of a sufficiently long history of recorded SSH observations used in training. This makes HIDRA2 less reliable for locations with less abundant SSH training data. Furthermore, since the inference requires immediate past SSH measurements as input, forecasts cannot be made during temporary tide gauge failures. We address the aforementioned issues using a new architecture, HIDRA3, that considers observations from multiple locations, shares the geophysical encoder across the locations, and constructs a joint latent state that is decoded into forecasts at individual locations. The new architecture brings several benefits: (i) it improves training at locations with scarce historical SSH data, (ii) it enables predictions even at locations with sensor failures, and (iii) it reliably estimates prediction uncertainties. HIDRA3 is evaluated by jointly training on 11 tide gauge locations along the Adriatic. Results show that HIDRA3 outperforms HIDRA2 and the Mediterranean basin Nucleus for European Modelling of the Ocean (NEMO) setup of the Copernicus Marine Environment Monitoring Service (CMEMS) by <span class="inline-formula">∼</span> 15 % and <span class="inline-formula">∼</span> 13 % mean absolute error (MAE) reductions at high SSH values, creating a solid new state of the art. The forecasting skill does not deteriorate even in the case of simultaneous failure of multiple sensors in the basin or when predicting solely from the tide gauges far outside the Rossby radius of a failed sensor. Furthermore, HIDRA3 shows remarkable performance with substantially smaller amounts of training data compared with HIDRA2, making it appropriate for sea level forecasting in basins with high regional variability in the available tide gauge data.</p>https://gmd.copernicus.org/articles/18/605/2025/gmd-18-605-2025.pdf |
| spellingShingle | M. Rus M. Rus H. Mihanović M. Ličer M. Ličer M. Kristan HIDRA3: a deep-learning model for multipoint ensemble sea level forecasting in the presence of tide gauge sensor failures Geoscientific Model Development |
| title | HIDRA3: a deep-learning model for multipoint ensemble sea level forecasting in the presence of tide gauge sensor failures |
| title_full | HIDRA3: a deep-learning model for multipoint ensemble sea level forecasting in the presence of tide gauge sensor failures |
| title_fullStr | HIDRA3: a deep-learning model for multipoint ensemble sea level forecasting in the presence of tide gauge sensor failures |
| title_full_unstemmed | HIDRA3: a deep-learning model for multipoint ensemble sea level forecasting in the presence of tide gauge sensor failures |
| title_short | HIDRA3: a deep-learning model for multipoint ensemble sea level forecasting in the presence of tide gauge sensor failures |
| title_sort | hidra3 a deep learning model for multipoint ensemble sea level forecasting in the presence of tide gauge sensor failures |
| url | https://gmd.copernicus.org/articles/18/605/2025/gmd-18-605-2025.pdf |
| work_keys_str_mv | AT mrus hidra3adeeplearningmodelformultipointensemblesealevelforecastinginthepresenceoftidegaugesensorfailures AT mrus hidra3adeeplearningmodelformultipointensemblesealevelforecastinginthepresenceoftidegaugesensorfailures AT hmihanovic hidra3adeeplearningmodelformultipointensemblesealevelforecastinginthepresenceoftidegaugesensorfailures AT mlicer hidra3adeeplearningmodelformultipointensemblesealevelforecastinginthepresenceoftidegaugesensorfailures AT mlicer hidra3adeeplearningmodelformultipointensemblesealevelforecastinginthepresenceoftidegaugesensorfailures AT mkristan hidra3adeeplearningmodelformultipointensemblesealevelforecastinginthepresenceoftidegaugesensorfailures |