Preprints
https://doi.org/10.5194/gmd-2020-355
https://doi.org/10.5194/gmd-2020-355

Submitted as: model description paper 02 Nov 2020

Submitted as: model description paper | 02 Nov 2020

Review status: a revised version of this preprint is currently under review for the journal GMD.

HIDRA 1.0: Deep-Learning-Based Ensemble Sea Level Forecasting in the Northern Adriatic

Lojze Žust1, Anja Fettich2, Matej Kristan1, and Matjaž Ličer3 Lojze Žust et al.
  • 1Faculty of Computer and Information Science, Visual Cognitive Systems Lab, University of Ljubljana, Ljubljana, Slovenia
  • 2Slovenian Environment Agency, Group for Meteorological, Hydrological and Oceanographic Modelling, Ljubljana, Slovenia
  • 3National Institute of Biology, Marine Biology Station, Piran, Slovenia

Abstract. Complex interactions between atmospheric forcing, topographic constraints to air and water flow, and resonant character of the basin, make sea level modeling in Adriatic a particularly challenging problem. In this study we present an ensemble deep-neural-network-based sea level forecasting method HIDRA, which outperforms our general ocean circulation model ensemble (NEMO v3.6) for all forecast lead times and at a minuscule fraction of the numerical cost (order of 2 × 10−6). HIDRA exhibits larger bias but lower RMSE than NEMO over most of the residual sea level bins. It introduces a trainable atmospheric spatial encoder and employs fusion of atmospheric and sea level features into a self-contained network which enables discriminative feature learning. The HIDRA architecture building blocks are experimentally analyzed in detail and compared to alternative approaches. Results show individual importance of sea level input for accurate forecast lead times below 24 h and of the atmospheric input for longer time leads. The best performance is achieved by considering the input as the total sea level, split into disjoint sets of tidal and residual signals. This enables HIDRA to optimize the prediction fidelity with respect to atmospheric forcing, while compensating for the errors in the tidal model. HIDRA is trained and analysed on a ten-year (2006–2016) timeseries of atmospheric surface fields from a single member of ECMWF atmospheric ensemble. In the testing phase, both HIDRA and NEMO ensemble systems are forced by the ECMWF atmospheric ensemble. Their performance is evaluated on a one-year (2019) hourly time series from tide gauge in Koper (Slovenia). Spectral analysis of the forecasts at semi-diurnal frequency (12 h)−1 and at ground-state basin seiche frequency (21.5 h)−1 is performed by a continuous wavelet transform. The energy at the basin seiche in the HIDRA forecast is close to the observed, while NEMO underestimates it. Analyses of the January 2015 and November 2019 storm surges indicate that HIDRA has learned to mimic timing and amplitude of resonant sea level excitations in the basin.

Lojze Žust et al.

 
Status: final response (author comments only)
Status: final response (author comments only)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Login for authors/topical editors] [Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement

Lojze Žust et al.

Data sets

NEMO, HIDRA and Tide Gauge Datasets for HIDRA Machine Learning Algorithm Verification Lojze Žust, Matej Kristan, Anja Fettich, and Matjaz Licer https://doi.org/10.5281/zenodo.4106440

Lojze Žust et al.

Viewed

Total article views: 368 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
285 78 5 368 9 6
  • HTML: 285
  • PDF: 78
  • XML: 5
  • Total: 368
  • BibTeX: 9
  • EndNote: 6
Views and downloads (calculated since 02 Nov 2020)
Cumulative views and downloads (calculated since 02 Nov 2020)

Viewed (geographical distribution)

Total article views: 224 (including HTML, PDF, and XML) Thereof 220 with geography defined and 4 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 26 Feb 2021
Download
Short summary
Adriatic basin sea level modeling is a challenging problem due to the interplay between terrain, weather, tides and seiches. Current state-of-the-art numerical models (e.g. NEMO) require large computational resources to produce reliable forecasts. In this study we propose HIDRA, a novel deep learning approach for sea level modeling, which drastically reduces the numerical cost while demonstrating predictive capabilities comparable to that of the NEMO model, outperforming it in many instances.