Articles | Volume 14, issue 4
Geosci. Model Dev., 14, 2057–2074, 2021
Geosci. Model Dev., 14, 2057–2074, 2021

Model description paper 21 Apr 2021

Model description paper | 21 Apr 2021

HIDRA 1.0: deep-learning-based ensemble sea level forecasting in the northern Adriatic

Lojze Žust et al.

Related authors

Lagrangian modelling of a person lost at sea during the Adriatic scirocco storm of 29 October 2018
Matjaž Ličer, Solène Estival, Catalina Reyes-Suarez, Davide Deponte, and Anja Fettich
Nat. Hazards Earth Syst. Sci., 20, 2335–2349,,, 2020
Short summary
DINCAE 1.0: a convolutional neural network with error estimates to reconstruct sea surface temperature satellite observations
Alexander Barth, Aida Alvera-Azcárate, Matjaz Licer, and Jean-Marie Beckers
Geosci. Model Dev., 13, 1609–1622,,, 2020
Short summary
Integrated sea storm management strategy: the 29 October 2018 event in the Adriatic Sea
Christian Ferrarin, Andrea Valentini, Martin Vodopivec, Dijana Klaric, Giovanni Massaro, Marco Bajo, Francesca De Pascalis, Amedeo Fadini, Michol Ghezzo, Stefano Menegon, Lidia Bressan, Silvia Unguendoli, Anja Fettich, Jure Jerman, Matjaz̆ Ličer, Lidija Fustar, Alvise Papa, and Enrico Carraro
Nat. Hazards Earth Syst. Sci., 20, 73–93,,, 2020
Short summary
Modeling the ocean and atmosphere during an extreme bora event in northern Adriatic using one-way and two-way atmosphere–ocean coupling
M. Ličer, P. Smerkol, A. Fettich, M. Ravdas, A. Papapostolou, A. Mantziafou, B. Strajnar, J. Cedilnik, M. Jeromel, J. Jerman, S. Petan, V. Malačič, and S. Sofianos
Ocean Sci., 12, 71–86,,, 2016
Short summary

Related subject area

Towards multiscale modeling of ocean surface turbulent mixing using coupled MPAS-Ocean v6.3 and PALM v5.0
Qing Li and Luke Van Roekel
Geosci. Model Dev., 14, 2011–2028,,, 2021
Short summary
Improved representation of river runoff in Estimating the Circulation and Climate of the Ocean Version 4 (ECCOv4) simulations: implementation, evaluation, and impacts to coastal plume regions
Yang Feng, Dimitris Menemenlis, Huijie Xue, Hong Zhang, Dustin Carroll, Yan Du, and Hui Wu
Geosci. Model Dev., 14, 1801–1819,,, 2021
Short summary
The Regional Ice Ocean Prediction System v2: a pan-Canadian ocean analysis system using an online tidal harmonic analysis
Gregory C. Smith, Yimin Liu, Mounir Benkiran, Kamel Chikhar, Dorina Surcel Colan, Audrey-Anne Gauthier, Charles-Emmanuel Testut, Frederic Dupont, Ji Lei, François Roy, Jean-François Lemieux, and Fraser Davidson
Geosci. Model Dev., 14, 1445–1467,,, 2021
Short summary
Global storm tide modeling with ADCIRC v55: unstructured mesh design and performance
William J. Pringle, Damrongsak Wirasaet, Keith J. Roberts, and Joannes J. Westerink
Geosci. Model Dev., 14, 1125–1145,,, 2021
Short summary
Development of a MetUM (v 11.1) and NEMO (v 3.6) coupled operational forecast model for the Maritime Continent – Part 1: Evaluation of ocean forecasts
Bijoy Thompson, Claudio Sanchez, Boon Chong Peter Heng, Rajesh Kumar, Jianyu Liu, Xiang-Yu Huang, and Pavel Tkalich
Geosci. Model Dev., 14, 1081–1100,,, 2021
Short summary

Cited articles

Bai, S., Kolter, J. Z., and Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, arXiv preprint arXiv:1803.01271, (last access: 14 April 2021), 2018. a
Bajo, M. and Umgiesser, G.: Storm surge forecast through a combination of dynamic and neural network models, Ocean Model., 33, 1–9,, 2010. a
Bernier, N. B. and Thompson, K. R.: Deterministic and ensemble storm surge prediction for Atlantic Canada with lead times of hours to ten days, Ocean Model., 86, 114–127,, 2015. a
Bertotti, L., Bidlot, J.-R., Buizza, R., Cavaleri, L., and Janousek, M.: Deterministic and ensemble-based prediction of Adriatic Sea sirocco storms leading to “acqua alta” in Venice, Q. J. Roy. Meteor. Soc., 137, 1446–1466,, 2011.  a
Short summary
Adriatic basin sea level modelling 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.