Abstract. We propose a new deep-learning architecture HIDRA2 for sea level and storm tide modeling, which is extremely fast to train and apply and outperforms both our previous network design HIDRA1 and two state-of-the-art numerical ocean models (a NEMO engine with sea level data assimilation and a SCHISM ocean modeling system), over all sea level bins and all forecast lead times. The architecture of HIDRA2 employs novel atmospheric, tidal and sea surface height (SSH) feature encoders as well as a novel feature fusion and SSH regression block. HIDRA2 was trained on surface wind and pressure fields from a single member of the European Centre for Medium-Range Weather Forecasts (ECMWF) atmospheric ensemble and on Koper tide gauge observations. An extensive ablation study was performed to estimate the individual importance of input encoders and data streams. Compared to HIDRA1, the overall mean absolute forecast error is reduced by 13 %, while in storm events it is lower by an even larger margin of 25 %. Consistent superior performance over HIDRA1 as well as over general circulation models is observed in both tails of the sea level distribution: low tail forecasting is relevant for marine traffic scheduling to ports of the northern Adriatic, while high tail accuracy helps coastal flood response. Power spectrum analysis indicates that HIDRA2 most accurately represents the energy density peak centered on the ground state sea surface eigenmode (seiche) and comes a close second to SCHISM in the energy band of the first excited eigenmode. To assign model errors to specific frequency bands covering diurnal and semi-diurnal tides and the two lowest basin seiches, spectral decomposition of sea levels during several historic storms is performed. HIDRA2 accurately predicts amplitudes and temporal phases of the Adriatic basin seiches, which is an important forecasting benefit due to the high sensitivity of the Adriatic storm tide level to the temporal lag between peak tide and peak seiche.

Abstract. We propose a new deep-learning architecture HIDRA2 for sea level and storm surge modeling, which is extremely fast to train and apply, and outperforms both our previous network design HIDRA1 and the state-of-the-art numerical ocean model (a NEMO engine with sea level data assimilation), over all sea level bins and all forecast lead times. The architecture of HIDRA2 employs novel atmospheric, tidal and SSH feature encoders, as well as a novel feature fusion and SSH regression block. HIDRA2 was trained on surface wind and pressure fields from a single member of ECMWF atmospheric ensemble and on Koper tide gauge observations during years 2006–2018, and evaluated on the data from June 2019 to December 2020. Compared to HIDRA1, the overall mean absolute forecast error is reduced by 13.9 %, while on storm surge events it is lower by even a larger margin of 25.1 %. Consistent superior performance over HIDRA1 as well as NEMO is observed in both tails of the sea level distribution. Power spectrum analysis indicates that HIDRA2 most accurately represents the energy density peaks centered on the two lowest Adriatic wind-induced free oscillation eigenmodes (seiches) among all tested models. To assign model errors to specific frequency bands covering diurnal and semi-diurnal tides and the lowest two basin seiches, sea level band-pass filtering of several historic storm surge events is applied. HIDRA2 performs well across all frequency bands and most accurately predicts amplitudes and temporal phases of the Adriatic basin seiches. This is shown to be an important forecasting benefit due to the high sensitivity of total Adriatic storm surge sea level to the phase lag between peak tide and peak seiche.

No abstract

No abstract

<p>We propose a new deep-learning architecture HIDRA2 for sea level and storm tide modeling, which is extremely fast to train and apply and outperforms both our previous network design HIDRA1 and two state-of-the-art numerical ocean models (a NEMO engine with sea level data assimilation and a SCHISM ocean modeling system), over all sea level bins and all forecast lead times. The architecture of HIDRA2 employs novel atmospheric, tidal and sea surface height (SSH) feature encoders as well as a novel feature fusion and SSH regression block. HIDRA2 was trained on surface wind and pressure fields from a single member of the European Centre for Medium-Range Weather Forecasts (ECMWF) atmospheric ensemble and on Koper tide gauge observations. An extensive ablation study was performed to estimate the individual importance of input encoders and data streams. Compared to HIDRA1, the overall mean absolute forecast error is reduced by 13 %, while in storm events it is lower by an even larger margin of 25 %. Consistent superior performance over HIDRA1 as well as over general circulation models is observed in both tails of the sea level distribution: low tail forecasting is relevant for marine traffic scheduling to ports of the northern Adriatic, while high tail accuracy helps coastal flood response. To assign model errors to specific frequency bands covering diurnal and semi-diurnal tides and the two lowest basin seiches, spectral decomposition of sea levels during several historic storms is performed. HIDRA2 accurately predicts amplitudes and temporal phases of the Adriatic basin seiches, which is an important forecasting benefit due to the high sensitivity of the Adriatic storm tide level to the temporal lag between peak tide and peak seiche.</p>