pith. machine review for the scientific record. sign in

arxiv: 2604.20688 · v2 · submitted 2026-04-22 · 💻 cs.LG · cs.AI

StormNet: Improving storm surge predictions with a GNN-based spatio-temporal offset forecasting model

Noujoud Nader , Stefanos Giaremis , Clint Dawson , Carola Kaiser , Karame Mohammadiporshokooh , Hartmut Kaiser This is my paper

Pith reviewed 2026-05-10 01:28 UTC · model grok-4.3

classification 💻 cs.LG cs.AI
keywords storm surge forecastinggraph neural networkbias correctionhurricane predictionspatio-temporal modelingwater level predictionGNNLSTM
0
0 comments X

The pith

A graph neural network corrects storm surge forecast biases by more than 70 percent for 48-hour predictions using Gulf Coast hurricane data.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces StormNet to improve storm surge forecasts by adding a data-driven bias correction step to traditional numerical models such as ADCIRC. It combines graph convolutional and attention layers with LSTM units to learn how water levels at different coastal gauges influence one another over time. Trained on past U.S. Gulf Coast hurricanes and tested on Hurricane Idalia, the model cuts root-mean-square errors substantially at 48- and 72-hour horizons while running fast enough for operational use. A sympathetic reader would care because more accurate forecasts give coastal communities clearer signals for evacuation and protection decisions during tropical cyclones. The work focuses on capturing spatial and temporal patterns that standard sequential models miss at longer lead times.

Core claim

StormNet integrates graph convolutional and graph attention mechanisms with LSTM components to capture complex spatial and temporal dependencies among water-level gauge stations, trained on historical U.S. Gulf Coast hurricane data and evaluated on Hurricane Idalia, where it reduces RMSE in water-level predictions by more than 70 percent for 48-hour forecasts and above 50 percent for 72-hour forecasts while outperforming a sequential LSTM baseline.

What carries the argument

Spatio-temporal graph neural network that combines GCN and GAT layers with LSTM units to produce offset forecasts for bias correction of water-level predictions across gauge stations.

If this is right

  • Water-level predictions become more accurate at 48- to 72-hour lead times during tropical cyclones.
  • The model runs with low training time and can support real-time operational forecasting systems.
  • It outperforms sequential LSTM approaches especially when forecast horizons lengthen.
  • The framework supplies a computationally efficient layer that can be added to existing high-fidelity numerical models.
  • Coastal impact mitigation improves because forecasts carry lower uncertainty during extreme weather events.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Retraining the network on local gauge data could allow similar error reductions in other coastal basins.
  • A hybrid system that feeds StormNet corrections back into ensemble numerical runs might lower overall computational cost.
  • The approach could be tested on rapidly intensifying storms that lie outside the historical training distribution to check robustness.
  • Extending the graph to include additional variables such as wind or pressure fields might further improve offset accuracy.

Load-bearing premise

The spatial and temporal patterns learned from historical Gulf Coast hurricanes will hold for new storms such as Idalia and for other coastal regions without retraining or adaptation.

What would settle it

Testing StormNet on a storm outside the Gulf Coast training distribution, such as a hurricane making landfall on the U.S. Atlantic coast, and finding no RMSE reduction relative to the LSTM baseline at 48-hour and longer horizons.

read the original abstract

Storm surge forecasting remains a critical challenge in mitigating the impacts of tropical cyclones on coastal regions, particularly given recent trends of rapid intensification and increasing nearshore storm activity. Traditional high fidelity numerical models such as ADCIRC, while robust, are often hindered by inevitable uncertainties arising from various sources. To address these challenges, this study introduces StormNet, a spatio-temporal graph neural network (GNN) designed for bias correction of storm surge forecasts. StormNet integrates graph convolutional (GCN) and graph attention (GAT) mechanisms with long short-term memory (LSTM) components to capture complex spatial and temporal dependencies among water-level gauge stations. The model was trained using historical hurricane data from the U.S. Gulf Coast and evaluated on Hurricane Idalia (2023). Results demonstrate that StormNet can effectively reduce the root mean square error (RMSE) in water-level predictions by more than 70\% for 48-hour forecasts and above 50\% for 72-hour forecasts, as well as outperform a sequential LSTM baseline, particularly for longer prediction horizons. The model also exhibits low training time, enhancing its applicability in real-time operational forecasting systems. Overall, StormNet provides a computationally efficient and physically meaningful framework for improving storm surge prediction accuracy and reliability during extreme weather events.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper introduces StormNet, a spatio-temporal GNN model combining graph convolutional networks (GCN), graph attention networks (GAT), and LSTM units to perform bias correction on numerical storm surge forecasts. Trained on historical U.S. Gulf Coast hurricane data, the model is evaluated on the held-out Hurricane Idalia (2023) and claims to reduce RMSE in water-level predictions by more than 70% for 48-hour forecasts and over 50% for 72-hour forecasts relative to the baseline numerical model, while also outperforming a sequential LSTM baseline especially at longer horizons.

Significance. If the performance gains prove robust, StormNet could provide a practical, low-latency post-processing framework for improving operational storm surge predictions, particularly by modeling spatial dependencies across gauge stations via graph mechanisms. This addresses a real need in coastal forecasting where numerical models like ADCIRC have persistent biases at extended lead times.

major comments (3)
  1. [Results / Evaluation] The central empirical claims (>70% RMSE reduction at 48 h and >50% at 72 h versus the numerical baseline and LSTM) rest exclusively on performance for a single held-out event (Hurricane Idalia). The results section provides no leave-one-storm-out cross-validation, no additional test storms, no variance estimates across events, and no statistical significance tests on the error reductions, leaving the generalizability of the reported gains open to question.
  2. [Methods] The methods section supplies no information on training dataset size (number of historical storms, number of gauge stations, total time steps), graph construction details (edge definition between stations), loss function, optimizer, or hyperparameter selection procedure. These omissions make it impossible to assess whether the reported improvements are reproducible or sensitive to implementation choices.
  3. [Results] The comparison to the sequential LSTM baseline is presented without an ablation study isolating the contribution of the GCN/GAT components, without details on the LSTM architecture or training regime, and without analysis of why the spatio-temporal GNN yields larger gains specifically at longer horizons.
minor comments (2)
  1. [Abstract] The abstract states that the model has 'low training time' but provides no quantitative runtime figures or comparison against the numerical model's wall-clock cost.
  2. [Methods] Notation for the offset forecasting target and the precise input/output formulation of the GNN-LSTM hybrid could be clarified with an equation or diagram in the methods section.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and detailed review. We address each major comment below and commit to revisions that improve reproducibility and clarify limitations without overstating the current results.

read point-by-point responses

  1. Referee: The central empirical claims (>70% RMSE reduction at 48 h and >50% at 72 h versus the numerical baseline and LSTM) rest exclusively on performance for a single held-out event (Hurricane Idalia). The results section provides no leave-one-storm-out cross-validation, no additional test storms, no variance estimates across events, and no statistical significance tests on the error reductions, leaving the generalizability of the reported gains open to question.

    Authors: We acknowledge that reliance on a single held-out event (Idalia) limits claims of broad generalizability. Idalia was chosen as a recent, high-impact hurricane with independent gauge data. In revision we will add a limitations subsection discussing this constraint, include statistical significance tests on the reported RMSE reductions where feasible, and explore performance on at least one additional historical storm if the training corpus permits. A full leave-one-storm-out study may not be possible given the limited number of well-observed Gulf Coast events, so this will be a partial revision. revision: partial

  2. Referee: The methods section supplies no information on training dataset size (number of historical storms, number of gauge stations, total time steps), graph construction details (edge definition between stations), loss function, optimizer, or hyperparameter selection procedure. These omissions make it impossible to assess whether the reported improvements are reproducible or sensitive to implementation choices.

    Authors: We apologize for these omissions. The revised methods section will explicitly state the training corpus size (number of historical storms and specific events), number of gauge stations, total time steps, graph construction (edge definition via geographic proximity with optional correlation threshold), loss function (MSE), optimizer (Adam with learning rate), and hyperparameter selection procedure (grid search or validation-based tuning). These additions will enable full reproducibility. revision: yes

  3. Referee: The comparison to the sequential LSTM baseline is presented without an ablation study isolating the contribution of the GCN/GAT components, without details on the LSTM architecture or training regime, and without analysis of why the spatio-temporal GNN yields larger gains specifically at longer horizons.

    Authors: We will add an ablation study quantifying the incremental benefit of the GCN and GAT layers over a pure LSTM. Full architectural details and training regime for the LSTM baseline will be provided. We will also include analysis attributing the larger gains at longer horizons to the GNN's explicit modeling of spatial error propagation across the gauge network, which becomes increasingly important as local biases accumulate over extended lead times. revision: yes

Circularity Check

0 steps flagged

No significant circularity; results are empirical on held-out data

full rationale

The paper introduces StormNet as a GNN-based model combining GCN, GAT, and LSTM components for storm surge bias correction. It is trained on historical U.S. Gulf Coast hurricane data and evaluated directly on the unseen Hurricane Idalia (2023) event, reporting RMSE reductions versus the ADCIRC numerical baseline and a sequential LSTM. No derivation chain, equations, or claims reduce outputs to inputs by construction; there are no self-definitional fits, fitted inputs renamed as predictions, load-bearing self-citations, uniqueness theorems, or smuggled ansatzes. The performance numbers are presented as straightforward empirical test outcomes on external held-out data, making the work self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The central claim depends on the empirical performance of a trained neural network; no additional free parameters, axioms, or invented physical entities are introduced beyond standard machine-learning training assumptions and the choice of graph connectivity among gauge stations.

pith-pipeline@v0.9.0 · 5547 in / 1100 out tokens · 29029 ms · 2026-05-10T01:28:17.003543+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

99 extracted references · 65 canonical work pages · 1 internal anchor

  1. [1]

    doi:10.25921/stkw-7w73 , urldate =

    Smith, A.B.: U.S. Billion-dollar Weather and Climate Disasters, 1980 - present (NCEI Accession 0209268). NOAA National Centers for Environmental Infor- mation. Dataset (2020). https://doi.org/10.25921/STKW-7W73 . https://www. ncei.noaa.gov/access/billions/summary-stats/US/2004-2024

    work page doi:10.25921/stkw-7w73 1980

  2. [2]

    Nature 603(7903), 841–845 (2022) https://doi.org/10.1038/s41586-022-04426-5 35

    Calafat, F.M., Wahl, T., Tadesse, M.G., Sparrow, S.N.: Trends in europe storm surge extremes match the rate of sea-level rise. Nature 603(7903), 841–845 (2022) https://doi.org/10.1038/s41586-022-04426-5 35

    work page doi:10.1038/s41586-022-04426-5 2022

  3. [3]

    Science 373(6553), 453–457 (2021) https://doi.org/10.1126/science.abb9038

    Wang, S., Toumi, R.: Recent migration of tropical cyclones toward coasts. Science 371(6528), 514–517 (2021) https://doi.org/10.1126/science.abb9038

    work page doi:10.1126/science.abb9038 2021

  4. [4]

    npj Climate and Atmospheric Science 2(1) (2019) https://doi.org/10.1038/s41612-019-0074-8

    Hall, T.M., Kossin, J.P.: Hurricane stalling along the North American coast and implications for rainfall. npj Climate and Atmospheric Science 2(1) (2019) https://doi.org/10.1038/s41612-019-0074-8

    work page doi:10.1038/s41612-019-0074-8 2019

  5. [5]

    Nature 563(7731), 339–346 (2018) https://doi.org/10.1038/ s41586-018-0673-2

    Patricola, C.M., Wehner, M.F.: Anthropogenic influences on major tropical cyclone events. Nature 563(7731), 339–346 (2018) https://doi.org/10.1038/ s41586-018-0673-2

    2018

  6. [6]

    Nature 587(7833), 230–234 (2020) https://doi.org/10.1038/ s41586-020-2867-7

    Li, L., Chakraborty, P.: Slower decay of landfalling hurricanes in a warming world. Nature 587(7833), 230–234 (2020) https://doi.org/10.1038/ s41586-020-2867-7

    2020

  7. [7]

    Earth’s Future 12(5) (2024) https://doi.org/10.1029/ 2023ef004230

    Balaguru, K., Chang, C., Leung, L.R., Foltz, G.R., Hagos, S.M., Wehner, M.F., Kossin, J.P., Ting, M., Xu, W.: A global increase in nearshore tropical cyclone intensification. Earth’s Future 12(5) (2024) https://doi.org/10.1029/ 2023ef004230

    2024

  8. [8]

    Climate Dynamics 62(1), 331–344 (2023) https://doi.org/10.1007/s00382-023-06917-1

    Li, X., Zhan, R., Wang, Y., Zhao, J., Ding, Y., Song, K.: Recent increase in rapid intensification events of tropical cyclones along China coast. Climate Dynamics 62(1), 331–344 (2023) https://doi.org/10.1007/s00382-023-06917-1

    work page doi:10.1007/s00382-023-06917-1 2023

  9. [9]

    Environmental Research Letters (2025)

    Shi, J., Hu, C., Cannizzaro, J., Barnes, B.B., Zhang, Y., Lembke, C., Le Henaff, M.: Intensification of hurricane idalia by a river plume in the eastern gulf of mexico. Environmental Research Letters (2025)

    2025

  10. [10]

    Geophysical Research Letters 52(1) (2024) https: 36 //doi.org/10.1029/2024gl113192

    Liu, Y., Weisberg, R.H., Sorinas, L., Law, J.A., Nickerson, A.K.: Rapid inten- sification of Hurricane Ian in relation to anomalously warm subsurface water on the wide continental shelf. Geophysical Research Letters 52(1) (2024) https: 36 //doi.org/10.1029/2024gl113192

    work page doi:10.1029/2024gl113192 2024

  11. [11]

    Bulletin of the Ameri- can Meteorological Society 103(10), 2354–2369 (2022) https://doi.org/10.1175/ bams-d-21-0240.1

    Zhu, Y.-J., Collins, J.M., Klotzbach, P.J., Schreck, C.J.: Hurricane Ida (2021): Rapid intensification followed by slow inland decay. Bulletin of the Ameri- can Meteorological Society 103(10), 2354–2369 (2022) https://doi.org/10.1175/ bams-d-21-0240.1

    2021

  12. [12]

    Tropical Cyclone Research and Review 13(2), 88–112 (2024) https://doi.org/10.1016/j.tcrr.2024.06.002

    Kotal, S.D., Arulalan, T., Mohapatra, M.: Forecasting of tropical cyclones ASANI (2022) and MOCHA (2023) over the Bay of Bengal - real time challenges to forecasters. Tropical Cyclone Research and Review 13(2), 88–112 (2024) https://doi.org/10.1016/j.tcrr.2024.06.002

    work page doi:10.1016/j.tcrr.2024.06.002 2022

  13. [13]

    Natural Hazards 121(7), 8279–8303 (2025) https://doi.org/ 10.1007/s11069-025-07138-x

    Petilla, C.E.R., Olaguera, L.M.P., Cruz, F.A.T., Villarin, J.R.T., Fudeyasu, H., Yoshida, R., Matsumoto, J.: The unique features of typhoon rai (2021): an observational study. Natural Hazards 121(7), 8279–8303 (2025) https://doi.org/ 10.1007/s11069-025-07138-x

    work page doi:10.1007/s11069-025-07138-x 2021

  14. [14]

    Journal of Geophysical Research: Atmospheres 124(24), 13731–13749 (2019) https:// doi.org/10.1029/2019jd031377

    Zhang, Z., Wang, Y., Zhang, W., Xu, J.: Coastal ocean response and its feedback to Typhoon Hato (2017) over the South China Sea: A numerical study. Journal of Geophysical Research: Atmospheres 124(24), 13731–13749 (2019) https:// doi.org/10.1029/2019jd031377

    work page doi:10.1029/2019jd031377 2017

  15. [15]

    Journal of the Atmospheric Sciences 74(4), 1169–1200 (2017) https://doi.org/10.1175/jas-d-16-0075.1

    Chang, C.-C., Wu, C.-C.: On the processes leading to the rapid intensification of Typhoon Megi (2010). Journal of the Atmospheric Sciences 74(4), 1169–1200 (2017) https://doi.org/10.1175/jas-d-16-0075.1

    work page doi:10.1175/jas-d-16-0075.1 2010

  16. [16]

    Atmospheric Chemistry and Physics 15(24), 14041–14053 (2015) https://doi.org/10.5194/ acp-15-14041-2015 37

    Wu, L., Su, H., Fovell, R.G., Dunkerton, T.J., Wang, Z., Kahn, B.H.: Impact of environmental moisture on tropical cyclone intensification. Atmospheric Chemistry and Physics 15(24), 14041–14053 (2015) https://doi.org/10.5194/ acp-15-14041-2015 37

    2015

  17. [17]

    Journal of the Atmospheric Sciences , author =

    Zagrodnik, J.P., Jiang, H.: Rainfall, convection, and latent heating distributions in rapidly intensifying tropical cyclones. Journal of the Atmospheric Sciences 71(8), 2789–2809 (2014) https://doi.org/10.1175/jas-d-13-0314.1

    work page doi:10.1175/jas-d-13-0314.1 2014

  18. [18]

    Geophysical Research Letters 52(10) (2025) https://doi.org/10.1029/ 2024gl113531

    Wu, X., Hoffmann, L., Wright, C.J., Hindley, N.P., Alexander, M.J., Wang, X., Chen, B., Wang, Y., Li, M.: Mechanisms linking stratospheric gravity wave activity to hurricane intensification: Insights from model simulation of Hurricane Joaquin. Geophysical Research Letters 52(10) (2025) https://doi.org/10.1029/ 2024gl113531

    2025

  19. [19]

    Environmental Research Letters 19(11), 114058 (2024) https: //doi.org/10.1088/1748-9326/ad7ee0

    Yang, S., Shin, D., Cocke, S., Nam, C.C., Bourassa, M., Cha, D.-H., Kim, B.- M.: Unveiling the pivotal influence of sea spray heat fluxes on hurricane rapid intensification. Environmental Research Letters 19(11), 114058 (2024) https: //doi.org/10.1088/1748-9326/ad7ee0

    work page doi:10.1088/1748-9326/ad7ee0 2024

  20. [20]

    Artificial Intelligence for the Earth Systems 3(2) (2024) https: //doi.org/10.1175/aies-d-23-0052.1

    Kim, J.-H., Ham, Y.-G., Kim, D., Li, T., Ma, C.: Improvement in forecasting short-term tropical cyclone intensity change and their rapid intensification using deep learning. Artificial Intelligence for the Earth Systems 3(2) (2024) https: //doi.org/10.1175/aies-d-23-0052.1

    work page doi:10.1175/aies-d-23-0052.1 2024

  21. [21]

    Weather and Forecasting 35(5), 1913–1922 (2020) https://doi.org/10.1175/waf-d-20-0059.1

    Cangialosi, J.P., Blake, E., DeMaria, M., Penny, A., Latto, A., Rappaport, E., Tallapragada, V.: Recent progress in tropical cyclone intensity forecasting at the National Hurricane Center. Weather and Forecasting 35(5), 1913–1922 (2020) https://doi.org/10.1175/waf-d-20-0059.1

    work page doi:10.1175/waf-d-20-0059.1 1913

  22. [22]

    Weather and Forecasting 35(6), 2219–2234 (2020) https://doi.org/10.1175/waf-d-19-0253.1

    Trabing, B.C., Bell, M.M.: Understanding error distributions of hurricane inten- sity forecasts during rapid intensity changes. Weather and Forecasting 35(6), 2219–2234 (2020) https://doi.org/10.1175/waf-d-19-0253.1

    work page doi:10.1175/waf-d-19-0253.1 2020

  23. [23]

    Coastal Engineering 137, 59–78 (2018) https: //doi.org/10.1016/j.coastaleng.2018.02.008

    Cyriac, R., Dietrich, J.C., Fleming, J.G., Blanton, B.O., Kaiser, C., Dawson, 38 C.N., Luettich, R.A.: Variability in coastal flooding predictions due to forecast errors during Hurricane Arthur. Coastal Engineering 137, 59–78 (2018) https: //doi.org/10.1016/j.coastaleng.2018.02.008

    work page doi:10.1016/j.coastaleng.2018.02.008 2018

  24. [25]

    Weather and Forecasting 38(12), 2461–2479 (2023) https://doi.org/10.1175/waf-d-22-0209.1

    Penny, A.B., Alaka, L., Taylor, A.A., Booth, W., DeMaria, M., Fritz, C., Rhome, J.: Operational storm surge forecasting at the national hurricane cen- ter: The case for probabilistic guidance and the evaluation of improved storm size forecasts used to define the wind forcing. Weather and Forecasting 38(12), 2461–2479 (2023) https://doi.org/10.1175/waf-d-22-0209.1

    work page doi:10.1175/waf-d-22-0209.1 2023

  25. [26]

    Ocean Dynamics 65(5), 617–646 (2015) https://doi.org/ 10.1007/s10236-015-0820-3

    Suh, S.W., Lee, H.Y., Kim, H.J., Fleming, J.G.: An efficient early warning system for typhoon storm surge based on time-varying advisories by coupled ADCIRC and SW AN. Ocean Dynamics 65(5), 617–646 (2015) https://doi.org/ 10.1007/s10236-015-0820-3

    work page doi:10.1007/s10236-015-0820-3 2015

  26. [27]

    Journal of Hydraulic Engineering 118(10), 1373–1390 (1992) https://doi.org/10.1061/ (asce)0733-9429(1992)118:10(1373)

    Westerink, J.J., Luettich, R.A., Baptists, A.M., Scheffner, N.W., Farrar, P.: Tide and storm surge predictions using finite element model. Journal of Hydraulic Engineering 118(10), 1373–1390 (1992) https://doi.org/10.1061/ (asce)0733-9429(1992)118:10(1373)

    1992

  27. [28]

    model description and validation

    Booij, N., Ris, R.C., Holthuijsen, L.H.: A third‚Äêgeneration wave model for coastal regions: 1. model description and validation. Journal of Geophys- ical Research: Oceans 104(C4), 7649–7666 (1999) https://doi.org/10.1029/ 98jc02622 39

    1999

  28. [30]

    https://cera.coastalrisk.live/ (2025)

    CERA - Coastal Emergency Risk Accessment: Center for Computation and Technology at Louisiana State University. https://cera.coastalrisk.live/ (2025)

    2025

  29. [31]

    Journal of Marine Science and Engineering 13(5), 864 (2025) https://doi.org/10.3390/ jmse13050864

    Chen, F., Yang, W., Xiao, L., Xia, X., Ding, K., Sun, Z.: An exploratory assess- ment of a submarine topographic characteristic index for predicting extreme flow velocities: A case study of Typhoon In—Fa in the Zhoushan Sea area. Journal of Marine Science and Engineering 13(5), 864 (2025) https://doi.org/10.3390/ jmse13050864

    2025

  30. [32]

    Geo- scientific Model Development 14(2), 1125–1145 (2021) https://doi.org/10.5194/ gmd-14-1125-2021

    Pringle, W.J., Wirasaet, D., Roberts, K.J., Westerink, J.J.: Global storm tide modeling with ADCIRC v55: unstructured mesh design and performance. Geo- scientific Model Development 14(2), 1125–1145 (2021) https://doi.org/10.5194/ gmd-14-1125-2021

    2021

  31. [33]

    Journal of Advances in Modeling Earth Systems 15(2) (2023) https://doi.org/10.1029/2022ms003356

    Khani, S., Dawson, C.N.: A gradient based subgrid‚Äêscale parameterization for ocean mesoscale eddies. Journal of Advances in Modeling Earth Systems 15(2) (2023) https://doi.org/10.1029/2022ms003356

    work page doi:10.1029/2022ms003356 2023

  32. [34]

    Journal of Geophysical Research: Oceans 127(5) (2022) https://doi.org/ 10.1029/2021jc018178 40

    Blakely, C.P., Ling, G., Pringle, W.J., Contreras, M.T., Wirasaet, D., Westerink, J.J., Moghimi, S., Seroka, G., Shi, L., Myers, E., Owensby, M., Massey, C.: Dissipation and bathymetric sensitivities in an unstructured mesh global tidal model. Journal of Geophysical Research: Oceans 127(5) (2022) https://doi.org/ 10.1029/2021jc018178 40

    work page doi:10.1029/2021jc018178 2022

  33. [35]

    Ocean Modelling 190, 102387 (2024) https://doi.org/10.1016/j.ocemod.2024.102387

    Loveland, M., Meixner, J., Valseth, E., Dawson, C.: Efficacy of reduced order source terms for a coupled wave-circulation model in the Gulf of Mexico. Ocean Modelling 190, 102387 (2024) https://doi.org/10.1016/j.ocemod.2024.102387

    work page doi:10.1016/j.ocemod.2024.102387 2024

  34. [36]

    npj Natural Hazards 1(1) (2024) https://doi.org/10

    Dawson, C., Loveland, M., Pachev, B., Proft, J., Valseth, E.: SWEMniCS: a software toolbox for modeling coastal ocean circulation, storm surges, inland, and compound flooding. npj Natural Hazards 1(1) (2024) https://doi.org/10. 1038/s44304-024-00036-5

    2024

  35. [37]

    Weather and Climate Extremes 45, 100689 (2024) https://doi.org/10.1016/j.wace.2024.100689

    Bernier, N.B., Hemer, M., Mori, N., Appendini, C.M., Breivik, O., Camargo, R., Casas-Prat, M., Duong, T.M., Haigh, I.D., Howard, T., Hernaman, V., Huizy, O., Irish, J.L., Kirezci, E., Kohno, N., Lee, J.-W., McInnes, K.L., Meyer, E.M.I., Marcos, M., Marsooli, R., Martin Oliva, A., Menendez, M., Moghimi, S., Muis, S., Polton, J.A., Pringle, W.J., Ranasinghe...

    work page doi:10.1016/j.wace.2024.100689 2024

  36. [38]

    Frontiers in Climate 2 (2021) https://doi.org/10.3389/fclim.2020.609610

    Loveland, M., Kiaghadi, A., Dawson, C.N., Rifai, H.S., Misra, S., Mosser, H., Parola, A.: Developing a modeling framework to simulate compound flooding: When storm surge interacts with riverine flow. Frontiers in Climate 2 (2021) https://doi.org/10.3389/fclim.2020.609610

    work page doi:10.3389/fclim.2020.609610 2021

  37. [39]

    Frontiers in Marine Science 11 (2024) https://doi.org/ 10.3389/fmars.2024.1364929 41

    Wei, W., Huang, S., Qin, H., Yu, L., Mu, L.: Storm surge risk assessment and sensitivity analysis based on multiple criteria decision-making methods: a case study of Huizhou city. Frontiers in Marine Science 11 (2024) https://doi.org/ 10.3389/fmars.2024.1364929 41

    work page doi:10.3389/fmars.2024.1364929 2024

  38. [40]

    Port vulnerability assessment from a supply chain perspective.Ocean & Coastal Management, 213:105851, 2021

    Zhang, Z., Lu, Y., Hu, D., Guo, F., Yu, Z., Song, Z., Chen, P., Wu, J., Huang, W.: A cross-scale modeling framework for simulating typhoon-induced com- pound floods and assessing the emergency response in urban regions. Ocean & Coastal Management 245, 106863 (2023) https://doi.org/10.1016/j.ocecoaman. 2023.106863

    work page doi:10.1016/j.ocecoaman 2023

  39. [41]

    Frontiers of Structural and Civil Engineering 15(6), 1301–1316 (2021) https://doi.org/10.1007/s11709-021-0765-1

    Huang, W., Yin, K., Ghorbanzadeh, M., Ozguven, E., Xu, S., Vijayan, L.: Integrating storm surge modeling with traffic data analysis to evaluate the effec- tiveness of hurricane evacuation. Frontiers of Structural and Civil Engineering 15(6), 1301–1316 (2021) https://doi.org/10.1007/s11709-021-0765-1

    work page doi:10.1007/s11709-021-0765-1 2021

  40. [42]

    Ocean Dynamics 75(8) (2025) https://doi.org/ 10.1007/s10236-025-01713-3

    Özkan, F.N., Verlaan, M., Muis, S., Zijl, F.: Sensitivity of global storm surge modelling to sea surface drag. Ocean Dynamics 75(8) (2025) https://doi.org/ 10.1007/s10236-025-01713-3

    work page doi:10.1007/s10236-025-01713-3 2025

  41. [43]

    Coastal Engineering 171, 104057 (2022) https://doi.org/10.1016/ j.coastaleng.2021.104057

    Muñoz, D.F., Abbaszadeh, P., Moftakhari, H., Moradkhani, H.: Account- ing for uncertainties in compound flood hazard assessment: The value of data assimilation. Coastal Engineering 171, 104057 (2022) https://doi.org/10.1016/ j.coastaleng.2021.104057

    work page arXiv 2022

  42. [44]

    Journal of Waterway, Port, Coastal, and Ocean Engineering 145(1) (2019) https://doi.org/10.1061/(asce)ww.1943-5460.0000496

    Torres, M.J., Reza Hashemi, M., Hayward, S., Spaulding, M., Ginis, I., Grilli, S.T.: Role of hurricane wind models in accurate simulation of storm surge and waves. Journal of Waterway, Port, Coastal, and Ocean Engineering 145(1) (2019) https://doi.org/10.1061/(asce)ww.1943-5460.0000496

    work page doi:10.1061/(asce)ww.1943-5460.0000496 2019

  43. [45]

    Geosciences 8(12), 450 (2018) https://doi.org/10.3390/geosciences8120450

    Gallien, T.W., Kalligeris, N., Delisle, M.-P.C., Tang, B.-X., Lucey, J.T.D., Win- ters, M.A.: Coastal flood modeling challenges in defended urban backshores. Geosciences 8(12), 450 (2018) https://doi.org/10.3390/geosciences8120450

    work page doi:10.3390/geosciences8120450 2018

  44. [46]

    Journal of Geophysical Research: Oceans 119(3), 1812–1827 (2014) https://doi.org/10.1002/2013jc009604

    Ferreira, C.M., Irish, J.L., Olivera, F.: Uncertainty in hurricane surge simulation 42 due to land cover specification. Journal of Geophysical Research: Oceans 119(3), 1812–1827 (2014) https://doi.org/10.1002/2013jc009604

    work page doi:10.1002/2013jc009604 2014

  45. [47]

    Ocean Modelling 144, 101483 (2019) https://doi.org/10.1016/j.ocemod.2019.101483

    Asher, T.G., Luettich Jr., R.A., Fleming, J.G., Blanton, B.O.: Low frequency water level correction in storm surge models using data assimilation. Ocean Modelling 144, 101483 (2019) https://doi.org/10.1016/j.ocemod.2019.101483

    work page doi:10.1016/j.ocemod.2019.101483 2019

  46. [48]

    Technical report, U.S

    Gonzalez, V.M., Nadal-Caraballo, N.C., Melby, J.A., Cialone, M.A.: Quantifi- cation of uncertainty in probabilistic storm surge models: Literature review. Technical report, U.S. Army Corps of Engineers, Engineer Research and Development Center (2019). https://chs.erdc.dren.mil/Library/References/ CHS_PCHA_Publications/Reports/SR-19-1_Gonzalez_et_al_2019_ ...

    2019

  47. [49]

    Natural Hazards 66(3), 1443–1459 (2012) https://doi.org/10.1007/s11069-012-0315-1

    Resio, D.T., Irish, J.L., Westerink, J.J., Powell, N.J.: The effect of uncertainty on estimates of hurricane surge hazards. Natural Hazards 66(3), 1443–1459 (2012) https://doi.org/10.1007/s11069-012-0315-1

    work page doi:10.1007/s11069-012-0315-1 2012

  48. [50]

    coastline using a common impact threshold

    Sweet, W.V., Obeysekera, J.T.B., Marra, J.J., Dusek, G.: Patterns and pro- jections of high tide flooding along the U.S. coastline using a common impact threshold. (2018) https://doi.org/10.7289/V5/TR-NOS-COOPS-086

    work page doi:10.7289/v5/tr-nos-coops-086 2018

  49. [51]

    Journal of Hydrology 617, 128759 (2023)

    Feng, J., Li, D., Dang, W., Zhao, L.: Changes in storm surges based on a bias- adjusted reconstruction dataset from 1900 to 2010. Journal of Hydrology 617, 128759 (2023)

    1900

  50. [52]

    Powell, N., A

    Resio, D.T., J. Powell, N., A. Cialone, M., Das, H.S., Westerink, J.J.: Quantify- ing impacts of forecast uncertainties on predicted storm surges. Natural Hazards 88(3), 1423–1449 (2017) https://doi.org/10.1007/s11069-017-2924-1 43

    work page doi:10.1007/s11069-017-2924-1 2017

  51. [53]

    Butler and M

    Butler, T., Altaf, M.U., Dawson, C., Hoteit, I., Luo, X., Mayo, T.: Data assim- ilation within the Advanced Circulation (ADCIRC) modeling framework for hurricane storm surge forecasting. Monthly Weather Review 140(7), 2215–2231 (2012) https://doi.org/10.1175/mwr-d-11-00118.1

    work page doi:10.1175/mwr-d-11-00118.1 2012

  52. [54]

    and Aerts, Jeroen C

    Muis, S., Verlaan, M., Winsemius, H.C., Aerts, J.C.J.H., Ward, P.J.: A global reanalysis of storm surges and extreme sea levels. Nature Communications 7(1) (2016) https://doi.org/10.1038/ncomms11969

    work page doi:10.1038/ncomms11969 2016

  53. [55]

    Scientific Data 8(1) (2021) https://doi.org/10.1038/s41597-021-00906-x

    Tadesse, M.G., Wahl, T.: A database of global storm surge reconstructions. Scientific Data 8(1) (2021) https://doi.org/10.1038/s41597-021-00906-x

    work page doi:10.1038/s41597-021-00906-x 2021

  54. [56]

    Designsafe-CI (2023)

    Kaiser, C., Dawson, C.N., Nikidis, E., Fleming, J.G.: ADCIRC/SW AN Hindcasts for Historical Storms 2003-2022. Designsafe-CI (2023). https://doi.org/10.17603/DS2-B5GH-CE94 . https://www.designsafe-ci. org/data/browser/public/designsafe.storage.published/PRJ-3932/ #details-5508251847528869395-242ac117-0001-012

    work page doi:10.17603/ds2-b5gh-ce94 2003

  55. [57]

    Geoscience Data Journal 10(3), 293–314 (2022) https://doi.org/10.1002/gdj3.174

    Haigh, I.D., Marcos, M., Talke, S.A., Woodworth, P.L., Hunter, J.R., Hague, B.S., Arns, A., Bradshaw, E., Thompson, P.: <scp>gesla</scp> version 3: A major update to the global higher‚Äêfrequency sea‚Äêlevel dataset. Geoscience Data Journal 10(3), 293–314 (2022) https://doi.org/10.1002/gdj3.174

    work page doi:10.1002/gdj3.174 2022

  56. [58]

    Quarterly Journal of the Royal Meteorological Society 150(764), 4014–4048 (2024) https://doi.org/10.1002/qj.4803

    Soci, C., Hersbach, H., Simmons, A., Poli, P., Bell, B., Berrisford, P., Hor√°nyi, A., Mu√±oz‚ÄêSabater, J., Nicolas, J., Radu, R., Schepers, D., Villaume, S., Haimberger, L., Woollen, J., Buontempo, C., Th√©paut, J.: The ERA5 global reanalysis from 1940 to 2022. Quarterly Journal of the Royal Meteorological Society 150(764), 4014–4048 (2024) https://doi....

    work page doi:10.1002/qj.4803 1940

  57. [59]

    Frontiers in Marine Science 7 (2020) https://doi.org/10.3389/fmars.2020.00263

    Muis, S., Apecechea, M.I., Dullaart, J., Lima Rego, J., Madsen, K.S., Su, J., 44 Yan, K., Verlaan, M.: A high-resolution global dataset of extreme sea levels, tides, and storm surges, including future projections. Frontiers in Marine Science 7 (2020) https://doi.org/10.3389/fmars.2020.00263

    work page doi:10.3389/fmars.2020.00263 2020

  58. [60]

    https://www.aoml.noaa.gov/hrd/ hurdat/Data_Storm.html

    HURDAT Re-analysis — aoml.noaa.gov. https://www.aoml.noaa.gov/hrd/ hurdat/Data_Storm.html. [Accessed 03-10-2025]

    2025

  59. [61]

    https:// historicalstorms.coastalrisk.live/

    CERA - Historical Storm Archive — historicalstorms.coastalrisk.live. https:// historicalstorms.coastalrisk.live/. [Accessed 13-10-2025] (2025)

    2025

  60. [62]

    Advances in Atmospheric Sciences38(4), 690–699 (2021) https://doi.org/10.1007/s00376-020-0211-7

    Lu, X., Yu, H., Ying, M., Zhao, B., Zhang, S., Lin, L., Bai, L., Wan, R.: Western north pacific tropical cyclone database created by the china meteoro- logical administration. Advances in Atmospheric Sciences 38(4), 690–699 (2021) https://doi.org/10.1007/s00376-020-0211-7

    work page doi:10.1007/s00376-020-0211-7 2021

  61. [63]

    In: NeurIPS 2023 Datasets and Benchmarks (Spotlight) (2023)

    KITAMOTO, A., HW ANG, J., VUILLOD, B., GAUTIER, L., TIAN, Y., CLANUW AT, T.: Digital typhoon: Long-term satellite image dataset for the spatio-temporal modeling of tropical cyclones. In: NeurIPS 2023 Datasets and Benchmarks (Spotlight) (2023)

    2023

  62. [64]

    arXiv preprint arXiv:2506.21743 (2025)

    Zhao, J., Cerrone, A., Valseth, E., Westerink, L., Dawson, C.: Storm surge in color: Rgb-encoded physics-aware deep learning for storm surge forecasting. arXiv preprint arXiv:2506.21743 (2025)

    work page arXiv 2025

  63. [65]

    Journal of Marine Science and Engineering 13(5), 896 (2025) https://doi.org/10.3390/jmse13050896

    Han, L., Lu, W., Dong, C.: XAI helps in storm surge forecasts: A case study for the southeastern chinese coasts. Journal of Marine Science and Engineering 13(5), 896 (2025) https://doi.org/10.3390/jmse13050896

    work page doi:10.3390/jmse13050896 2025

  64. [66]

    Natural Hazards 121(14), 16317–16344 (2025) https://doi.org/10.1007/s11069-025-07428-4 45

    Saviz Naeini, S., Snaiki, R., Wu, T.: Advancing spatio-temporal storm surge prediction with hierarchical deep neural networks. Natural Hazards 121(14), 16317–16344 (2025) https://doi.org/10.1007/s11069-025-07428-4 45

    work page doi:10.1007/s11069-025-07428-4 2025

  65. [67]

    Coastal Engineering 197, 104686 (2025) https://doi

    Zhu, Z., Wang, Z., Dong, C., Yu, M., Xie, H., Cao, X., Han, L., Qi, J.: Physics informed neural network modelling for storm surge forecasting — a case study in the Bohai Sea, China. Coastal Engineering 197, 104686 (2025) https://doi. org/10.1016/j.coastaleng.2024.104686

    work page doi:10.1016/j.coastaleng.2024.104686 2025

  66. [68]

    Environmental Research Letters 20(8), 084058 (2025) https: //doi.org/10.1088/1748-9326/ade9e0

    Sreeraj, P., Swapna, P., Singh, M., Krishnan, R.: Improved storm surge pre- diction and extreme sea level future projections in the indian ocean using deep learning. Environmental Research Letters 20(8), 084058 (2025) https: //doi.org/10.1088/1748-9326/ade9e0

    work page doi:10.1088/1748-9326/ade9e0 2025

  67. [69]

    Water 16(17), 2452 (2024) https://doi.org/10

    Huang, S., Nie, H., Jiao, J., Chen, H., Xie, Z.: Tidal level prediction model based on VMD-LSTM neural network. Water 16(17), 2452 (2024) https://doi.org/10. 3390/w16172452

    2024

  68. [70]

    Hendriks, Gregory Y.H

    Shi, X., Chen, P., Ye, Z., Zhang, X., Wang, W.: Tide level prediction dur- ing typhoons based on variable topology in graph convolution recurrent neural networks. Ocean Engineering 312, 119228 (2024) https://doi.org/10.1016/j. oceaneng.2024.119228

    work page doi:10.1016/j 2024

  69. [71]

    A framework for flexible peak storm surge prediction , journal =

    Pachev, B., Arora, P., del-Castillo-Negrete, C., Valseth, E., Dawson, C.: A framework for flexible peak storm surge prediction. Coastal Engineering 186, 104406 (2023) https://doi.org/10.1016/j.coastaleng.2023.104406

    work page doi:10.1016/j.coastaleng.2023.104406 2023

  70. [72]

    Modeling Earth Systems and Environment 10(1), 19–44 (2023) https://doi.org/10.1007/ s40808-023-01835-x

    Dotse, S.-Q., Larbi, I., Limantol, A.M., De Silva, L.C.: A review of the applica- tion of hybrid machine learning models to improve rainfall prediction. Modeling Earth Systems and Environment 10(1), 19–44 (2023) https://doi.org/10.1007/ s40808-023-01835-x

    2023

  71. [73]

    Journal 46 of Geophysical Research: Atmospheres 130(2) (2025) https://doi.org/10.1029/ 2024jd042737

    Wei, C., Zhao, X., Liu, Y., Yang, P., Zhou, Z., Chen, Y.: Bias analysis and correction of ERA5 reanalysis in the context of tropical cyclones. Journal 46 of Geophysical Research: Atmospheres 130(2) (2025) https://doi.org/10.1029/ 2024jd042737

    2025

  72. [74]

    Geophysical Research Letters 52(11), 2025–116048 (2025)

    Li, R., Guilloteau, C., Foufoula-Georgiou, E.: Added value of environmental variables for satellite precipitation retrieval: A temporal coevolution perspective and a machine learning integration assessment. Geophysical Research Letters 52(11), 2025–116048 (2025)

    2025

  73. [75]

    Ocean Modelling 195, 102509 (2025) https://doi.org/10.1016/j.ocemod.2025.102509

    Cerrone, A.R., Westerink, L.G., Ling, G., Blakely, C.P., Wirasaet, D., Dawson, C., Westerink, J.J.: Correcting physics-based global tide and storm water level forecasts with the temporal fusion transformer. Ocean Modelling 195, 102509 (2025) https://doi.org/10.1016/j.ocemod.2025.102509

    work page doi:10.1016/j.ocemod.2025.102509 2025

  74. [76]

    Water 17(10), 1478 (2025) https://doi.org/10.3390/w17101478

    Carneiro-Barros, J.E., Majidi, A.G., Plomaritis, T., Fazeres-Ferradosa, T., Rosa- Santos, P., Taveira-Pinto, F.: Coastal flooding hazards in northern Portugal: A practical large-scale evaluation of total water levels and swash regimes. Water 17(10), 1478 (2025) https://doi.org/10.3390/w17101478

    work page doi:10.3390/w17101478 2025

  75. [77]

    Coastal Engineering 191, 104532 (2024)

    Giaremis, S., Nader, N., Dawson, C., Kaiser, C., Nikidis, E., Kaiser, H.: Storm surge modeling in the AI era: Using LSTM-based machine learning for enhancing forecasting accuracy. Coastal Engineering 191, 104532 (2024)

    2024

  76. [78]

    Ocean Modelling 188, 102334 (2024) https://doi.org/10

    Tedesco, P., Rabault, J., S√¶tra, M.L., Kristensen, N.M., Aarnes, O.J., Breivik, √., Mauritzen, C., S√¶tra, √.: Bias correction of operational storm surge forecasts using neural networks. Ocean Modelling 188, 102334 (2024) https://doi.org/10. 1016/j.ocemod.2024.102334

    work page arXiv 2024

  77. [79]

    Ocean Engineering 311, 118827 (2024) https://doi.org/10.1016/j.oceaneng

    Liao, J., Li, Y., Li, J., Li, S., Peng, S.: A two-module bias-correction model for sea wave hindcasting based on the long-short term memory neural network. Ocean Engineering 311, 118827 (2024) https://doi.org/10.1016/j.oceaneng. 2024.118827 47

    work page doi:10.1016/j.oceaneng 2024

  78. [80]

    Journal of Advances in Modeling Earth Systems 16(8) (2024) https://doi.org/ 10.1029/2023ms004138

    Zhang, S., Harrop, B., Leung, L.R., Charalampopoulos, A., Barthel Sorensen, B., Xu, W., Sapsis, T.: A machine learning bias correction on large‚Äêscale environment of high‚Äêimpact weather systems in E3SM atmosphere model. Journal of Advances in Modeling Earth Systems 16(8) (2024) https://doi.org/ 10.1029/2023ms004138

    work page doi:10.1029/2023ms004138 2024

  79. [81]

    Ocean Modelling 187, 102289 (2024) https://doi.org/10.1016/j.ocemod.2023.102289

    Zhang, W., Sun, Y., Wu, Y., Dong, J., Song, X., Gao, Z., Pang, R., Guoan, B.: A deep-learning real-time bias correction method for significant wave height forecasts in the Western North Pacific. Ocean Modelling 187, 102289 (2024) https://doi.org/10.1016/j.ocemod.2023.102289

    work page doi:10.1016/j.ocemod.2023.102289 2024

  80. [82]

    Journal of Hydrology 629, 130621 (2024) https: //doi.org/10.1016/j.jhydrol.2024.130621

    Kao, Y.-C., Tsou, H.-E., Chen, C.-J.: Development of multi-source weighted- ensemble precipitation: Influence of bias correction based on recurrent con- volutional neural networks. Journal of Hydrology 629, 130621 (2024) https: //doi.org/10.1016/j.jhydrol.2024.130621

    work page doi:10.1016/j.jhydrol.2024.130621 2024

Showing first 80 references.