[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128054-en":3,"doc-seo-128054-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128054,5909887256941,"Levi","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Robust storm surge forecasts for early warning system - a machine learning approach using Monte Carlo Bayesian model selection algorithm","Machine-learning methods are increasingly used to predict storm surges and support coastal flood early warning systems, where forecast uncertainty must be handled explicitly. Uncertainty can arise from imperfect model inputs and from intrinsic model limitations, making prediction intervals and the validity range essential. This work proposes a robust forecasting methodology that propagates input uncertainty via a Monte Carlo approach through an adaptive Bayesian model selection framework using artificial neural networks. The approach targets 24-hour surge forecasts for Millport and improves predictive performance while producing meaningful intervals that reflect feature, model, and forecast uncertainty.","Stochastic Environmental Research and Risk Assessment (2025) 39:2789–2816  \n[https://doi.org/10.1007/s00477-025-02993-3](https://doi.org/10.1007/s00477-025-02993-3)  \nORIGINAL PAPER  \nRobust storm surge forecasts for early warning system: a machine learning approach using Monte Carlo Bayesian model selection algorithm  \nE. Macdonald1 · E. Tubaldi1 · E. Patelli1  \nAccepted: 12 April 2025 / Published online: 7 May 2025 © The Author(s) 2025  \nAbstract  \nMachine-learning based methods are increasingly employed for the prediction of storm surges and development of early warning systems for coastal flooding. The evaluation of the quality of such methods needs to explicitly consider the uncertainty of the prediction, which may stem from the inaccuracy in the forecasted inputs to the model as well as from the uncertainty inherent to the model itself. Defining the range of validity of the prediction is essential for the correct application of such models. A methodology is proposed for building a robust model for forecasting storm surges accounting for the relevant sources of uncertainty. The model uses as inputs the mean sea level pressure and wind velocity components at 10 m above sea level. A set of Artificial Neural Networks are used in conjunction with an adaptive Bayesian model selection process to make robust storm surge forecast predictions with associated prediction intervals. The input uncertainty, characterised by comparing hindcast data and one day forecasted data, is propagated through the model via a Monte Carlo based approach. The application of the proposed methodology is illustrated by considering 24 h target forecast predictions of storm surges for Millport, in the Firth of Clyde, Scotland, UK. It is shown that the proposed approach significantly improves the predictive performance of existing machine learning based models and provides a meaningful prediction interval that characterises feature, model and forecast uncertainty. The forecast system has negligible computational time requirements and showed very good agreement with observations acccording different metrics and achieving e.g., a correlation coefficient of 0.942 for 24 h forecasted surge from 2021 to 2023. The mean absolute error was 0.06 m for all observations and only 0.10 m for observations above 0.75 m showing its accuracy for predicting extreme events.  \n1 Introduction  \nCoastal flooding is one of the most pressing effects of climate change, with a growing body of research and evidence suggesting that the problem is likely to worsen in the coming years. The Intergovernmental Panel on Climate Change has projected that global mean sea level will rise by 0.43 to 0.84 m by the end of this century, depending on future  \n􀀍 E. Patelli [edoardo.patelli@strath.ac.uk](edoardo.patelli@strath.ac.uk)  \nE. Macdonald [euan.macdonald@strath.ac.uk](euan.macdonald@strath.ac.uk)  \nE. Tubaldi [enrico.tubaldi@strath.ac.uk](enrico.tubaldi@strath.ac.uk)  \n1 Department of Civil and Environmental Engineering, University of Strathclyde, Glasgow, Scotland  \nemissions scenarios (IPCC 2022). As sea levels rise, the risk of coastal flooding increases, as higher sea levels will most likely result in more frequent and severe flooding events (Nicholls et al. 2018) . Climate change is also contributing to more intense and frequent storms, see e.g. (Knutson 2010) . These storms can produce surges, which contribute to coastal flooding (Emanuel 2017) . In addition, warmer oceans are providing more energy to fuel these storms, making them more dangerous and unpredictable (IPCC 2022) . Addressing the above problems requires investment in measures to protect vulnerable coastal communities. There is also an urgent need for robust early warning tools that are capable of forecasting extreme surge events with sufficient lead time so that preventive risk-mitigation and emergencymanagement measures can be taken. Accurately forecasting storm surge events is difficult owing to abrupt variations in th","cbCaiatXyDGgB7sF","https://ap.wps.com/l/cbCaiatXyDGgB7sF","pdf",4579414,4,1,28,"English","en",105,"# Abstract\n# Introduction\n## Motivation from climate change and coastal flooding risk\n## Challenges in accurate storm surge forecasting\n## Existing modelling approaches and uncertainty considerations\n# Proposed methodology (robust forecasting with uncertainty quantification)\n# Application and results for Millport (24 h forecasts)\n# Conclusion","[{\"question\":\"Why is uncertainty considered essential in storm surge forecasting for early warning systems?\",\"answer\":\"Uncertainty affects both the forecast inputs to the model and the model’s own limitations, so prediction intervals and the range of validity are needed to apply results correctly.\"},{\"question\":\"What model inputs does the proposed approach use?\",\"answer\":\"The method uses mean sea level pressure and wind velocity components at 10 m above sea level.\"},{\"question\":\"How does the approach account for input uncertainty and generate robust predictions?\",\"answer\":\"Input uncertainty is characterized by comparing hindcast data with one-day forecasted data, then propagated through the model using a Monte Carlo based approach combined with adaptive Bayesian model selection with artificial neural networks.\"}]","Robust storm surge forecasts for early warning system - a machine learning approach using Monte Carlo Bayesian model selection algorithm | PDF",1785944511,71,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"robust-storm-surge-forecasts-for-early-warning-system-a-machine-learning-approach-using-monte-carlo-bayesian-model-selection-algorithm","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/robust-storm-surge-forecasts-for-early-warning-system-a-machine-learning-approach-using-monte-carlo-bayesian-model-selection-algorithm/128054/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-26","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is uncertainty considered essential in storm surge forecasting for early warning systems?","Question",{"text":76,"@type":77},"Uncertainty affects both the forecast inputs to the model and the model’s own limitations, so prediction intervals and the range of validity are needed to apply results correctly.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What model inputs does the proposed approach use?",{"text":81,"@type":77},"The method uses mean sea level pressure and wind velocity components at 10 m above sea level.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the approach account for input uncertainty and generate robust predictions?",{"text":85,"@type":77},"Input uncertainty is characterized by comparing hindcast data with one-day forecasted data, then propagated through the model using a Monte Carlo based approach combined with adaptive Bayesian model selection with artificial neural networks.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]