{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:52:48Z","timestamp":1771951968377,"version":"3.50.1"},"reference-count":45,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T00:00:00Z","timestamp":1754956800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Appl. Math. Stat."],"abstract":"<jats:p>Accurate disaster prediction combined with reliable uncertainty quantification is crucial for timely and effective decision-making in emergency management. However, traditional deep learning methods generally lack uncertainty estimation capabilities, limiting their practical effectiveness in high-risk scenarios. To overcome these limitations, this study proposes an enhanced Bayesian Deep Neural Network (BDNN) tailored for flood forecasting, effectively integrating Variational Inference (VI), Monte Carlo (MC) Dropout, and a Hierarchical Attention Mechanism. By leveraging hydrological and meteorological data from the Yellow River basin (2001\u20132023), the BDNN model not only achieves superior prediction accuracy (94.6%) but also significantly enhances reliability through robust uncertainty quantification. Comparative analyses demonstrate that the proposed approach markedly outperforms conventional models such as Random Forest, XGBoost, and Multi-layer Perceptron. Ablation studies further confirm the critical role of the hierarchical attention mechanism in capturing essential features, while VI and MC Dropout substantially improve prediction reliability. These advancements highlight the potential of BDNNs to significantly enhance disaster preparedness and support more informed emergency response decisions in complex, uncertain environments.<\/jats:p>","DOI":"10.3389\/fams.2025.1653562","type":"journal-article","created":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T05:32:09Z","timestamp":1754976729000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Enhancing disaster prediction with Bayesian deep learning: a robust approach for uncertainty estimation"],"prefix":"10.3389","volume":"11","author":[{"given":"Hao","family":"Peng","sequence":"first","affiliation":[]},{"given":"Sen","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Haichao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Fei","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Fawang","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Ruige","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,8,12]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"4014","DOI":"10.3390\/app15074014","article-title":"Comparative analysis of target displacements in RC Buildings for 2023 T\u00fcrkiye earthquakes","volume":"15","author":"I\u015f\u0131k","year":"2025","journal-title":"Appl Sci"},{"key":"B2","doi-asserted-by":"publisher","first-page":"8129","DOI":"10.3390\/app14188129","article-title":"Geospatial and temporal patterns of natural and man-made (technological) disasters (1900-2024): insights from different socio-economic and demographic perspectives","volume":"14","author":"Cvetkovi\u0107","year":"2024","journal-title":"Appl Sci"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1557","DOI":"10.1080\/1331677X.2018.1504689","article-title":"The impact of human development on natural disaster fatalities and damage: panel data evidence","volume":"31","author":"Padli","year":"2018","journal-title":"Econ Res-Ekonomska Istra\u017eivanja"},{"key":"B4","doi-asserted-by":"publisher","first-page":"102186","DOI":"10.1016\/j.ijdrr.2021.102186","article-title":"Human-induced or natural hazard? Factors influencing perceptions of actions to be taken in response to induced seismicity","volume":"57","author":"Tracy","year":"2021","journal-title":"Int J Disaster Risk Reduct"},{"key":"B5","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1007\/978-3-030-98989-7_2","article-title":"Early warning systems and their role in disaster risk reduction","volume-title":"Towards the \u201cPerfect\u201d Weather Warning: Bridging Disciplinary Gaps Through Partnership and Communication","author":"\u0160aki\u0107 Trogrli\u0107","year":"2022"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13643-019-1211-5","article-title":"Early warning system models and components in emergency and disaster: a systematic literature review protocol","volume":"8","author":"Khankeh","year":"2019","journal-title":"Syst Rev"},{"key":"B7","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1016\/j.techfore.2009.10.008","article-title":"The limits of forecasting methods in anticipating rare events","volume":"77","author":"Goodwin","year":"2010","journal-title":"Technol Forecast Soc Change"},{"key":"B8","doi-asserted-by":"publisher","first-page":"37","DOI":"10.3233\/RDA-150114","article-title":"Forecasting and uncertainty: a survey","volume":"6","author":"Makridakis","year":"2016","journal-title":"Risk and Decision Analysis"},{"key":"B9","doi-asserted-by":"publisher","first-page":"10543","DOI":"10.3390\/su151310543","article-title":"The state of the art in deep learning applications, challenges, and future prospects: a comprehensive review of flood forecasting and management","volume":"15","author":"Kumar","year":"2023","journal-title":"Sustainability"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1314","DOI":"10.3390\/w17091314","article-title":"Worldwide research progress and trends in application of machine learning to wastewater treatment: a bibliometric analysis","volume":"17","author":"Zhou","year":"2025","journal-title":"Water"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1431","DOI":"10.3390\/w17101431","article-title":"An explainable machine learning framework for forecasting lake water equivalent using satellite data: a 20-year analysis of the urmia lake basin","volume":"17","author":"Habibi","year":"2025","journal-title":"Water"},{"key":"B12","doi-asserted-by":"publisher","first-page":"e17689","DOI":"10.1016\/j.heliyon.2023.e17689","article-title":"Exploring machine learning algorithms for accurate water level forecasting in Muda river, Malaysia","volume":"9","author":"Zakaria","year":"2023","journal-title":"Heliyon"},{"key":"B13","doi-asserted-by":"publisher","first-page":"2762","DOI":"10.1038\/s41598-025-87187-1","article-title":"Enhanced streamflow forecasting using hybrid modelling integrating glacio-hydrological outputs, deep learning and wavelet transformation","volume":"15","author":"Ougahi","year":"2025","journal-title":"Sci Rep"},{"key":"B14","doi-asserted-by":"publisher","first-page":"4491","DOI":"10.3390\/app15084491","article-title":"Spatio-temporal deformation prediction of large landslides in the three gorges reservoir area based on time-series graph convolutional network model","volume":"15","author":"Ma","year":"2025","journal-title":"Appl Sci"},{"key":"B15","doi-asserted-by":"publisher","first-page":"123369","DOI":"10.1109\/ACCESS.2019.2963045","article-title":"Short-term prediction of residential power energy consumption via CNN and multi-layer bi-directional LSTM networks","volume":"8","author":"Ullah","year":"2019","journal-title":"IEEE Access"},{"key":"B16","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1016\/j.jhydrol.2018.11.069","article-title":"An enhanced extreme learning machine model for river flow forecasting: state-of-the-art, practical applications in water resource engineering area and future research direction","volume":"569","author":"Yaseen","year":"2019","journal-title":"J Hydrol"},{"key":"B17","first-page":"259","article-title":"Flood flow prediction based on combined CNN-GRU-XGBoost model","volume-title":"IEEE International Conference on Electronic Technology, Communication and Information","author":"Fan","year":"2023"},{"key":"B18","doi-asserted-by":"publisher","first-page":"3192","DOI":"10.3390\/w16223192","article-title":"Multiple types of missing precipitation data filling based on ensemble artificial intelligence models","volume":"16","author":"Qiu","year":"2024","journal-title":"Water"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1475","DOI":"10.3390\/w17101475","article-title":"Seasonal precipitation and anomaly analysis in middle east Asian countries using google earth engine","volume":"17","author":"Radwan","year":"2025","journal-title":"Water"},{"key":"B20","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","article-title":"A review of uncertainty quantification in deep learning: techniques, applications and challenges","volume":"76","author":"Abdar","year":"2021","journal-title":"Inf Fusion"},{"key":"B21","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1038\/s41558-019-0639-x","article-title":"The potential to reduce uncertainty in regional runoff projections from climate models","volume":"9","author":"Lehner","year":"2019","journal-title":"Nat Clim Chang"},{"key":"B22","doi-asserted-by":"publisher","first-page":"961954","DOI":"10.3389\/frwa.2022.961954","article-title":"A review of machine learning concepts and methods for addressing challenges in probabilistic hydrological post-processing and forecasting","volume":"4","author":"Papacharalampous","year":"2022","journal-title":"Front Water"},{"key":"B23","doi-asserted-by":"publisher","first-page":"125206","DOI":"10.1016\/j.jhydrol.2020.125206","article-title":"physical process and machine learning combined hydrological model for daily streamflow simulations of large watersheds with limited observation data","volume":"590","author":"Yang","year":"2020","journal-title":"J Hydrol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"127297","DOI":"10.1016\/j.jhydrol.2021.127297","article-title":"Improving streamflow prediction in the WRF-Hydro model with LSTM networks","volume":"605","author":"Cho","year":"2022","journal-title":"J Hydrol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5194\/hess-2024-393","article-title":"Deep learning of flood forecasting by considering interpretability and physical constraints","volume":"2025","author":"Zhang","year":"2025","journal-title":"Hydrol Earth Syst Sci Discuss"},{"key":"B26","doi-asserted-by":"publisher","first-page":"446","DOI":"10.3390\/make4020020","article-title":"Machine learning in disaster management: recent developments in methods and applications","volume":"4","author":"Linardos","year":"2022","journal-title":"Mach Learn Knowl Extraction"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1536","DOI":"10.3390\/w10111536","article-title":"Flood prediction using machine learning models: literature review","volume":"10","author":"Mosavi","year":"2018","journal-title":"Water"},{"key":"B28","doi-asserted-by":"publisher","first-page":"2835","DOI":"10.1007\/s12205-020-1677-7","article-title":"Real-time flood disaster prediction system by applying machine learning technique","volume":"24","author":"Keum","year":"2020","journal-title":"KSCE J Civ Eng"},{"key":"B29","doi-asserted-by":"publisher","first-page":"105436","DOI":"10.1016\/j.envsoft.2022.105436","article-title":"Coupling machine learning and weather forecast to predict farmland flood disaster: a case study in Yangtze River basin","volume":"155","author":"Jiang","year":"2022","journal-title":"Environ Modell Softw"},{"key":"B30","doi-asserted-by":"publisher","first-page":"128086","DOI":"10.1016\/j.jhydrol.2022.128086","article-title":"Spatial-temporal flood inundation nowcasts by fusing machine learning methods and principal component analysis","volume":"612","author":"Chang","year":"2022","journal-title":"J Hydrol"},{"key":"B31","doi-asserted-by":"publisher","first-page":"3117","DOI":"10.3390\/app15063117","article-title":"Seasonal pollution levels and heavy metal contamination in the Jukskei River, South Africa","volume":"15","author":"Mukwevho","year":"2025","journal-title":"Appl Sci"},{"key":"B32","doi-asserted-by":"publisher","first-page":"112810","DOI":"10.1016\/j.jenvman.2021.112810","article-title":"Towards better flood risk management: assessing flood risk and investigating the potential mechanism based on machine learning models","volume":"293","author":"Chen","year":"2021","journal-title":"J Environ Manage"},{"key":"B33","doi-asserted-by":"publisher","first-page":"e12671","DOI":"10.1111\/jfr3.12671","article-title":"Mapping the risk zoning of storm flood disaster based on heterogeneous data and a machine learning algorithm in Xinjiang, China","volume":"14","author":"Liu","year":"2021","journal-title":"J Flood Risk Manag"},{"key":"B34","doi-asserted-by":"publisher","first-page":"101075","DOI":"10.1016\/j.gsf.2020.09.006","article-title":"Flood susceptibility modelling using advanced ensemble machine learning models","volume":"12","author":"Islam","year":"2021","journal-title":"Geosci Front"},{"key":"B35","doi-asserted-by":"publisher","first-page":"102154","DOI":"10.1016\/j.ijdrr.2021.102154","article-title":"A mixed approach for urban flood prediction using Machine Learning and GIS","volume":"56","author":"Motta","year":"2021","journal-title":"Int J Disaster Risk Reduct"},{"key":"B36","doi-asserted-by":"publisher","first-page":"127594","DOI":"10.1016\/j.jclepro.2021.127594","article-title":"Development of flood hazard map and emergency relief operation system using hydrodynamic modeling and machine learning algorithm","volume":"311","author":"Rahman","year":"2021","journal-title":"J Clean Prod"},{"key":"B37","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/j.ijdrr.2018.12.002","article-title":"A machine learning-based prediction and analysis of flood affected households: a case study of floods in Bangladesh","volume":"34","author":"Ganguly","year":"2019","journal-title":"Int J Disaster Risk Reduct"},{"key":"B38","doi-asserted-by":"publisher","first-page":"8431","DOI":"10.1007\/s00521-020-05487-1","article-title":"A novel emergency situation awareness machine learning approach to assess flood disaster risk based on Chinese Weibo","volume":"34","author":"Bai","year":"2022","journal-title":"Neural Comput Appl"},{"key":"B39","doi-asserted-by":"publisher","first-page":"13393","DOI":"10.1007\/s00500-019-03878-8","article-title":"Analysis of remote sensing imagery for disaster assessment using deep learning: a case study of flooding event","volume":"23","author":"Yang","year":"2019","journal-title":"Soft Comput"},{"key":"B40","doi-asserted-by":"publisher","first-page":"7249","DOI":"10.1038\/s41598-021-86650-z","article-title":"Towards global flood mapping onboard low cost satellites with machine learning","volume":"11","author":"Mateo-Garcia","year":"2021","journal-title":"Sci Rep"},{"key":"B41","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3390\/ijerph17010049","article-title":"A machine learning ensemble approach based on random forest and radial basis function neural network for risk evaluation of regional flood disaster: a case study of the Yangtze River Delta, China","volume":"17","author":"Chen","year":"2020","journal-title":"Int J Environ Res Public Health"},{"key":"B42","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.procs.2019.08.214","article-title":"Flood forecasting with machine learning technique on hydrological modeling","volume":"156","author":"Noymanee","year":"2019","journal-title":"Procedia Comput Sci"},{"key":"B43","article-title":"After the flood: a novel application of image processing and machine learning for post-flood disaster management","author":"Munawar","year":"2019","journal-title":"International Conference on Sustainable Development in Civil Engineering"},{"key":"B44","first-page":"1","article-title":"Advancing flood disaster mitigation in Indonesia using machine learning methods","volume-title":"International Conference on ICT for Smart Society","author":"Riza","year":"2020"},{"key":"B45","doi-asserted-by":"publisher","first-page":"4485","DOI":"10.1007\/s00477-024-02814-z","article-title":"Prediction of urban flood inundation using Bayesian convolutional neural networks","volume":"38","author":"Zheng","year":"2024","journal-title":"Stoch Environ Res Risk Assess"}],"container-title":["Frontiers in Applied Mathematics and Statistics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2025.1653562\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,12]],"date-time":"2025-08-12T05:32:10Z","timestamp":1754976730000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fams.2025.1653562\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,12]]},"references-count":45,"alternative-id":["10.3389\/fams.2025.1653562"],"URL":"https:\/\/doi.org\/10.3389\/fams.2025.1653562","relation":{},"ISSN":["2297-4687"],"issn-type":[{"value":"2297-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,12]]},"article-number":"1653562"}}