Pub Date : 2024-12-31DOI: 10.1038/s44304-024-00050-7
Maria Shahgedanova, Zarina Saidaliyeva, Ainur Mussina, Vassily Kapitsa, Zhanar Raimbekova, Denis Donskikh, Daulet Kissebayev, Murat Kasenov, Maxim Petrov
Debris flows, caused by Glacier Lake Outburst Floods (GLOF) or extreme weather, threaten lives and infrastructure in the northern Tien Shan. A geo-referenced database of 458 debris flow events of different geneses was compiled for the region. Between 1887 and 2020, there were 55 GLOF events, all resulting in debris flow formation. Their frequency peaked in the 1970s and declined afterwards. These events were associated with high air temperatures but not heavy rainfall. Debris flows unrelated to GLOFs were documented in the central Ile Alatau for the 1931–2020 period. They were predominantly caused by short-duration intense rainfall (pluvial debris flows) and/or intense glaciers and snowmelt. The median rainfall intensity triggering pluvial debris flows was 22–28 mm/day, depending on the catchment. There was no long-term trend in the frequency of pluvial debris flows, but their formation is increasingly observed at higher elevations.
{"title":"Debris flows in the northern Tien Shan, Central Asia: regional database, meteorological triggers, and trends","authors":"Maria Shahgedanova, Zarina Saidaliyeva, Ainur Mussina, Vassily Kapitsa, Zhanar Raimbekova, Denis Donskikh, Daulet Kissebayev, Murat Kasenov, Maxim Petrov","doi":"10.1038/s44304-024-00050-7","DOIUrl":"10.1038/s44304-024-00050-7","url":null,"abstract":"Debris flows, caused by Glacier Lake Outburst Floods (GLOF) or extreme weather, threaten lives and infrastructure in the northern Tien Shan. A geo-referenced database of 458 debris flow events of different geneses was compiled for the region. Between 1887 and 2020, there were 55 GLOF events, all resulting in debris flow formation. Their frequency peaked in the 1970s and declined afterwards. These events were associated with high air temperatures but not heavy rainfall. Debris flows unrelated to GLOFs were documented in the central Ile Alatau for the 1931–2020 period. They were predominantly caused by short-duration intense rainfall (pluvial debris flows) and/or intense glaciers and snowmelt. The median rainfall intensity triggering pluvial debris flows was 22–28 mm/day, depending on the catchment. There was no long-term trend in the frequency of pluvial debris flows, but their formation is increasingly observed at higher elevations.","PeriodicalId":501712,"journal":{"name":"npj Natural Hazards","volume":" ","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2024-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44304-024-00050-7.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142906139","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-30DOI: 10.1038/s44304-024-00049-0
Alik Ismail-Zadeh
To answer the question of why seismic hazards turn into disasters, I provide here an overview of studies on the lithosphere dynamics, seismic hazard assessments, earthquake-triggered hazards, forecasting of large earthquakes, vulnerability and resilience assessments, and risk communication. Knowledge gaps in these fields are discussed. Integrated research on risks of earthquake-triggered disasters is essential in producing useful and usable knowledge for informed decision-making to reduce disaster risks.
{"title":"Earthquakes yes, disasters no","authors":"Alik Ismail-Zadeh","doi":"10.1038/s44304-024-00049-0","DOIUrl":"10.1038/s44304-024-00049-0","url":null,"abstract":"To answer the question of why seismic hazards turn into disasters, I provide here an overview of studies on the lithosphere dynamics, seismic hazard assessments, earthquake-triggered hazards, forecasting of large earthquakes, vulnerability and resilience assessments, and risk communication. Knowledge gaps in these fields are discussed. Integrated research on risks of earthquake-triggered disasters is essential in producing useful and usable knowledge for informed decision-making to reduce disaster risks.","PeriodicalId":501712,"journal":{"name":"npj Natural Hazards","volume":" ","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44304-024-00049-0.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142906130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Adaptation is critically important for coping with climate change. However, quantitative studies on which adaptation measures should be taken to maintain the present water risk level in the context of climate change have been explored little, particularly at large basin scales. Here, we devised three adaptation portfolios composed of combinations of measures to alleviate floods and drought with explicit basin-wide modelling in the Chao Phraya River basin, Thailand. Two portfolios mitigated future water scarcity to the present level but failed to eliminate extreme floods. The remaining portfolio with basin-wide reforestation substantially reduced the number of future flooding days but enhanced the number of drought months to 3–6 months a year, resulting from increased evapotranspiration by 7–11%. Overall, future flood adaptation remains challenging even in highly regulated rivers. We also observed that adaptation effects differ substantially by sub-basins. It highlights the necessity of spatio-temporal detailed impact modelling, including multiple adaptation measures.
{"title":"Adaptation portfolio – a multi-measure framework for future floods and droughts","authors":"Saritha Padiyedath Gopalan, Naota Hanasaki, Adisorn Champathong, Taikan Oki","doi":"10.1038/s44304-024-00048-1","DOIUrl":"10.1038/s44304-024-00048-1","url":null,"abstract":"Adaptation is critically important for coping with climate change. However, quantitative studies on which adaptation measures should be taken to maintain the present water risk level in the context of climate change have been explored little, particularly at large basin scales. Here, we devised three adaptation portfolios composed of combinations of measures to alleviate floods and drought with explicit basin-wide modelling in the Chao Phraya River basin, Thailand. Two portfolios mitigated future water scarcity to the present level but failed to eliminate extreme floods. The remaining portfolio with basin-wide reforestation substantially reduced the number of future flooding days but enhanced the number of drought months to 3–6 months a year, resulting from increased evapotranspiration by 7–11%. Overall, future flood adaptation remains challenging even in highly regulated rivers. We also observed that adaptation effects differ substantially by sub-basins. It highlights the necessity of spatio-temporal detailed impact modelling, including multiple adaptation measures.","PeriodicalId":501712,"journal":{"name":"npj Natural Hazards","volume":" ","pages":"1-13"},"PeriodicalIF":0.0,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44304-024-00048-1.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142906111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-30DOI: 10.1038/s44304-024-00052-5
Subhadarsini Das, John T. Allen
Large hail causes significant economic losses in the United States each year. Despite these impacts, hail is not typically included in building and infrastructure design standards, and assessments of hazards from extreme hail size remain limited. Here, we use a novel approach and multiple hail size datasets to develop a new Generalized Extreme Value model through a Bayesian framework to identify large hail-prone regions across the country at 0.25° × 0.25°. This model is smoothed using Gaussian process regression for nationwide estimation of return likelihood. To contextualize local risk, hazard returns intersecting high-population exposure centers are compared. Fitted extreme value models suggest earlier work likely underestimates the hail hazard. Especially for higher return periods, the Bayesian approach is found to better model very rare hail occurrences than traditional approaches. This provides a framework for appreciating underlying risk from hail and motivates mitigative approaches through improving design standards.
{"title":"Bayesian estimation of the likelihood of extreme hail sizes over the United States","authors":"Subhadarsini Das, John T. Allen","doi":"10.1038/s44304-024-00052-5","DOIUrl":"10.1038/s44304-024-00052-5","url":null,"abstract":"Large hail causes significant economic losses in the United States each year. Despite these impacts, hail is not typically included in building and infrastructure design standards, and assessments of hazards from extreme hail size remain limited. Here, we use a novel approach and multiple hail size datasets to develop a new Generalized Extreme Value model through a Bayesian framework to identify large hail-prone regions across the country at 0.25° × 0.25°. This model is smoothed using Gaussian process regression for nationwide estimation of return likelihood. To contextualize local risk, hazard returns intersecting high-population exposure centers are compared. Fitted extreme value models suggest earlier work likely underestimates the hail hazard. Especially for higher return periods, the Bayesian approach is found to better model very rare hail occurrences than traditional approaches. This provides a framework for appreciating underlying risk from hail and motivates mitigative approaches through improving design standards.","PeriodicalId":501712,"journal":{"name":"npj Natural Hazards","volume":" ","pages":"1-15"},"PeriodicalIF":0.0,"publicationDate":"2024-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44304-024-00052-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142906163","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-18DOI: 10.1038/s44304-024-00036-5
Clint Dawson, Mark Loveland, Benjamin Pachev, Jennifer Proft, Eirik Valseth
Flooding from storm surges, rainfall-runoff, and their interaction into compounding events are major natural hazards in coastal regions. To assess risks of damages to life and properties alike, numerical models are needed to guide emergency responses and future assessments. Numerical models, such as ADCIRC have over many decades shown their usefulness in such assessments. However, these models have a high threshold in terms of new user engagement as development and compilation is not trivial for users trained in compiled programming languages. Here, we develop a new open-source finite element solver for the numerical simulation of flooding. The numerical solution of the underlying PDEs is developed using the finite element framework FEniCSx. The goal is a framework where new methods can be rapidly tested before time-consuming development into codes like ADCIRC. We validate the framework on several test cases, including large-scale computations in the Gulf of Mexico for Hurricane Ike (2008).
{"title":"SWEMniCS: a software toolbox for modeling coastal ocean circulation, storm surges, inland, and compound flooding","authors":"Clint Dawson, Mark Loveland, Benjamin Pachev, Jennifer Proft, Eirik Valseth","doi":"10.1038/s44304-024-00036-5","DOIUrl":"10.1038/s44304-024-00036-5","url":null,"abstract":"Flooding from storm surges, rainfall-runoff, and their interaction into compounding events are major natural hazards in coastal regions. To assess risks of damages to life and properties alike, numerical models are needed to guide emergency responses and future assessments. Numerical models, such as ADCIRC have over many decades shown their usefulness in such assessments. However, these models have a high threshold in terms of new user engagement as development and compilation is not trivial for users trained in compiled programming languages. Here, we develop a new open-source finite element solver for the numerical simulation of flooding. The numerical solution of the underlying PDEs is developed using the finite element framework FEniCSx. The goal is a framework where new methods can be rapidly tested before time-consuming development into codes like ADCIRC. We validate the framework on several test cases, including large-scale computations in the Gulf of Mexico for Hurricane Ike (2008).","PeriodicalId":501712,"journal":{"name":"npj Natural Hazards","volume":" ","pages":"1-17"},"PeriodicalIF":0.0,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44304-024-00036-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-18DOI: 10.1038/s44304-024-00046-3
L. E. Grimley, K. E. Hollinger Beatty, A. Sebastian, S. Bunya, G. M. Lackmann
Tropical cyclones (TCs) generate substantial damage raising concerns about how climate change may amplify their impacts. However, linking changes in TC characteristics (wind, precipitation) to shifts in flood hazards and exposure, particularly due to the interaction of multiple drivers, is challenging. In this study, we use highly resolved physics-based models to investigate how flooding from three recent TCs in North and South Carolina would change under 4 degrees Celsius of warming. Runoff processes are the largest contributor to the total flood extent in both the present and future. However, the relative contribution of compound processes increases in the future, expanding upriver and beyond the floodplain where runoff processes previously occurred in isolation. The total area exposed to compound flooding increases by 65% and flood depths in these areas increase by 0.8 m highlighting the importance of simulating compound processes in TC flood exposure assessment.
{"title":"Climate change exacerbates compound flooding from recent tropical cyclones","authors":"L. E. Grimley, K. E. Hollinger Beatty, A. Sebastian, S. Bunya, G. M. Lackmann","doi":"10.1038/s44304-024-00046-3","DOIUrl":"10.1038/s44304-024-00046-3","url":null,"abstract":"Tropical cyclones (TCs) generate substantial damage raising concerns about how climate change may amplify their impacts. However, linking changes in TC characteristics (wind, precipitation) to shifts in flood hazards and exposure, particularly due to the interaction of multiple drivers, is challenging. In this study, we use highly resolved physics-based models to investigate how flooding from three recent TCs in North and South Carolina would change under 4 degrees Celsius of warming. Runoff processes are the largest contributor to the total flood extent in both the present and future. However, the relative contribution of compound processes increases in the future, expanding upriver and beyond the floodplain where runoff processes previously occurred in isolation. The total area exposed to compound flooding increases by 65% and flood depths in these areas increase by 0.8 m highlighting the importance of simulating compound processes in TC flood exposure assessment.","PeriodicalId":501712,"journal":{"name":"npj Natural Hazards","volume":" ","pages":"1-10"},"PeriodicalIF":0.0,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44304-024-00046-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-13DOI: 10.1038/s44304-024-00047-2
Yifan Yang, Chen Xie, Ziwu Fan, Zhonghou Xu, Bruce W. Melville, Guoqing Liu, Lei Hong
Digital twins are transforming the paradigm of water management and water hazard mitigation globally, facilitating more effective governance. However, comprehensive digitalisation at the basin scale still faces major challenges in data, modelling, policy incentives, and, most critically, widespread inequity. This article outlines a framework for building widely applicable digital-twin basins and addressing the main obstacles. Ensuring high-quality water data requires more comprehensive and well-controlled data aggregation and provision protocols. Significant improvements to the existing data infrastructure are necessary to support this effort. Most existing water models are not effectively integrated and do not include multi-physics to reflect all essential correlated physical processes at the basin scale. The current advancement in physics-informed data-driven approaches may provide a solution. Furthermore, global initiatives are critical to reducing major inequity in less developed regions, particularly the Global South, during digitalisation. It is imperative that researchers, practitioners and policymakers take decisive actions to prioritise research and allocate resources to foster transboundary collaborations towards integrated and extensive digital-twin basin systems, promoting the sustainability and resilience of global water resources.
{"title":"Digital twinning of river basins towards full-scale, sustainable and equitable water management and disaster mitigation","authors":"Yifan Yang, Chen Xie, Ziwu Fan, Zhonghou Xu, Bruce W. Melville, Guoqing Liu, Lei Hong","doi":"10.1038/s44304-024-00047-2","DOIUrl":"10.1038/s44304-024-00047-2","url":null,"abstract":"Digital twins are transforming the paradigm of water management and water hazard mitigation globally, facilitating more effective governance. However, comprehensive digitalisation at the basin scale still faces major challenges in data, modelling, policy incentives, and, most critically, widespread inequity. This article outlines a framework for building widely applicable digital-twin basins and addressing the main obstacles. Ensuring high-quality water data requires more comprehensive and well-controlled data aggregation and provision protocols. Significant improvements to the existing data infrastructure are necessary to support this effort. Most existing water models are not effectively integrated and do not include multi-physics to reflect all essential correlated physical processes at the basin scale. The current advancement in physics-informed data-driven approaches may provide a solution. Furthermore, global initiatives are critical to reducing major inequity in less developed regions, particularly the Global South, during digitalisation. It is imperative that researchers, practitioners and policymakers take decisive actions to prioritise research and allocate resources to foster transboundary collaborations towards integrated and extensive digital-twin basin systems, promoting the sustainability and resilience of global water resources.","PeriodicalId":501712,"journal":{"name":"npj Natural Hazards","volume":" ","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44304-024-00047-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142811345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-12DOI: 10.1038/s44304-024-00038-3
Shijie Liu, Hengxing Lan, Alexander Strom, Langping Li, Han Bao
Jiali Fault plays a key role in the dextral fault system in the southeastern Tibetan Plateau. Although it forms a striking topographic lineament the Yigong and Parlung Rivers, evidence for faulting in the Holocene has been equivocal. In this study, Holocene sediment deformation caused by the Jiali Fault was discovered in the debris flow fan near the Guxiang barrier lake. A palaeo-earthquake event that occurred between 3494 and 2865 cal B.P. was revealed, as evidenced by geological, seismic, and radiocarbon dating investigations. On the basis of a compilation of dating results, the middle segment of the Jiali Fault was proposed to belong to a Holocene active fault. This was attributed to the strong influence of the continued north eastwards compression of the Indian Plate and the clockwise rotation of the eastern Himalayan syntaxis. These findings provide new insights into the tectonic implications and earthquake activity of the southeastern Tibetan Plateau.
{"title":"Spatial segmentation of Jiali Fault’s Holocene activity in the southeastern Tibetan Plateau","authors":"Shijie Liu, Hengxing Lan, Alexander Strom, Langping Li, Han Bao","doi":"10.1038/s44304-024-00038-3","DOIUrl":"10.1038/s44304-024-00038-3","url":null,"abstract":"Jiali Fault plays a key role in the dextral fault system in the southeastern Tibetan Plateau. Although it forms a striking topographic lineament the Yigong and Parlung Rivers, evidence for faulting in the Holocene has been equivocal. In this study, Holocene sediment deformation caused by the Jiali Fault was discovered in the debris flow fan near the Guxiang barrier lake. A palaeo-earthquake event that occurred between 3494 and 2865 cal B.P. was revealed, as evidenced by geological, seismic, and radiocarbon dating investigations. On the basis of a compilation of dating results, the middle segment of the Jiali Fault was proposed to belong to a Holocene active fault. This was attributed to the strong influence of the continued north eastwards compression of the Indian Plate and the clockwise rotation of the eastern Himalayan syntaxis. These findings provide new insights into the tectonic implications and earthquake activity of the southeastern Tibetan Plateau.","PeriodicalId":501712,"journal":{"name":"npj Natural Hazards","volume":" ","pages":"1-12"},"PeriodicalIF":0.0,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44304-024-00038-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142811371","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-12-09DOI: 10.1038/s44304-024-00044-5
V. K. Krishnapriya, A. Rajaneesh, K. S. Sajinkumar, Thomas Oommen, Ali P. Yunus, Nikhil Nedumpallile Vasu, R. B. Binoj Kumar, S. Adarsh
The long run-out debris flows caused by oversaturated soil systems during the aggravated monsoon period in the Western Ghats raise questions about the hill community’s future. Here, we report the catastrophic long run-out Wayanad debris flow that occurred on 30th July 2024, which resulted in 231 fatalities and 128 people missing, and caused widespread destruction to infrastructure. This involved a maximum flow height of 10.66 m and maximum flow velocity of 18.7 m/s, simulated using RApid Mass Movement Simulation.
{"title":"A rapid run-out assessment methodology for the 2024 Wayanad debris flow","authors":"V. K. Krishnapriya, A. Rajaneesh, K. S. Sajinkumar, Thomas Oommen, Ali P. Yunus, Nikhil Nedumpallile Vasu, R. B. Binoj Kumar, S. Adarsh","doi":"10.1038/s44304-024-00044-5","DOIUrl":"10.1038/s44304-024-00044-5","url":null,"abstract":"The long run-out debris flows caused by oversaturated soil systems during the aggravated monsoon period in the Western Ghats raise questions about the hill community’s future. Here, we report the catastrophic long run-out Wayanad debris flow that occurred on 30th July 2024, which resulted in 231 fatalities and 128 people missing, and caused widespread destruction to infrastructure. This involved a maximum flow height of 10.66 m and maximum flow velocity of 18.7 m/s, simulated using RApid Mass Movement Simulation.","PeriodicalId":501712,"journal":{"name":"npj Natural Hazards","volume":" ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44304-024-00044-5.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142790467","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Machine learning (ML) models can simulate flood risk by identifying critical non-linear relationships between flood damage locations and flood risk factors (FRFs). To explore it, Tampa Bay, Florida, is selected as a test site. The study’s goal is to simulate flood risk and identify dominant FRFs using historical flood damage data as target variable, with 16 FRFs as predictor variables. Five different ML models such as decision tree (DT), support vector machine (SVM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and random forest (RF) were adopted. RF classifies 2.42% of Tampa Bay as very high risk and 2.54% as high risk, while XGBoost classifies 3.85% as very high risk and 1.11% as high risk. Moreover, the communities reside at low altitudes and near the waterbodies, with dense man-made infrastructure, are at high flood risk. This study introduces a comprehensive framework for flood risk assessment and helps policymakers mitigate flood risk.
{"title":"Simulating flood risk in Tampa Bay using a machine learning driven approach","authors":"Hemal Dey, Md Munjurul Haque, Wanyun Shao, Matthew VanDyke, Feng Hao","doi":"10.1038/s44304-024-00045-4","DOIUrl":"10.1038/s44304-024-00045-4","url":null,"abstract":"Machine learning (ML) models can simulate flood risk by identifying critical non-linear relationships between flood damage locations and flood risk factors (FRFs). To explore it, Tampa Bay, Florida, is selected as a test site. The study’s goal is to simulate flood risk and identify dominant FRFs using historical flood damage data as target variable, with 16 FRFs as predictor variables. Five different ML models such as decision tree (DT), support vector machine (SVM), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), and random forest (RF) were adopted. RF classifies 2.42% of Tampa Bay as very high risk and 2.54% as high risk, while XGBoost classifies 3.85% as very high risk and 1.11% as high risk. Moreover, the communities reside at low altitudes and near the waterbodies, with dense man-made infrastructure, are at high flood risk. This study introduces a comprehensive framework for flood risk assessment and helps policymakers mitigate flood risk.","PeriodicalId":501712,"journal":{"name":"npj Natural Hazards","volume":" ","pages":"1-16"},"PeriodicalIF":0.0,"publicationDate":"2024-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.nature.com/articles/s44304-024-00045-4.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142778629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：