Predicting flood damage probability across the conterminous United States
Floods are the leading cause of natural disaster damages in the United States, with billions of dollars incurred every year in the form of government payouts, property damages, and agricultural losses. The Federal Emergency Management Agency oversees the delineation of floodplains to mitigate damage...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2022-01-01
|
| Series: | Environmental Research Letters |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/1748-9326/ac4f0f |
| _version_ | 1797747058370674688 |
|---|---|
| author | Elyssa L Collins Georgina M Sanchez Adam Terando Charles C Stillwell Helena Mitasova Antonia Sebastian Ross K Meentemeyer |
| author_facet | Elyssa L Collins Georgina M Sanchez Adam Terando Charles C Stillwell Helena Mitasova Antonia Sebastian Ross K Meentemeyer |
| author_sort | Elyssa L Collins |
| collection | DOAJ |
| description | Floods are the leading cause of natural disaster damages in the United States, with billions of dollars incurred every year in the form of government payouts, property damages, and agricultural losses. The Federal Emergency Management Agency oversees the delineation of floodplains to mitigate damages, but disparities exist between locations designated as high risk and where flood damages occur due to land use and climate changes and incomplete floodplain mapping. We harnessed publicly available geospatial datasets and random forest algorithms to analyze the spatial distribution and underlying drivers of flood damage probability (FDP) caused by excessive rainfall and overflowing water bodies across the conterminous United States. From this, we produced the first spatially complete map of FDP for the nation, along with spatially explicit standard errors for four selected cities. We trained models using the locations of historical reported flood damage events ( n = 71 434) and a suite of geospatial predictors (e.g. flood severity, climate, socio-economic exposure, topographic variables, soil properties, and hydrologic characteristics). We developed independent models for each hydrologic unit code level 2 watershed and generated a FDP for each 100 m pixel. Our model classified damage or no damage with an average area under the curve accuracy of 0.75; however, model performance varied by environmental conditions, with certain land cover classes (e.g. forest) resulting in higher error rates than others (e.g. wetlands). Our results identified FDP hotspots across multiple spatial and regional scales, with high probabilities common in both inland and coastal regions. The highest flood damage probabilities tended to be in areas of low elevation, in close proximity to streams, with extreme precipitation, and with high urban road density. Given rapid environmental changes, our study demonstrates an efficient approach for updating FDP estimates across the nation. |
| first_indexed | 2024-03-12T15:45:43Z |
| format | Article |
| id | doaj.art-1a49baeb09a44c1da25644710553a29b |
| institution | Directory Open Access Journal |
| issn | 1748-9326 |
| language | English |
| last_indexed | 2024-03-12T15:45:43Z |
| publishDate | 2022-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Environmental Research Letters |
| spelling | doaj.art-1a49baeb09a44c1da25644710553a29b2023-08-09T15:26:23ZengIOP PublishingEnvironmental Research Letters1748-93262022-01-0117303400610.1088/1748-9326/ac4f0fPredicting flood damage probability across the conterminous United StatesElyssa L Collins0https://orcid.org/0000-0002-8054-8468Georgina M Sanchez1https://orcid.org/0000-0002-2365-6200Adam Terando2https://orcid.org/0000-0002-9280-043XCharles C Stillwell3https://orcid.org/0000-0002-4571-4897Helena Mitasova4https://orcid.org/0000-0002-6906-3398Antonia Sebastian5https://orcid.org/0000-0002-4309-2561Ross K Meentemeyer6https://orcid.org/0000-0002-1247-6212Center for Geospatial Analytics, North Carolina State University , Raleigh, NC, United States of AmericaCenter for Geospatial Analytics, North Carolina State University , Raleigh, NC, United States of AmericaCenter for Geospatial Analytics, North Carolina State University , Raleigh, NC, United States of America; U.S. Geological Survey, Southeast Climate Adaptation Science Center , Raleigh, NC, United States of America; Department of Applied Ecology, North Carolina State University , Raleigh, NC, United States of AmericaU.S. Geological Survey, South Atlantic Water Science Center , Raleigh, NC, United States of AmericaCenter for Geospatial Analytics, North Carolina State University , Raleigh, NC, United States of America; Department of Marine, Earth and Atmospheric Sciences, North Carolina State University , Raleigh, NC, United States of AmericaDepartment of Earth, Marine and Environmental Sciences, University of North Carolina at Chapel Hill , Chapel Hill, NC, United States of AmericaCenter for Geospatial Analytics, North Carolina State University , Raleigh, NC, United States of America; Department of Forestry and Environmental Resources, North Carolina State University , Raleigh, NC, United States of AmericaFloods are the leading cause of natural disaster damages in the United States, with billions of dollars incurred every year in the form of government payouts, property damages, and agricultural losses. The Federal Emergency Management Agency oversees the delineation of floodplains to mitigate damages, but disparities exist between locations designated as high risk and where flood damages occur due to land use and climate changes and incomplete floodplain mapping. We harnessed publicly available geospatial datasets and random forest algorithms to analyze the spatial distribution and underlying drivers of flood damage probability (FDP) caused by excessive rainfall and overflowing water bodies across the conterminous United States. From this, we produced the first spatially complete map of FDP for the nation, along with spatially explicit standard errors for four selected cities. We trained models using the locations of historical reported flood damage events ( n = 71 434) and a suite of geospatial predictors (e.g. flood severity, climate, socio-economic exposure, topographic variables, soil properties, and hydrologic characteristics). We developed independent models for each hydrologic unit code level 2 watershed and generated a FDP for each 100 m pixel. Our model classified damage or no damage with an average area under the curve accuracy of 0.75; however, model performance varied by environmental conditions, with certain land cover classes (e.g. forest) resulting in higher error rates than others (e.g. wetlands). Our results identified FDP hotspots across multiple spatial and regional scales, with high probabilities common in both inland and coastal regions. The highest flood damage probabilities tended to be in areas of low elevation, in close proximity to streams, with extreme precipitation, and with high urban road density. Given rapid environmental changes, our study demonstrates an efficient approach for updating FDP estimates across the nation.https://doi.org/10.1088/1748-9326/ac4f0fflood damagehazardsmachine learningrandom forestCONUSgeospatial |
| spellingShingle | Elyssa L Collins Georgina M Sanchez Adam Terando Charles C Stillwell Helena Mitasova Antonia Sebastian Ross K Meentemeyer Predicting flood damage probability across the conterminous United States Environmental Research Letters flood damage hazards machine learning random forest CONUS geospatial |
| title | Predicting flood damage probability across the conterminous United States |
| title_full | Predicting flood damage probability across the conterminous United States |
| title_fullStr | Predicting flood damage probability across the conterminous United States |
| title_full_unstemmed | Predicting flood damage probability across the conterminous United States |
| title_short | Predicting flood damage probability across the conterminous United States |
| title_sort | predicting flood damage probability across the conterminous united states |
| topic | flood damage hazards machine learning random forest CONUS geospatial |
| url | https://doi.org/10.1088/1748-9326/ac4f0f |
| work_keys_str_mv | AT elyssalcollins predictingflooddamageprobabilityacrosstheconterminousunitedstates AT georginamsanchez predictingflooddamageprobabilityacrosstheconterminousunitedstates AT adamterando predictingflooddamageprobabilityacrosstheconterminousunitedstates AT charlescstillwell predictingflooddamageprobabilityacrosstheconterminousunitedstates AT helenamitasova predictingflooddamageprobabilityacrosstheconterminousunitedstates AT antoniasebastian predictingflooddamageprobabilityacrosstheconterminousunitedstates AT rosskmeentemeyer predictingflooddamageprobabilityacrosstheconterminousunitedstates |