干旱区生态环境知识资源中心(Arid): Development of a spatially complete floodplain map of the conterminous United States using random forest

Arid

DOI	10.1016/j.scitotenv.2018.07.353
	Development of a spatially complete floodplain map of the conterminous United States using random forest
	Woznicki, Sean A.1; Baynes, Jeremy 1; Panlasigui, Stephanie 2,3; Mehaffey, Megan 1; Neale, Anne 1
通讯作者	Woznicki, Sean A.
来源期刊	SCIENCE OF THE TOTAL ENVIRONMENT
ISSN	0048-9697
EISSN	1879-1026
出版年	2019
卷号	647 页码:942-953
英文摘要	Floodplains perform several important ecosystem services, including storing water during precipitation events and reducing peak flows, thus reducing flooding of downstream communities. Understanding the relationship between flood inundation and floodplains is critical for ecosystem and community health and well-being, as well as targeting floodplain and riparian restoration. Many communities in the United States, particularly those in rural areas, lack in-undation maps due to the high cost of flood modeling. Only 60% of the conterminous United States has Flood Insurance Rate Maps (FIRMs) through the U.S. Federal Emergency Management Agency (FEMA). We developed a 30-meter resolution flood inundation map of the conterminous United States (CONUS) using random forest classification to fill the gaps in the FIRM. Input datasets included digital elevation model (DEM)-derived variables, flood-related soil characteristics, and land cover. The existing FIRM 100-year floodplains, called the Special Flood Hazard Area (SHFA), were used to train and test the random forests for fluvial and coastal flooding. Models were developed for each hydrologic unit code level four (HUC-4) watershed and each 30-meter pixel in the CONUS was classified as floodplain or non-floodplain. The most important variables were DEM-derivatives and flood-based soil characteristics. Models captured 79% of the SFHA in the CONUS. The overall F1 score, which balances precision and recall, was 0.78. Performance varied geographically, exceeding the CONUS scores in temperate and coastal watersheds but were less robust in the arid southwest. The models also consistently identified headwater floodplains not present in the SFHA, lowering performance measures but providing critical information missing in many low-order stream systems. The performance of the random forest models demonstrates the method's ability to successfully fill in the remaining unmapped floodplains in the CONUS, while using only publicly available data and open source software. Published by Elsevier B.V.
英文关键词	CONUS Ecosystem services EnviroAtlas Flood Geographic information systems Machine learning
类型	Article
语种	英语
国家	USA
开放获取类型	hybrid, Green Accepted
收录类别	SCI-E
WOS记录号	WOS:000447090400095
WOS关键词	SUPPORT VECTOR MACHINE ; SUSCEPTIBILITY ASSESSMENT ; NATIONAL SCALE ; DECISION TREE ; MODELS ; AREAS ; RECONNECTION ; PREDICTION ; BIVARIATE ; SERVICES
WOS类目	Environmental Sciences
WOS研究方向	Environmental Sciences & Ecology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/218582
作者单位	1.US EPA, Natl Exposure Res Lab, Res Triangle Pk, NC 27711 USA; 2.US EPA, Oak Ridge Inst Sci & Educ Res Participant Program, Res Triangle Pk, NC 27711 USA; 3.Eno River Assoc, 4404 Guess Rd, Durham, NC 27712 USA
推荐引用方式 GB/T 7714	Woznicki, Sean A.,Baynes, Jeremy,Panlasigui, Stephanie,et al. Development of a spatially complete floodplain map of the conterminous United States using random forest[J],2019,647:942-953.
APA	Woznicki, Sean A.,Baynes, Jeremy,Panlasigui, Stephanie,Mehaffey, Megan,&Neale, Anne.(2019).Development of a spatially complete floodplain map of the conterminous United States using random forest.SCIENCE OF THE TOTAL ENVIRONMENT,647,942-953.
MLA	Woznicki, Sean A.,et al."Development of a spatially complete floodplain map of the conterminous United States using random forest".SCIENCE OF THE TOTAL ENVIRONMENT 647(2019):942-953.