A step toward considering the return period in flood spatial modeling

Bahram Choubin (), Farzaneh Sajedi Hosseini, Omid Rahmati and Mansor Mehdizadeh Youshanloei
Additional contact information
Bahram Choubin: AREEO
Farzaneh Sajedi Hosseini: University of Tehran
Omid Rahmati: AREEO
Mansor Mehdizadeh Youshanloei: AREEO

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, 2023, vol. 115, issue 1, No 17, 460 pages

Abstract: Abstract In recent years, there has been an increasing interest in spatial modeling, and flood hazard prediction is a major area of interest within the field of hydrology. It is necessary to consider return periods for identifying the flood hazard zones. In hydraulic modeling such as HEC-RAS, this is usually done, but in spatial modeling by machine learning (ML) models, this has not been taken into account so far. This study seeks to obtain data that will help to address this research gap. The Sentinel-1 Radar images have been used for identifying the flooded locations in different return periods. An embedded feature selection algorithm (i.e., recursive feature elimination random forest; RFE-RF) was used in the current research for key feature selection. Then, three ML models of neural networks using model averaging, classification and regression tree, and support vector machine were employed. The flood hazard prediction demonstrated a great performance for all the applied models (i.e., accuracy and precision > 90%, Kappa > 88%). Sensitivity analysis disclosed that the variables of elevation and distance from stream are in the first importance order, the variables of precipitation, slope, and land use are in the second importance order, and other variables are in the third importance order in all return periods. The modeling results indicated that among man-made land uses the irrigated area between 17.7 and 31.4%, dry farming from 0.5 to 2.4%, and residential areas between 8.3 and 25.1% are exposed to high and very high flood hazard areas. The current findings add to a growing body of literature on the spatial modeling of floods.

Keywords: Flood; Machine learning; Radar; Remote sensing; Return period; Embedded feature selection (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11069-022-05561-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:nathaz:v:115:y:2023:i:1:d:10.1007_s11069-022-05561-y

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11069

DOI: 10.1007/s11069-022-05561-y

Access Statistics for this article

Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards is currently edited by Thomas Glade, Tad S. Murty and Vladimír Schenk

More articles in Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards from Springer, International Society for the Prevention and Mitigation of Natural Hazards
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().