Delineating flood prone areas using a statistical approach
- Published
- Accepted
- Subject Areas
- Data Mining and Machine Learning, Spatial and Geographic Information Systems
- Keywords
- Flood, DEM, Machine Learning Algorithm, Zonation, Statistical model, Hazard
- Copyright
- © 2016 Marchesini et al.
- Licence
- This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Preprints) and either DOI or URL of the article must be cited.
- Cite this article
- 2016. Delineating flood prone areas using a statistical approach. PeerJ Preprints 4:e1937v2 https://doi.org/10.7287/peerj.preprints.1937v2
Abstract
Floods are frequent and widespread in Italy and pose a severe risk for the population. Local administrations commonly use flow propagation models to delineate the flood prone areas. These modeling approaches require a detail geo-environmental data knowledge, intensive calculation and long computational times. Conversely, statistical methods can be used to asses flood hazard over large areas, or to extend the flood hazard zonation to the portion of the river networks where hydraulic models have still not been applied or can be applied with difficulties. In this paper, we describe a statistical approach to prepare flood hazard maps for the whole of Italy. The proposed method is based on a multivariate machine learning algorithm calibrated using in input flood hazard maps delineated by the local authorities and terrain elevation data. The preliminary results obtained in several major Italian catchments indicate good performances of the statistical algorithm in matching the training data. Results are promising giving the possibility to obtain reliable delineations of flood prone areas obtained in the rest of the Italian territory.
Author Comment
This version of the document has been formatted according to the OGRS2016 template.
Supplemental Information
Boundaries of the Italian River Basin Authorities
Boundaries of the Italian River Basin Authorities (RBAs). Red shows catchments considered in this study.
Logical framework and algorithm
Logical framework and algorithm adopted for the production of Logistic Regression classification models for flood hazard zonation, and the preparation of the modeled, statistically based binary FHMs for selected areas in Italy.
Comparison of FHMS
Comparison of FHMS produced by River Basin Authorities and prepared in this study using a statistically-based zonation