Articles | Volume 21, issue 2
Research article
16 Feb 2021
Research article |  | 16 Feb 2021

Are OpenStreetMap building data useful for flood vulnerability modelling?

Marco Cerri, Max Steinhausen, Heidi Kreibich, and Kai Schröter

Data sets

Reshaping Data with the reshape Package H. Wickham

gdalUtilities: Wrappers for ``GDAL'' Utilities Executables J. O'Brien

rpostgis: linking R with a PostGIS spatial database D. Bucklin and M. Basille

rgdal: Bindings for the ``Geospatial'' Data Abstraction Librar R. Bivand, T. Keitt, and B. Rowlingson

raster: Geographic Data Analysis and Modeling R. J. Hijmans

RPostgreSQL: R Interface to the ``PostgreSQL'' Database System J. Conway, D. Eddelbuettel, T. Nishiyama, S. K. Prayaga, and N. Tiffin

Welcome to the tidyverse H. Wickham, M. Averick, J. Bryan, W. Chang, L. D. McGowan, R. François, G. Grolemund, A. Hayes, L. Henry, J. Hester, M. Kuhn, T. L. Pedersen, E. Miller, S. M. Bache, K. Müller, J. Ooms, D. Robinson, D. P. Seidel, V. Spinu, K. Takahashi, D. Vaughan, C. Wilke, K. Woo, and H. Yutani

Classification and Regression by randomForest A. Liaw and M. Wiener

Short summary
Effective flood management requires information about the potential consequences of flooding. We show how openly accessible data from OpenStreetMap can support the estimation of flood damage for residential buildings. Working with methods of machine learning, the building geometry is used to predict flood damage in combination with information about inundation depth. Our approach makes it easier to transfer models to regions where no detailed data of flood impacts have been observed yet.
Final-revised paper