Abstract
Compound natural hazards like El Niño events cause high damage to society, which to manage requires reliable risk assessments. Damage modelling is a prerequisite for quantitative risk estimations, yet many procedures still rely on expert knowledge, and empirical studies investigating damage from compound natural hazards hardly exist. A nationwide building survey in Peru after the El Niño event 2017 – which caused intense rainfall, ponding water, flash floods and landslides – enables us to apply data-mining methods for statistical groundwork, using explanatory features generated from remote sensing products and open data. We separate regions of different dominant characteristics through unsupervised clustering, and investigate feature importance rankings for classifying damage via supervised machine learning. Besides the expected effect of precipitation, the classification algorithms select the topographic wetness index as most important feature, especially in low elevation areas. The slope length and steepness factor ranks high for mountains and canyons. Partial dependence plots further hint at amplified vulnerability in rural areas. An example of an empirical damage probability map, developed with a random forest model, is provided to demonstrate the technical feasibility.
Highlights
El Nin~o events are compound events, comprising torrential rainfall, fluvial and flash floods, mudslides, and other processes difficult to disentangle
Google Earth Engine pixels in Bare Soil Index (BSI)), holes were interpolated by GDAL.fillnodata – this should not have any effect on the results presented here, except for the classified map, since the statistical analysis in this paper is based on extracted points at the location of buildings, not on the entire rasters
This study has demonstrated how a research question from the natural hazard risk domain can be formulated as data-mining problem, and the potential of machine learning (ML) methods in combination with open geodata, to identify drivers of observed building damage from a compound El Nin~o event
Summary
El Nin~o events are compound events, comprising torrential rainfall, fluvial and flash floods, mudslides, and other processes difficult to disentangle. Relevant for society is the total damage resulting from consecutive or cascading hazards during several months. Modelling studies and measurements still do not provide a clear image about the effect of climate change on the El Nin~o Southern Oscillation, but the general expectation is that more extreme states will occur more frequently
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call