A glimpse into the future of exposure and vulnerabilities in cities? Modelling of residential location choice of urban population with random forest

Abstract. The most common approach to assessing natural hazard risk is investigating the willingness pay in presence or absence of such risk. In this work, we propose a new, machine-learning-based, indirect problem, i.e. through residential-choice modelling. Especially urban environments, exposure and vulnerability are highly dynamic components, both being shaped by complex continuous reorganization redistribution assets within space, including (re-)location dwellers. By modelling behaviour city Leipzig, Germany, seek examine how vulnerabilities residential-location-choice process. proposed reveals hot spots cold residential choice for distinct socioeconomic groups exhibiting heterogeneous preferences. We discuss relationship between observed patterns disaster lens vulnerability, as well links planning, explore methodology may contribute predicting future trends exposure, analytical focus. Avenues research include operational strengthening these linkages more effective management.