Future exposure estimation with machine learning models

Kurzfassung

We anticipate geospatial population distributions to quantify the future number of people living in earthquake-prone and tsunami-prone areas of Lima, Peru. We capitalize upon existing gridded population time series data sets, which are provided on an open source basis globally, and implement machine learning models tailored for time series analysis, i.e., Long Short-Term Memory-based (LSTM) networks, for prediction of future time steps. In detail, we harvest WorldPop population data and learn LSTM and Convolutional LSTM models equipped with both unidirectional and bidirectional learning mechanisms and derived from different feature sets, i.e., driving factors. To gain insights regarding the competitive performance of LSTM-based models in this application context, we also implement multilinear regression and Random Forest models for comparison. The results clearly underline the usefulness of the LSTM-based models for forecasting gridded population data. The best model is deployed for anticipation of population along a three-year interval until the year 2035. Especially in areas of high peak ground acceleration of 207- 210 cm/s^2 , the population will experience a growth of almost 30% over the forecasted time span which simultaneously corresponds to 70% of the predicted additional inhabitants of Lima. The population in the tsunami inundation area will grow by 61% until 2035, which is substantially more than the average growth of 35% for the city. Uncovering those relations can help urban planers and policy makers to develop effective risk mitigation strategies.