Preprints
https://doi.org/10.5194/egusphere-2023-1794
https://doi.org/10.5194/egusphere-2023-1794
15 Aug 2023
 | 15 Aug 2023

Anticipating a risky future: LSTM models for spatiotemporal extrapolation of population data in areas prone to earthquakes and tsunamis in Lima, Peru

Christian Geiß, Jana Maier, Emily So, Elisabeth Schoepfer, Sven Harig, Juan Camilo Gomez Zapata, and Yue Zhu

Abstract. In this paper, we anticipate geospatial population distributions to quantify the future number of people living in earthquake-prone and tsunami-prone areas of Lima and Callao, 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 value of the LSTM-based models for forecasting gridded population data. The best trained 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 , 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 planners and policy makers to develop effective risk mitigation strategies.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Share

Journal article(s) based on this preprint

28 Mar 2024
Anticipating a risky future: long short-term memory (LSTM) models for spatiotemporal extrapolation of population data in areas prone to earthquakes and tsunamis in Lima, Peru
Christian Geiß, Jana Maier, Emily So, Elisabeth Schoepfer, Sven Harig, Juan Camilo Gómez Zapata, and Yue Zhu
Nat. Hazards Earth Syst. Sci., 24, 1051–1064, https://doi.org/10.5194/nhess-24-1051-2024,https://doi.org/10.5194/nhess-24-1051-2024, 2024
Short summary
Download

The requested preprint has a corresponding peer-reviewed final revised paper. You are encouraged to refer to the final revised version.

Short summary
We establish a model of future geospatial population distributions to quantify the number of...
Share