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.

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

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2023-1794', Anonymous Referee #1, 10 Sep 2023
    • AC1: 'Reply on RC1', Christian Geiß, 02 Nov 2023
  • RC2: 'Comment on egusphere-2023-1794', Anonymous Referee #2, 11 Sep 2023
    • AC2: 'Reply on RC2', Christian Geiß, 02 Nov 2023
Christian Geiß, Jana Maier, Emily So, Elisabeth Schoepfer, Sven Harig, Juan Camilo Gomez Zapata, and Yue Zhu
Christian Geiß, Jana Maier, Emily So, Elisabeth Schoepfer, Sven Harig, Juan Camilo Gomez Zapata, and Yue Zhu

Viewed

Total article views: 469 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
280 164 25 469 15 14
  • HTML: 280
  • PDF: 164
  • XML: 25
  • Total: 469
  • BibTeX: 15
  • EndNote: 14
Views and downloads (calculated since 15 Aug 2023)
Cumulative views and downloads (calculated since 15 Aug 2023)

Viewed (geographical distribution)

Total article views: 456 (including HTML, PDF, and XML) Thereof 456 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 01 Mar 2024
Download
Short summary
We establish a model of future geospatial population distributions to quantify the number of people living in earthquake-prone and tsunami-prone areas of Lima and Callao, Peru, for the year 2035. Areas of a high earthquake intensity will experience a population growth of almost 30 %. The population in the tsunami inundation area is estimated to grow by more than 60 %. Uncovering those relations can help urban planners and policy makers to develop effective risk mitigation strategies.