Articles | Volume 24, issue 3
https://doi.org/10.5194/nhess-24-1051-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Special issue:
https://doi.org/10.5194/nhess-24-1051-2024
© Author(s) 2024. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Research article
| 
28 Mar 2024
Research article |
| 28 Mar 2024
| 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
German Aerospace Center (DLR), German Remote Sensing Data Center (DFD), 82234 Wessling, Germany
Department of Geography, University of Bonn, 53115 Bonn, Germany
Jana Maier
German Aerospace Center (DLR), German Remote Sensing Data Center (DFD), 82234 Wessling, Germany
Emily So
Cambridge University Centre for Risk in the Built Environment, University of Cambridge, CB2 1PX, Cambridge, UK
Elisabeth Schoepfer
German Aerospace Center (DLR), German Remote Sensing Data Center (DFD), 82234 Wessling, Germany
Sven Harig
Alfred Wegener Institute, Helmholtz Centre for Polar and Marine Research (AWI), 27570 Bremerhaven, Germany
Juan Camilo Gómez Zapata
Helmholtz Centre Potsdam, GFZ German Research Centre for Geosciences, 14473 Potsdam, Germany
Institute for Geosciences, University of Potsdam, 14476 Potsdam, Germany
Cambridge University Centre for Risk in the Built Environment, University of Cambridge, CB2 1PX, Cambridge, UK
Institute of Environmental Engineering, ETH Zurich, 8093 Zurich, Switzerland
Related authors
Yue Zhu, Paolo Burlando, Puay Yok Tan, Christian Geiß, and Simone Fatichi
Nat. Hazards Earth Syst. Sci., 25, 2271–2286, https://doi.org/10.5194/nhess-25-2271-2025, https://doi.org/10.5194/nhess-25-2271-2025, 2025
Short summary
Short summary
This study addresses the challenge of accurately predicting floods in regions with limited terrain data. By utilising a deep learning model, we developed a method that improves the resolution of digital elevation data by fusing low-resolution elevation data with high-resolution satellite imagery. This approach not only substantially enhances flood prediction accuracy, but also holds potential for broader applications in simulating natural hazards that require terrain information.
Elisabeth Schoepfer, Jörn Lauterjung, Torsten Riedlinger, Harald Spahn, Juan Camilo Gómez Zapata, Christian D. León, Hugo Rosero-Velásquez, Sven Harig, Michael Langbein, Nils Brinckmann, Günter Strunz, Christian Geiß, and Hannes Taubenböck
Nat. Hazards Earth Syst. Sci., 24, 4631–4660, https://doi.org/10.5194/nhess-24-4631-2024, https://doi.org/10.5194/nhess-24-4631-2024, 2024
Short summary
Short summary
In this paper, we provide a brief introduction of the paradigm shift from managing disasters to managing risks, followed by single-hazard to multi-risk assessment. We highlight four global strategies that address disaster risk reduction and call for action. Subsequently, we present a conceptual approach for multi-risk assessment which was designed to serve potential users like disaster risk managers, urban planners or operators of critical infrastructure to increase their capabilities.
Wenyue Zou, Ruidong Li, Daniel B. Wright, Jovan Blagojevic, Peter Molnar, Mohammad A. Hussain, Yue Zhu, Yongkun Li, Guangheng Ni, and Nadav Peleg
EGUsphere, https://doi.org/10.5194/egusphere-2025-4099, https://doi.org/10.5194/egusphere-2025-4099, 2025
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
Short summary
We present a framework using observed rainfall and temperature to generate realistic storms and simulate street-scale flooding for present and future climates. It integrates temperature-based rainfall scaling, storm-frequency estimation, and urban flood modeling, demonstrated in Beijing to assess changes in regional storm and flood depth, timing, and flow velocity. The workflow is data-light, physically grounded, and transferable worldwide.
Yue Zhu, Paolo Burlando, Puay Yok Tan, Christian Geiß, and Simone Fatichi
Nat. Hazards Earth Syst. Sci., 25, 2271–2286, https://doi.org/10.5194/nhess-25-2271-2025, https://doi.org/10.5194/nhess-25-2271-2025, 2025
Short summary
Short summary
This study addresses the challenge of accurately predicting floods in regions with limited terrain data. By utilising a deep learning model, we developed a method that improves the resolution of digital elevation data by fusing low-resolution elevation data with high-resolution satellite imagery. This approach not only substantially enhances flood prediction accuracy, but also holds potential for broader applications in simulating natural hazards that require terrain information.
Elisabeth Schoepfer, Rodrigo Cienfuegos, Jörn Lauterjung, Torsten Riedlinger, and Hannes Taubenböck
Nat. Hazards Earth Syst. Sci., 25, 1163–1167, https://doi.org/10.5194/nhess-25-1163-2025, https://doi.org/10.5194/nhess-25-1163-2025, 2025
Elisabeth Schoepfer, Jörn Lauterjung, Torsten Riedlinger, Harald Spahn, Juan Camilo Gómez Zapata, Christian D. León, Hugo Rosero-Velásquez, Sven Harig, Michael Langbein, Nils Brinckmann, Günter Strunz, Christian Geiß, and Hannes Taubenböck
Nat. Hazards Earth Syst. Sci., 24, 4631–4660, https://doi.org/10.5194/nhess-24-4631-2024, https://doi.org/10.5194/nhess-24-4631-2024, 2024
Short summary
Short summary
In this paper, we provide a brief introduction of the paradigm shift from managing disasters to managing risks, followed by single-hazard to multi-risk assessment. We highlight four global strategies that address disaster risk reduction and call for action. Subsequently, we present a conceptual approach for multi-risk assessment which was designed to serve potential users like disaster risk managers, urban planners or operators of critical infrastructure to increase their capabilities.
Hugo Rosero-Velásquez, Mauricio Monsalve, Juan Camilo Gómez Zapata, Elisa Ferrario, Alan Poulos, Juan Carlos de la Llera, and Daniel Straub
Nat. Hazards Earth Syst. Sci., 24, 2667–2687, https://doi.org/10.5194/nhess-24-2667-2024, https://doi.org/10.5194/nhess-24-2667-2024, 2024
Short summary
Short summary
Seismic risk management uses reference earthquake scenarios, but the criteria for selecting them do not always consider consequences for exposed assets. Hence, we adopt a definition of representative scenarios associated with a return period and loss level to select such scenarios among a large set of possible earthquakes. We identify the scenarios for the residential-building stock and power supply in Valparaíso and Viña del Mar, Chile. The selected scenarios depend on the exposed assets.
Ivan Kuznetsov, Benjamin Rabe, Alexey Androsov, Ying-Chih Fang, Mario Hoppmann, Alejandra Quintanilla-Zurita, Sven Harig, Sandra Tippenhauer, Kirstin Schulz, Volker Mohrholz, Ilker Fer, Vera Fofonova, and Markus Janout
Ocean Sci., 20, 759–777, https://doi.org/10.5194/os-20-759-2024, https://doi.org/10.5194/os-20-759-2024, 2024
Short summary
Short summary
Our research introduces a tool for dynamically mapping the Arctic Ocean using data from the MOSAiC experiment. Incorporating extensive data into a model clarifies the ocean's structure and movement. Our findings on temperature, salinity, and currents reveal how water layers mix and identify areas of intense water movement. This enhances understanding of Arctic Ocean dynamics and supports climate impact studies. Our work is vital for comprehending this key region in global climate science.
Alexey Androsov, Sven Harig, Natalia Zamora, Kim Knauer, and Natalja Rakowsky
Nat. Hazards Earth Syst. Sci., 24, 1635–1656, https://doi.org/10.5194/nhess-24-1635-2024, https://doi.org/10.5194/nhess-24-1635-2024, 2024
Short summary
Short summary
Two numerical codes are used in a comparative analysis of the calculation of the tsunami wave due to an earthquake along the Peruvian coast. The comparison primarily evaluates the flow velocity fields in flooded areas. The relative importance of the various parts of the equations is determined, focusing on the nonlinear terms. The influence of the nonlinearity on the degree and volume of flooding, flow velocity, and small-scale fluctuations is determined.
Juan Camilo Gómez Zapata, Massimiliano Pittore, Nils Brinckmann, Juan Lizarazo-Marriaga, Sergio Medina, Nicola Tarque, and Fabrice Cotton
Nat. Hazards Earth Syst. Sci., 23, 2203–2228, https://doi.org/10.5194/nhess-23-2203-2023, https://doi.org/10.5194/nhess-23-2203-2023, 2023
Short summary
Short summary
To investigate cumulative damage on extended building portfolios, we propose an alternative and modular method to probabilistically integrate sets of single-hazard vulnerability models that are being constantly developed by experts from various research fields to be used within a multi-risk context. We demonstrate its application by assessing the economic losses expected for the residential building stock of Lima, Peru, a megacity commonly exposed to consecutive earthquake and tsunami scenarios.
Dirsa Feliciano, Orlando Arroyo, Tamara Cabrera, Diana Contreras, Jairo Andrés Valcárcel Torres, and Juan Camilo Gómez Zapata
Nat. Hazards Earth Syst. Sci., 23, 1863–1890, https://doi.org/10.5194/nhess-23-1863-2023, https://doi.org/10.5194/nhess-23-1863-2023, 2023
Short summary
Short summary
This article presents the number of damaged buildings and estimates the economic losses from a set of earthquakes in Sabana Centro, a region of 11 towns in Colombia.
Juan Camilo Gomez-Zapata, Nils Brinckmann, Sven Harig, Raquel Zafrir, Massimiliano Pittore, Fabrice Cotton, and Andrey Babeyko
Nat. Hazards Earth Syst. Sci., 21, 3599–3628, https://doi.org/10.5194/nhess-21-3599-2021, https://doi.org/10.5194/nhess-21-3599-2021, 2021
Short summary
Short summary
We present variable-resolution boundaries based on central Voronoi tessellations (CVTs) to spatially aggregate building exposure models and physical vulnerability assessment. Their geo-cell sizes are inversely proportional to underlying distributions that account for the combination between hazard intensities and exposure proxies. We explore their efficiency and associated uncertainties in risk–loss estimations and mapping from decoupled scenario-based earthquakes and tsunamis in Lima, Peru.
Cited articles
Abar, S., Theodoropoulos, G. K., Lemarinier, P., and O'Hare, G. M. P.: Agent Based Modelling and Simulation tools: A review of the state-of-art software, Computer Science Review, 24, 13–33, https://doi.org/10.1016/j.cosrev.2017.03.001, 2017.
Aggarwal, C. C.: Neural Networks and Deep Learning: A Textbook, Springer International Publishing, Cham, https://doi.org/10.1007/978-3-319-94463-0, 2018.
Androsov, A., Harig, S., Zamora, N., Knauer, K., and Rakowsky, N.: Nonlinear processes in tsunami simulations for the Peruvian coast with focus on Lima/Callao, EGUsphere [preprint], https://doi.org/10.5194/egusphere-2023-1365, 2023.
Calderon, A. and Silva, V.: Exposure forecasting for seismic risk estimation: Application to Costa Rica, Earthq. Spectra, 37, 1806–1826, https://doi.org/10.1177/8755293021989333.
Chen, Y., Li, X., Huang, K., Luo, M., and Gao, M.: High-Resolution Gridded Population Projections for China Under the Shared Socioeconomic Pathways, Earths Future, 8, e2020EF001491, https://doi.org/10.1029/2020EF001491, 2020.
Clarke, K. C.: Cellular Automata and Agent-Based Models, in: Handbook of Regional Science, edited by: Fischer, M. M. and Nijkamp, P., Springer, Berlin, Heidelberg, 1217–1233, https://doi.org/10.1007/978-3-642-23430-9_63, 2014.
Cremen, G., Galasso, C., and McCloskey, J.: Modelling and quantifying tomorrow's risks from natural hazards, Sci. Total Environ., 817, 152552, https://doi.org/10.1016/j.scitotenv.2021.152552, 2022.
Dobson, J. E., Bright, E. A., Coleman, P. R., Durfee, R. C., and Worley, B. A.: LandScan: a global population database for estimating populations at risk, Photogramm. Eng. Rem. S., 66, 849–857, 2000.
ESA: Copernicus DEM – Global and European Digital Elevation Model (COP-DEM), European Space Agency (ESA) [data set], https://doi.org/10.5270/ESA-c5d3d65, 2022.
Friedl, M. and Sulla-Menashe, D.: MCD12Q1 modis/terra+aqua land cover type yearly l3 global 500m sin grid v006, NASA EOSDIS Land Processes DAAC [data set], https://doi.org/10.5067/MODIS/MCD12Q1.006, 2022.
Gagniuc, P. A.: Markov Chains: From Theory to Implementation and Experimentation, Wiley, ISBN 978-1-119-38755-8, 2017.
Gavahi, K., Abbaszadeh, P., and Moradkhani, H.: DeepYield: A combined convolutional neural network with long short-term memory for crop yield forecasting, Expert Syst. Appl., 184, 115511, https://doi.org/10.1016/j.eswa.2021.115511, 2021.
Geiß, C., Brzoska, E., Aravena Pelizari, P., Lautenbach, S., and Taubenböck, H.: Multi-target regressor chains with repetitive permutation scheme for characterization of built environments with remote sensing, Int. J. Appl. Earth Obs., 106, 102657, https://doi.org/10.1016/j.jag.2021.102657, 2022.
Gómez, J. A., Patiño, J. E., Duque, J. C., and Passos, S.: Spatiotemporal Modeling of Urban Growth Using Machine Learning, Remote Sens., 12, 109, https://doi.org/10.3390/rs12010109, 2020.
Gomez-Zapata, J. C., Brinckmann, N., Harig, S., Zafrir, R., Pittore, M., Cotton, F., and Babeyko, A.: Variable-resolution building exposure modelling for earthquake and tsunami scenario-based risk assessment: an application case in Lima, Peru, Nat. Hazards Earth Syst. Sci., 21, 3599–3628, https://doi.org/10.5194/nhess-21-3599-2021, 2021.
Goodfellow, I., Bengio, Y., and Courville, A.: Deep learning. Adaptive computation and machine learning, The MIT Press, Cambridge, Massachusetts and London, England, ISBN 9780262035613, 2016.
Hochreiter, S. and Schmidhuber, J.: Long Short-Term Memory, Neural Comput., 9, 1735–1780, https://doi.org/10.1162/neco.1997.9.8.1735, 1997.
Iglesias, V., Braswell, A. E., Rossi, M. W., Joseph, M. B., McShane, C., Cattau, M., Koontz, M. J., McGlinchy, J., Nagy, R. C., Balch, J., Leyk, S., and Travis, W. R.: Risky Development: Increasing Exposure to Natural Hazards in the United States, Earths Future, 9, e2020EF001795, https://doi.org/10.1029/2020EF001795, 2021.
Jimenez, C., Moggiano, N., Mas, E., Adriano, B., Koshimura, S., Fujii, Y., and Yanagisawa, H.: Seismic Source of 1746 Callao Earthquake from Tsunami Numerical Modeling, Journal of Disaster Research, 8, 266–273, https://doi.org/10.20965/jdr.2013.p0266, 2013.
Johnson, B. A., Estoque, R. C., Li, X., Kumar, P., Dasgupta, R., Avtar, R., and Magcale-Macandog, D. B.: High-resolution urban change modeling and flood exposure estimation at a national scale using open geospatial data: A case study of the Philippines, Comput. Environ. Urban, 90, 101704, https://doi.org/10.1016/j.compenvurbsys.2021.101704, 2021.
Koehler, J. and Kuenzer, C.: Forecasting Spatio-Temporal Dynamics on the Land Surface Using Earth Observation Data – A Review, Remote Sens., 12, 3513, https://doi.org/10.3390/rs12213513, 2020.
Kubota, Y., Ohira, Y., and Shimizu, T.: Attention-based Contextual Multi-View Graph Convolutional Networks for Short-term Population Prediction, arXiv [preprint], https://doi.org/10.48550/arXiv.2203.00489, 2022.
LeCun, Y., Bengio, Y., and Hinton, G.: Deep learning, Nature, 521, 436–444, https://doi.org/10.1038/nature14539, 2015.
Liu, X., Liang, X., Li, X., Xu, X., Ou, J., Chen, Y., Li, S., Wang, S., and Pei, F.: A future land use simulation model (FLUS) for simulating multiple land use scenarios by coupling human and natural effects, Landscape Urban Plan., 168, 94–116, https://doi.org/10.1016/j.landurbplan.2017.09.019, 2017.
Lloyd, C. T., Sorichetta, A., and Tatem, A. J.: High resolution global gridded data for use in population studies, Sci. Data, 4, 170001, https://doi.org/10.1038/sdata.2017.1, 2017.
Montalva, G. A., Bastías, N., and Rodriguez-Marek, A.: Ground-Motion Prediction Equation for the Chilean Subduction Zone, B. Seismol. Soc. Am., 107, 901–911, https://doi.org/10.1785/0120160221, 2017.
OpenStreetMap contributors: Planet dump, Planet OSM [data set], https://planet.openstreetmap.org/ (last access: 26 September 2022), 2022.
Pijanowski, B. C., Brown, D. G., Shellito, B. A., and Manik, G. A.: Using neural networks and GIS to forecast land use changes: a Land Transformation Model, Comput. Environ. Urban, 26, 553–575, https://doi.org/10.1016/S0198-9715(01)00015-1, 2002.
RIESGOS: RIESGOS Scenario-based multi-risk assessment in the Andes region, https://riesgos.de/de (last access: 26 September 2022), 2022.
Rumelhart, D. E., Hinton, G. E., and Williams, R. J.: Learning representations by back-propagating errors, Nature, 323, 533–536, https://doi.org/10.1038/323533a0, 1986.
Scheuer, S., Haase, D., Haase, A., Wolff, M., and Wellmann, T.: A glimpse into the future of exposure and vulnerabilities in cities? Modelling of residential location choice of urban population with random forest, Nat. Hazards Earth Syst. Sci., 21, 203–217, https://doi.org/10.5194/nhess-21-203-2021, 2021.
Schoepfer, E., Lauterjung, J., Riedlinger, T., Spahn, H., Gómez Zapata, J. C., León, C. D., Rosero-Velásquez, H., Harig, S., Langbein, M., Brinckmann, N., Strunz, G., Geiß, C., and Taubenböck, H.: Between global risk reduction goals, scientific-technical capabilities and local realities: a novel modular approach for multi-risk assessment, Nat. Hazards Earth Syst. Sci. Discuss. [preprint], https://doi.org/10.5194/nhess-2023-142, in review, 2023.
Shi, X., Chen, Z., Wang, H., Yeung, D.-Y., Wong, W., and WOO, W.: Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting, Adv. Neur. In., arXiv [preprint], https://doi.org/10.48550/arXiv.1506.04214, 2015.
Stevens, F. R., Gaughan, A. E., Linard, C., and Tatem, A. J.: Disaggregating Census Data for Population Mapping Using Random Forests with Remotely-Sensed and Ancillary Data, PLOS ONE, 10, e0107042, https://doi.org/10.1371/journal.pone.0107042, 2015.
UN Habitat: Urban impact, United nations human settlement programme, https://unhabitat.org/urban-impact-newsletters (last access: 30 April 2022), 2016.
United Nations: World Population Prospects, https://population.un.org/wpp/, last access: 29 September 2022.
UNISDR: Sendai Framework for Disaster Risk Reduction 2015–2030, UNISDR/GE/ 2015 – ICLUX EN5000, 1st edn., 2015.
Wang, C.-Y. and Lee, S.-J.: Regional Population Forecast and Analysis Based on Machine Learning Strategy, Entropy, 23, 656, https://doi.org/10.3390/e23060656, 2021.
Wang, Z., Bachofer, F., Koehler, J., Huth, J., Hoeser, T., Marconcini, M., Esch, T., and Kuenzer, C.: Spatial Modelling and Prediction with the Spatio-Temporal Matrix: A Study on Predicting Future Settlement Growth, Land, 11, 1174, https://doi.org/10.3390/land11081174, 2022.
Zheng, Z. and Zhang, G.: The Prediction of Finely-Grained Spatiotemporal Relative Human Population Density Distributions in China, IEEE Access, 8, 181534–181546, https://doi.org/10.1109/ACCESS.2020.3027824, 2020.
Zhu, Y.: A Deep Learning Framework for Investigating Spatio-temporal Evolution of Land Use and Land Cover Patterns, Apollo – University of Cambridge Repository, https://doi.org/10.17863/CAM.92921, 2023.
Zhu, Y., Geiß, C., and So, E.: Image super-resolution with dense-sampling residual channel-spatial attention networks for multi-temporal remote sensing image classification, Int. J. Appl. Earth Obs., 104, 102543, https://doi.org/10.1016/j.jag.2021.102543, 2021a.
Zhu, Y., Geiß, C., So, E., and Jin, Y.: Multitemporal Relearning with Convolutional LSTM Models for Land Use Classification, IEEE J. Sel. Top. Appl., 14, 3251–3265, https://doi.org/10.1109/JSTARS.2021.3055784, 2021b.
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 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 policymakers to develop effective risk mitigation strategies.
We establish a model of future geospatial population distributions to quantify the number of...
Special issue
Altmetrics
Final-revised paper
Preprint