Articles | Volume 21, issue 10
https://doi.org/10.5194/nhess-21-3199-2021
https://doi.org/10.5194/nhess-21-3199-2021
Research article
 | 
27 Oct 2021
Research article |  | 27 Oct 2021

Improving flood damage assessments in data-scarce areas by retrieval of building characteristics through UAV image segmentation and machine learning – a case study of the 2019 floods in southern Malawi

Lucas Wouters, Anaïs Couasnon, Marleen C. de Ruiter, Marc J. C. van den Homberg, Aklilu Teklesadik, and Hans de Moel

Related authors

Multi-hazards in Scandinavia: impacts and risks from compound heatwaves, droughts and wildfires
Gwendoline Ducros, Timothy Tiggeloven, Lin Ma, Anne Sophie Daloz, Nina Schuhen, Judith Claassen, and Marleen C. de Ruiter
Nat. Hazards Earth Syst. Sci., 25, 4693–4712, https://doi.org/10.5194/nhess-25-4693-2025,https://doi.org/10.5194/nhess-25-4693-2025, 2025
Short summary
Invited perspectives: Towards usable compound event research
Kai Kornuber, Emanuele Bevacqua, Mariana Madruga de Brito, Wiebke S. Jäger, Pauline Rivoire, Cassandra D. W. Rogers, Fabiola Banfi, Fulden Batibeniz, James Carruthers, Carlo de Michele, Silvia de Angeli, Cristina Deidda, Marleen C. de Ruiter, Andreas H. Fink, Henrique M. D. Goulart, Katharina Küpfer, Patrick Ludwig, Douglas Maraun, Gabriele Messori, Shruti Nath, Fiachra O’Loughlin, Joaquim G. Pinto, Benjamin Poschlod, Alexandre M. Ramos, Colin Raymond, Andreia F. S. Ribeiro, Deepti Singh, Laura Suarez Gutierrez, Philip J. Ward, and Christopher J. White
EGUsphere, https://doi.org/10.5194/egusphere-2025-4683,https://doi.org/10.5194/egusphere-2025-4683, 2025
This preprint is open for discussion and under review for Natural Hazards and Earth System Sciences (NHESS).
Short summary
Validation of the Open-Source Hydrodynamic Model SFINCS on Historical River Floods at the Global Scale
Tarun Sadana, Jeroen C. J. H. Aerts, Dirk Eilander, Bruno Merz, Hans de Moel, Tim Busker, Veerle Bril, and Jens de Bruijn
EGUsphere, https://doi.org/10.5194/egusphere-2025-4387,https://doi.org/10.5194/egusphere-2025-4387, 2025
This preprint is open for discussion and under review for Hydrology and Earth System Sciences (HESS).
Short summary
A pathways analysis dashboard prototype for multi-risk systems
Julius Schlumberger, Robert Šakić Trogrlić, Jeroen C. J. H. Aerts, Jung-Hee Hyun, Stefan Hochrainer-Stigler, Marleen de Ruiter, and Marjolijn Haasnoot
Nat. Hazards Earth Syst. Sci., 25, 4089–4113, https://doi.org/10.5194/nhess-25-4089-2025,https://doi.org/10.5194/nhess-25-4089-2025, 2025
Short summary
Recovery under consecutive disasters: how recovery dynamics shape societal resilience
Sophie L. Buijs, Inga J. Sauer, Chahan M. Kropf, Samuel Juhel, Zélie Stalhandske, and Marleen C. De Ruiter
EGUsphere, https://doi.org/10.5194/egusphere-2025-3200,https://doi.org/10.5194/egusphere-2025-3200, 2025
This preprint is open for discussion and under review for Natural Hazards and Earth System Sciences (NHESS).
Short summary

Cited articles

Ai, J., Zhang, C., Chen, L., and Li, D.: Mapping Annual Land Use and Land Cover Changes in the Yangtze Estuary Region Using an Object-Based Classification Framework and Landsat Time Series Data, Sustainability, 12, 659, https://doi.org/10.3390/su12020659, 2020. 
Alam, A., Bhat, M. S., Farooq, H., Ahmad, B., Ahmad, S., and Sheikh, A. H.: Flood risk assessment of Srinagar city in Jammu and Kashmir, India, International Journal of Disaster Resilience in the Built Environment, 9, 114–129, https://doi.org/10.1108/IJDRBE-02-2017-0012, 2018. 
Amirebrahimi, S., Rajabifard, A., Mendis, P., and Ngo, T.: A framework for a microscale flood damage assessment and visualization for a building using BIM–GIS integration, Int. J. Digit. Earth, 9, 363–386, https://doi.org/10.1080/17538947.2015.1034201, 2016. 
Belgiu, M. and Draguţ, L.: Comparing supervised and unsupervised multiresolution segmentation approaches for extracting buildings from very high resolution imagery, ISPRS J. Photogramm., 96, 67–75, https://doi.org/10.1016/j.isprsjprs.2014.07.002, 2014. 
Blanco-Vogt, Á., Haala, N., and Schanze, J.: Building parameters extraction from remote-sensing data and GIS analysis for the derivation of a building taxonomy of settlements – a contribution to flood building susceptibility assessment, International Journal of Image and Data Fusion, 6, 22–41, https://doi.org/10.1080/19479832.2014.926296, 2015. 
Download
Short summary
This research introduces a novel approach to estimate flood damage in Malawi by applying a machine learning model to UAV imagery. We think that the development of such a model is an essential step to enable the swift allocation of resources for recovery by humanitarian decision-makers. By comparing this method (EUR 10 140) to a conventional land-use-based approach (EUR 15 782) for a specific flood event, recommendations are made for future assessments.
Share
Altmetrics
Final-revised paper
Preprint