Articles | Volume 24, issue 12
https://doi.org/10.5194/nhess-24-4585-2024
https://doi.org/10.5194/nhess-24-4585-2024
Research article
 | 
12 Dec 2024
Research article |  | 12 Dec 2024

Automating tephra fall building damage assessment using deep learning

Eleanor Tennant, Susanna F. Jenkins, Victoria Miller, Richard Robertson, Bihan Wen, Sang-Ho Yun, and Benoit Taisne

Related authors

Evaluating and ranking Southeast Asia's exposure to explosive volcanic hazards
Susanna F. Jenkins, Sébastien Biass, George T. Williams, Josh L. Hayes, Eleanor Tennant, Qingyuan Yang, Vanesa Burgos, Elinor S. Meredith, Geoffrey A. Lerner, Magfira Syarifuddin, and Andrea Verolino
Nat. Hazards Earth Syst. Sci., 22, 1233–1265, https://doi.org/10.5194/nhess-22-1233-2022,https://doi.org/10.5194/nhess-22-1233-2022, 2022
Short summary

Related subject area

Volcanic Hazards
Social sensing a volcanic eruption: application to Kīlauea, 2018
James Hickey, James Young, Michelle Spruce, Ravi Pandit, Hywel Williams, Rudy Arthur, Wendy Stovall, and Matthew Head
Nat. Hazards Earth Syst. Sci., 25, 1681–1696, https://doi.org/10.5194/nhess-25-1681-2025,https://doi.org/10.5194/nhess-25-1681-2025, 2025
Short summary
Quantifying economic risks to dairy farms from volcanic hazards in Taranaki, Aotearoa / New Zealand
Nicola J. McDonald, Leslie Dowling, Emily P. Harvey, Alana M. Weir, Mark S. Bebbington, Nam Bui, Christina Magill, Heather M. Craig, Garry W. McDonald, Juan J. Monge, Shane J. Cronin, Thomas M. Wilson, and Duncan Walker
Nat. Hazards Earth Syst. Sci., 25, 1543–1571, https://doi.org/10.5194/nhess-25-1543-2025,https://doi.org/10.5194/nhess-25-1543-2025, 2025
Short summary
Geophysical fingerprint of the 4–11 July 2024 eruptive activity at Stromboli volcano, Italy
Luciano Zuccarello, Duccio Gheri, Silvio De Angelis, Riccardo Civico, Tullio Ricci, and Piergiorgio Scarlato
EGUsphere, https://doi.org/10.5194/egusphere-2024-3773,https://doi.org/10.5194/egusphere-2024-3773, 2024
Short summary
Where will the next flank eruption at Etna occur? An updated spatial probabilistic assessment
Laura Sandri, Alexander Garcia, Cristina Proietti, Stefano Branca, Gaetana Ganci, and Annalisa Cappello
Nat. Hazards Earth Syst. Sci., 24, 4431–4455, https://doi.org/10.5194/nhess-24-4431-2024,https://doi.org/10.5194/nhess-24-4431-2024, 2024
Short summary
Brief communication: Small-scale geohazards cause significant and highly variable impacts on emotions
Evgenia Ilyinskaya, Vésteinn Snæbjarnarson, Hanne Krage Carlsen, and Björn Oddsson
Nat. Hazards Earth Syst. Sci., 24, 3115–3128, https://doi.org/10.5194/nhess-24-3115-2024,https://doi.org/10.5194/nhess-24-3115-2024, 2024
Short summary

Cited articles

Aggarwal, C. C. (Eds.): Neural networks and deep learning, Springer, eBook ISBN 978-3-319-94463-0, 2018. 
An, G., Akiba, M., Omodaka, K., Nakazawa, T., and Yokota, H.: Hierarchical deep learning models using transfer learning for disease detection and classification based on small number of medical images, Sci. Rep., 11, 4250, https://doi.org/10.1038/s41598-021-83503-7, 2021. 
Andaru, R. and Rau, J. Y.: Lava dome changes detection at Agung Mountain during high level of volcanic activity using UAV photogrammetry, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 173–179, https://doi.org/10.5194/isprs-archives-XLII-2-W13-173-2019, 2019. 
Anniballe, R., Noto, F., Scalia, T., Bignami, C., Stramondo, S., Chini, M., and Pierdicca, N.: Earthquake damage mapping: An overall assessment of ground surveys and VHR image change detection after L'Aquila 2009 earthquake, Remote Sens. Environ., 210, 166–178, https://doi.org/10.1016/j.rse.2018.03.004, 2018. 
Ben-David, S., Blitzer, J., Crammer, K., Kulesza, A., Pereira, F., and Vaughan, J. W.: A theory of learning from different domains, Mach. Learn., 79, 151–175, https://doi.org/10.1007/s10994-009-5152-4, 2010. 
Download
Short summary
After a volcanic eruption, assessing building damage quickly is important for responding to and recovering from the disaster. Traditional damage assessment methods such as ground surveys can be time-consuming and resource-intensive, hindering rapid response and recovery efforts. To overcome this, we have developed an automated approach for tephra fall building damage assessment. Our approach uses drone-acquired optical images and deep learning to rapidly generate building damage data.
Share
Altmetrics
Final-revised paper
Preprint