Towards reliable deep learning for post-disaster damage Assessment: An XAI-based evaluation
Authors:
- Umut LagapULUmut Lagap
- Saman GhaffarianSaman Ghaffarian
- Sophie Gelinas-GagneSGSophie Gelinas-Gagne
- Jasmin JilmaJJJasmin Jilma
- Zhiyu LiuZLZhiyu Liu
- Zhiyuan LuoZLZhiyuan Luo
Open Access
- 27 September 2025
- journal article
- Published by Elsevier in International Journal of Disaster Risk Reduction
- Vol. 130
Abstract
No abstract availableFunding Information
- University College London
This publication has 38 references indexed in Scilit:
- A Class Distance Penalty Deep Learning Method for Post-disaster Building Damage AssessmentKSCE Journal of Civil Engineering, 2024
- A Deep Learning Application for Building Damage Assessment Using Ultra-High-Resolution Remote Sensing Imagery in Turkey EarthquakeInternational Journal of Disaster Risk Science, 2023
- Explainable artificial intelligence in disaster risk management: Achievements and prospective futuresInternational Journal of Disaster Risk Reduction, 2023
- Survey on Explainable AI: From Approaches, Limitations and Applications AspectsHuman-Centric Intelligent Systems, 2023
- Beyond explaining: Opportunities and challenges of XAI-based model improvementInformation Fusion, 2022
- Data augmentation: A comprehensive survey of modern approachesArray, 2022
- Post-disaster building damage assessment based on improved U-NetScientific Reports, 2022
- Uncertainty‐aware convolutional neural network for explainable artificial intelligence‐assisted disaster damage assessmentStructural Control and Health Monitoring, 2022
- Exploring probable reasons for record fatalities: the case of 2011 Joplin, Missouri, TornadoNatural Hazards, 2012
- Color image segmentation using pixel wise support vector machine classificationPattern Recognition, 2011