Disaster Recognition and Classification Based on Improved ResNet-50 Neural Network
Applied Sciences · 06.05.2025 · 15 (9) · 5143
DOI: 10.3390/app15095143 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 06.05.2025. Verfasst von Lei Wen und 3 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Student Innovation and Entrepreneurship Training Program of Xiangtan University.
Abstract (Originalsprache)
Accurate and timely disaster classification is critical for effective disaster management and emergency response. This study proposes an improved ResNet-50-based deep learning model to classify seven types of natural disasters, including earthquake, fire, flood, mudslide, avalanche, landslide, and land subsidence. The dataset was compiled from publicly available sources and partitioned into training and validation sets using an 8:2 split. Experimental results demonstrate that the proposed model achieves a classification accuracy of 87% on the validation set and outperforms the traditional VGG16 model in most evaluation metrics, including precision, recall, F1-score, AUC, specificity, and log loss. Furthermore, the model effectively mitigates the gradient vanishing problem, ensuring stable convergence and robust training performance. These findings provide a practical technical reference for multi-disaster classification tasks and contribute to enhancing the efficiency of disaster response and societal resilience.
Förderung
- Student Innovation and Entrepreneurship Training Program of Xiangtan University
Zitieren
APA
Wen, L., Xiao, Z., Xu, X., & Liu, B. (2025). Disaster Recognition and Classification Based on Improved ResNet-50 Neural Network. Applied Sciences, 15(9), 5143. https://doi.org/10.3390/app15095143
Vancouver
Wen L, Xiao Z, Xu X, Liu B. Disaster Recognition and Classification Based on Improved ResNet-50 Neural Network. Applied Sciences. 2025;15(9):5143. doi:10.3390/app15095143
BibTeX
@article{Wen2025,
author = {Wen, Lei and Xiao, Zikai and Xu, Xiaoting and Liu, Bin},
title = {Disaster Recognition and Classification Based on Improved ResNet-50 Neural Network},
journal = {Applied Sciences},
year = {2025},
volume = {15},
number = {9},
pages = {5143},
doi = {10.3390/app15095143}
}
EUVIMED