INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Effective assessment of building damage following earthquakes is crucial for prompt emergency response and allocation of resources. In this study, we propose an integrated approach that combines high-resolution building inventory data, earthquake ground shaking intensity maps, and post-event InSAR imagery analysis aided by recent advances in machine learning algorithms. Our methodology involves the utilization of ensemble models in a machine learning framework to classify the damage state of buildings affected by earthquakes. We leverage post event very high-resolution remote sensing imagery to identify collapsed buildings, with a particular focus on the potential of Convolutional Neural Networks (CNNs) in extracting deep features for this purpose. We compare the performance of CNN features with texture features using the Random Forest classifier. Additionally, we employ VGG19, a pre-trained deep learning model, to gain insights into the defining characteristics of images in terms of shape, color, and structure. The results of our approach are visualized through color-coded satellite images, where completely damaged buildings are represented in red, partially collapsed buildings in blue, and basically intact buildings in green. Regions marked in red denote areas requiring urgent assistance and support. The integration of remote sensing data, machine learning algorithms, and visual representations enhances the effectiveness of earthquake damage assessment and aids in facilitating timely and targeted emergency response efforts.
"DETECTION OF POST-EARTHQUAKE DAMAGE SEVERITY FROM SATELLITE IMAGES USING VGG19", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.9, Issue 3, page no.d169-d177, March-2024, Available :http://www.ijnrd.org/papers/IJNRD2403323.pdf
Downloads:
00032
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn