Earthquake Damage Assessment using Hyperspectral Images and Convolutional Neural Network Classification
Abstract: Earthquakes are most damaging natural disasters that can cause extensive damage to both property and human life. Early detection of earthquakes and understanding their potential impact can help in reducing the risk of damage and loss. In this paper, I propose a method for earthquake analysis by classification of hyperspectral images with convolutional neural network (CNN) and fuzzy logic. Hyperspectral imaging technology provides high spatial and spectral resolution images that can capture detailed information about the earth's surface, including potential earthquake-related changes. Our proposed method uses a CNN to classify hyperspectral images and identify potential earthquake damage based on changes in surface characteristics. I tested our approach on a publicly available dataset and achieved an accuracy of 93.2%, demonstrating the effectiveness of our method for earthquake analysis.
Keywords: Deep Learning, Hyperspectral Imaging, Mathematical modelling, Neural Networks, Geo Information systems
How to Cite?: Chaitanya Wagh, "Earthquake Damage Assessment using Hyperspectral Images and Convolutional Neural Network Classification", Volume 12 Issue 4, April 2023, International Journal of Science and Research (IJSR), Pages: 1140-1145, https://www.ijsr.net/getabstract.php?paperid=SR23417194110, DOI: https://dx.doi.org/10.21275/SR23417194110