Open Access Open Access  Restricted Access Subscription Access

DISASTER DAMAGE ESTIMATION USING SATELLITE IMAGERY AND MACHINE LEARNING

Muthumuniyasamy ., P. Sini Pabhakar, S. Mukkesh, S. Koushik Kumar, S. Naresh

Abstract


This research presents a comprehensive framework for disaster damage estimation using multispectral satellite imagery and machine learning models. The system leverages Google Earth Engine (GEE) for geospatial data collection and employs deep learning algorithms to classify the extent of damage in affected areas. In addition to classification, the model quantifies the estimated economic loss in INR, providing actionable insights for post-disaster management and recovery. The pipeline integrates preprocessing, segmentation, feature extraction, and INR conversion to deliver accurate, scalable, and real-time assessments for both natural and man-made disasters.


Full Text:

PDF

References


Sinha, P., Ghosh, S., & Patel, N. (2018). Flood damage assessment using multi-temporal satellite images. Remote Sensing Letters.

Krizhevsky, A., Sutskever, I., & Hinton, G. (2012). ImageNet classification with deep convolutional neural networks.

Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. ICML.

Gorelick, N., et al. (2017). Google Earth Engine: Planetary-scale geospatial analysis. Remote Sensing of Environment.

Ghosh, A., & Kumar, R. (2020). Machine learning for post-disaster assessment using satellite imagery. IEEE Transactions on Geoscience and Remote Sensing.


Refbacks

  • There are currently no refbacks.