Nationwide Landslide Prediction in India Using Neural Networks and Multi-Source Satellite Data.

Karan Uddhavrao Dakhore; Anil Dnyanadev Kalasakar

doi:10.36948/ijfmr.2024.v06i06.31933

Nationwide Landslide Prediction in India Using Neural Networks and Multi-Source Satellite Data.

Author(s)	Karan Uddhavrao Dakhore, Anil Dnyanadev Kalasakar
Country	India
Abstract	Landslides are a prevalent and devastating natural hazard in mountainous regions, particularly in high-risk areas such as Uttarakhand and Meghalaya, India, where factors like intense rainfall, steep slopes, and changing land cover significantly contribute to landslide occurrences. Traditional ground-based monitoring methods provide limited coverage and scalability, underscoring the need for a more extensive and real-time approach to landslide prediction. This study addresses this gap by developing an advanced predictive model using neural network architectures and multi-source satellite data, including Synthetic Aperture Radar (SAR) from Sentinel-1 for ground deformation, optical imagery from Sentinel-2 for vegetation and land cover analysis, and Digital Elevation Models (DEM) for slope assessment. Additionally, rainfall data from the Global Precipitation Measurement (GPM) mission was integrated to evaluate precipitation as a potential landslide trigger. Through a comparative analysis of Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and a hybrid CNN-LSTM model, we found that the CNN-LSTM hybrid model achieved superior performance, with an F1 score of 0.91. This model effectively captures both spatial and temporal patterns, enabling early detection of landslide-prone conditions and surpassing the predictive accuracy of traditional methods. The proposed approach provides a scalable solution for real-time, large-scale monitoring, with the potential to enhance disaster preparedness and resilience in vulnerable communities. By advancing landslide prediction capabilities, this model contributes a valuable tool for proactive risk management and offers significant potential for integration into regional early warning systems.
Keywords	Landslide prediction, neural networks, SAR, Sentinel-1, Sentinel-2, CNN-LSTM, DEM, disaster resilience, early warning systems, real-time monitoring.
Field	Computer > Artificial Intelligence / Simulation / Virtual Reality
Published In	Volume 6, Issue 6, November-December 2024
Published On	2024-11-30
Cite This	Nationwide Landslide Prediction in India Using Neural Networks and Multi-Source Satellite Data. - Karan Uddhavrao Dakhore, Anil Dnyanadev Kalasakar - IJFMR Volume 6, Issue 6, November-December 2024. DOI 10.36948/ijfmr.2024.v06i06.31933
DOI	https://doi.org/10.36948/ijfmr.2024.v06i06.31933
Short DOI	https://doi.org/g8sg5t

View / Download PDF File

E-ISSN 2582-2160

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJFMR DOI prefix is
10.36948/ijfmr

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 6 Isu 6 Cover Page Vol 6 Isu 5 Cover Page Vol 6 Isu 4

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-5948-55	editor@ijfmr.com

International Journal For Multidisciplinary Research

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

Nationwide Landslide Prediction in India Using Neural Networks and Multi-Source Satellite Data.

Share this