Scribd
Upload
5 views

Landslide Detection Using Deep Learning.pptx (4)[1]

The document presents a project on landslide detection using deep learning, highlighting the limitations of traditional methods and proposing a data-driven approach utilizing machine learning. It outlines the process of analyzing satellite images, training a convolutional neural network (CNN), and implementing an automated predictive system. Future work includes improving model accuracy and integrating real-time data.

Uploaded by

Aryan Shukla
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
5 views

Landslide Detection Using Deep Learning.pptx (4)[1]

The document presents a project on landslide detection using deep learning, highlighting the limitations of traditional methods and proposing a data-driven approach utilizing machine learning. It outlines the process of analyzing satellite images, training a convolutional neural network (CNN), and implementing an automated predictive system. Future work includes improving model accuracy and integrating real-time data.

Uploaded by

Aryan Shukla
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

DEPARTMENT OF COMPUTER

ENGINEERING

Landslide Detection Using


Deep Learning

PRESENTED GUIDED
BY
• Harish Prajapati Prof. BY
Ravindra
• Srinjoy Pramanik
Ghugare
• Aryan Shukla
• Ayush Roy
Introduction to Landslide
Detection
Landslides are natural
disasters that cause severe
damage to infrastructure and
human lives.
Traditional detection methods
rely on field surveys and
remote sensing, which are
time-consuming.
Machine learning offers a
faster and more accurate
approach to detecting
landslide-prone areas.
Problem
Statement
1 Difficult 2 Extensive
Prediction Intervention
Due to various Existing methods
environmental require human
factors. intervention and
are prone to
errors.
3 Automated
Approach
Need for a data-driven approach.
Proposed
Solution

Analyze Train Implement


Data Model System
Analyze Train a deep
satellite Predictive
learning
images and system using
model.
topographical CNNs.

data.
Technology
Used
• pandas (for data handling),
• numpy (for numerical computing),
• h5py (for handling .h5 data files),
• glob (for file handling),
• matplotlib.pyplot (for visualization),
• %matplotlib inline (to display plots in Jupyter
Notebook),
• tensorflow (for deep learning models).
Model
Development
Data Collection
1
Gathering satellite images and landslide masks.

2 Data Preprocessing
Normalization, feature extraction.

3 Model Training
Training CNN for segmentation.

4 Model Evaluation
Accuracy, loss function, validation.
Flowchart of Landslide
Detection

Input Data Preprocessing Feature Extraction Model Training

Normalize Extract RGB, Use CNN to


Collect satellite
NDVI, slope, learn patterns
images, elevation, data,
and elevation from labeled
and slope data. extract
features. data.
NDVI.
Conclusion
Enhances Accuracy Automated Systems
Machine learning enhances Reduces the need for
detection accuracy. manual surveys.

Future Work
Improving model accuracy, integrating real-time data.
References

Susceptibility-Guided Landslide Detection Using Fully Convolutional Neural Network

https://www.nrsc.gov.in/sites/default/files/pdf/techtransfer/Detection_of_landslides_from_high_resolution_
optical_satellite

https://ieeexplore.ieee.org/document/
9459015/
https://ieeexplore.ieee.org/document/
10593354/
Literature Review
1] Use of Satellite Data :
Several studies highlight the effectiveness of satellite imagery for landslide mapping:
Singh et al. (2020) demonstrated how Sentinel-2 and Landsat-8 imagery can be used to monitor vegetation and terrain
conditions in landslide-prone areas.
Youssef et al. (2019) used Digital Elevation Models (DEM) to analyze slope and elevation, showing that landslides occur
frequently in regions with steep slopes (>30°) and loose soil.
Lu & Wang (2021) applied NDVI (Normalized Difference Vegetation Index) to assess changes in vegetation cover,
showing that landslide-prone regions often exhibit sudden drops in NDVI values.

2] Digital Elevation Model (DEM) and Terrain Analysis :


DEM-based studies confirm that slope, curvature, and elevation play a significant role in landslide occurrences.
Chen et al. (2020) used Shuttle Radar Topography Mission (SRTM) data to map landslide risks across mountainous
regions.
Thank
You

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy