• Home
  • Search
  • Unsupervised Deep Learning for Landslide Detection from Multispectral Sentinel-2 Imagery
  • Open Access IconOpen Access
  • Cite Icon78
  • https://doi.org/10.3390/rs13224698Copy DOI Icon

Unsupervised Deep Learning for Landslide Detection from Multispectral Sentinel-2 Imagery

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

This paper proposes a new approach based on an unsupervised deep learning (DL) model for landslide detection. Recently, supervised DL models using convolutional neural networks (CNN) have been widely studied for landslide detection. Even though these models provide robust performance and reliable results, they depend highly on a large labeled dataset for their training step. As an alternative, in this paper, we developed an unsupervised learning model by employing a convolutional auto-encoder (CAE) to deal with the problem of limited labeled data for training. The CAE was used to learn and extract the abstract and high-level features without using training data. To assess the performance of the proposed approach, we used Sentinel-2 imagery and a digital elevation model (DEM) to map landslides in three different case studies in India, China, and Taiwan. Using minimum noise fraction (MNF) transformation, we reduced the multispectral dimension to three features containing more than 80% of scene information. Next, these features were stacked with slope data and NDVI as inputs to the CAE model. The Huber reconstruction loss was used to evaluate the inputs. We achieved reconstruction losses ranging from 0.10 to 0.147 for the MNF features, slope, and NDVI stack for all three study areas. The mini-batch K-means clustering method was used to cluster the features into two to five classes. To evaluate the impact of deep features on landslide detection, we first clustered a stack of MNF features, slope, and NDVI, then the same ones plus with the deep features. For all cases, clustering based on deep features provided the highest precision, recall, F1-score, and mean intersection over the union in landslide detection.

Loading PDF

Similar Papers
  • Conference Article
  • Citations9

Rapid Mapping of Landslides from Sentinel-2 Data Using Unsupervised Deep Learning

  • Mar 07, 2022
  • H Shahabi +6
  • PDF
  • Research Article
  • Citations16

An Unsupervised Deep Feature Learning Model Based on Parallel Convolutional Autoencoder for Intelligent Fault Diagnosis of Main Reducer

  • Jan 01, 2021
  • Computational Intelligence and Neuroscience
  • Qing Ye +1
  • Research Article
  • Citations23

Applying image transformation and classification techniques to airborne hyperspectral imagery for mapping Ashe juniper infestations

  • Jun 10, 2009
  • International Journal of Remote Sensing
  • Chenghai Yang +2
  • PDF
  • Research Article
  • Citations64

Synergistic Use of Multi-Temporal RADARSAT-2 and VENµS Data for Crop Classification Based on 1D Convolutional Neural Network

  • Mar 04, 2020
  • Remote Sensing
  • Chunhua Liao +6
  • Conference Article
  • Citations3

SAR Object Classification with a Multi-Scale Convolutional Auto-Encoder

  • Aug 01, 2019
  • Sirui Tian +2
  • Conference Article
  • Citations2

Anomaly detection of multivariate image time series based on Gramian angular field using convolutional autoencoder

  • Dec 09, 2022
  • Fatih Sultan Bayram +3
  • Preprint Article
  • Citations1

DTM-based landslide detection using deep learning: A case study in Hong Kong

  • Mar 23, 2020
  • Haojie Wang +1
  • Research Article
  • Citations7

DL-EDOF: Novel Multi-Focus Image Data Set and Deep Learning-Based Approach for More Accurate and Specimen-Free Extended Depth of Focus.

  • Mar 25, 2024
  • Journal of imaging informatics in medicine
  • Hulya Dogan +3
  • PDF
  • Research Article
  • Citations180

Landslide Detection Using Residual Networks and the Fusion of Spectral and Topographic Information

  • Jan 01, 2019
  • IEEE Access
  • Maher Ibrahim Sameen +1
  • PDF
  • Research Article
  • Citations21

An Efficient Multi-Sensor Remote Sensing Image Clustering in Urban Areas via Boosted Convolutional Autoencoder (BCAE)

  • Jun 26, 2021
  • Remote Sensing
  • Maryam Rahimzad +3
  • Conference Article

Processing and analyzing advanced hyperspectral imagery data

  • Sep 29, 2006
  • Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE
  • A H El-Nahry
  • Research Article
  • Citations14

Contribution of Minimum Noise Fraction Transformation of Multi-temporal RADARSAT-2 Polarimetric SAR Data to Cropland Classification

  • May 04, 2018
  • Canadian Journal of Remote Sensing
  • Chunhua Liao +3
  • Research Article
  • Citations6

Superpixel-Based Minimum Noise Fraction Feature Extraction for Classification of Hyperspectral Images

  • Nov 25, 2020
  • Traitement du Signal
  • Behnam Asghari Beirami +1
  • Research Article
  • Citations13

Integrating Zhuhai-1 Hyperspectral Imagery With Sentinel-2 Multispectral Imagery to Improve High-Resolution Impervious Surface Area Mapping

  • Jan 01, 2022
  • IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
  • Xiaoxiao Feng +5
  • Research Article
  • Citations27

Multi-level supervised hashing with deep features for efficient image retrieval

  • Feb 14, 2020
  • Neurocomputing
  • Wing W.Y Ng +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.