Dépôt numérique
RECHERCHER

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

Téléchargements

Téléchargements par mois depuis la dernière année

Plus de statistiques...

Shahabi, Hejar; Rahimzad, Maryam; Tavakkoli Piralilou, Sepideh; Ghorbanzadeh, Omid; Homayouni, Saeid ORCID logoORCID: https://orcid.org/0000-0002-0214-5356; Blaschke, Thomas; Lim, Samsung et Ghamisi, Pedram (2021). Unsupervised Deep Learning for Landslide Detection from Multispectral Sentinel-2 Imagery. Remote Sensing , vol. 13 , nº 22. p. 4698. DOI: 10.3390/rs13224698.

[thumbnail of P4223.pdf]
Prévisualisation
PDF
Télécharger (5MB) | Prévisualisation

Résumé

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.

Type de document: Article
Mots-clés libres: landslide mapping; remote sensing; unsupervised feature learning; convolutional auto-encoder (CAE); mini-batch K-means
Centre: Centre Eau Terre Environnement
Date de dépôt: 17 mai 2023 15:13
Dernière modification: 17 mai 2023 15:13
URI: https://espace.inrs.ca/id/eprint/13311

Gestion Actions (Identification requise)

Modifier la notice Modifier la notice