Detection of Forest Fires through Deep Unsupervised Learning Modeling of Sentinel-1 Time Series - Laboratoire franco-singapourien de recherche en électromagnétisme et radars Access content directly
Journal Articles ISPRS International Journal of Geo-Information Year : 2023

Detection of Forest Fires through Deep Unsupervised Learning Modeling of Sentinel-1 Time Series

Abstract

With an increase in the amount of natural disasters, the combined use of cloud-penetrating Synthetic Aperture Radar and deep learning becomes unavoidable for their monitoring. This article proposes a methodology for forest fire detection using unsupervised location-expert autoencoders and Sentinel-1 SAR time series. The models are trained on SAR multitemporal images over a specific area using a reference period and extract any deviating time series over that same area for the test period. We present three variations of the autoencoder, incorporating either temporal features or spatiotemporal features, and we compare it against a state-of-the-art supervised autoencoder. Despite their limitations, we show that unsupervised approaches are on par with supervised techniques, performance-wise. A specific architecture, the fully temporal autoencoder, stands out as the best-performing unsupervised approach by leveraging temporal information of Sentinel-1 time series using one-dimensional convolutional layers. The approach is generic and can be applied to many applications, though we focus here on forest fire detection in Canadian boreal forests as a successful use case.
Fichier principal
Vignette du fichier
IJGI___Proofread-2.pdf (42.69 Mo) Télécharger le fichier
Origin Publisher files allowed on an open archive
licence

Dates and versions

hal-04215824 , version 1 (22-09-2023)

Licence

Identifiers

Cite

Thomas Di Martino, Bertrand Le Saux, Régis Guinvarc’h, Laetitia Thirion-Lefevre, Elise Colin. Detection of Forest Fires through Deep Unsupervised Learning Modeling of Sentinel-1 Time Series. ISPRS International Journal of Geo-Information, 2023, 12 (8), pp.332. ⟨10.3390/ijgi12080332⟩. ⟨hal-04215824⟩
33 View
3 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More