Machine Learning and Feature Extraction for Industrial Smoke Plumes Detection from Sentinel-2 Images - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Machine Learning and Feature Extraction for Industrial Smoke Plumes Detection from Sentinel-2 Images

Résumé

The detection of smoke plumes by satellite imagery is a comprehensive research topic that can be used to better monitor activity and emissions from the energy and industrial sectors. In this study, we propose a machine learning methodology based on the extraction of relevant features from Sentinel-2 images to perform industrial smoke plume detection. This computer vision problem is modeled as an image classification task based on the presence or absence of plumes from previously identified sources. A dataset of nearly 17,000 hand-labeled images of smoke plumes for activity classification has been compiled to train and evaluate our detection models. The final Gradient Boosting model only uses the 3 RGB bands of Sentinel-2 and after a post-processing step reaches an accuracy of 95%.
Fichier principal
Vignette du fichier
igarss2023_Smoke_Plume_Detection_v2.pdf (1.69 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04497731 , version 1 (10-03-2024)

Identifiants

Citer

Florentin Poucin, Elyes Ouerghi, Simon Lajouanie, Hugo de Almeida Rodrigues, Gabriele Facciolo, et al.. Machine Learning and Feature Extraction for Industrial Smoke Plumes Detection from Sentinel-2 Images. 2023 IEEE International Geoscience and Remote Sensing Symposium (IGARSS 2023 ), Jul 2023, Pasadena, CA, United States. pp.6113-6116, ⟨10.1109/IGARSS52108.2023.10282662⟩. ⟨hal-04497731⟩
15 Consultations
27 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More