Anomaly detection for the identification of volcanic unrest in satellite imagery

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Popescu, Robert Gabriel, Anantrasirichai, Nantheera, Biggs, Juliet
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917677720666112
author Popescu, Robert Gabriel
Anantrasirichai, Nantheera
Biggs, Juliet
author_facet Popescu, Robert Gabriel
Anantrasirichai, Nantheera
Biggs, Juliet
contents Satellite images have the potential to detect volcanic deformation prior to eruptions, but while a vast number of images are routinely acquired, only a small percentage contain volcanic deformation events. Manual inspection could miss these anomalies, and an automatic system modelled with supervised learning requires suitably labelled datasets. To tackle these issues, this paper explores the use of unsupervised deep learning on satellite data for the purpose of identifying volcanic deformation as anomalies. Our detector is based on Patch Distribution Modeling (PaDiM), and the detection performance is enhanced with a weighted distance, assigning greater importance to features from deeper layers. Additionally, we propose a preprocessing approach to handle noisy and incomplete data points. The final framework was tested with five volcanoes, which have different deformation characteristics and its performance was compared against the supervised learning method for volcanic deformation detection.
format Preprint
id arxiv_https___arxiv_org_abs_2405_18487
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Anomaly detection for the identification of volcanic unrest in satellite imagery
Popescu, Robert Gabriel
Anantrasirichai, Nantheera
Biggs, Juliet
Computer Vision and Pattern Recognition
Image and Video Processing
Satellite images have the potential to detect volcanic deformation prior to eruptions, but while a vast number of images are routinely acquired, only a small percentage contain volcanic deformation events. Manual inspection could miss these anomalies, and an automatic system modelled with supervised learning requires suitably labelled datasets. To tackle these issues, this paper explores the use of unsupervised deep learning on satellite data for the purpose of identifying volcanic deformation as anomalies. Our detector is based on Patch Distribution Modeling (PaDiM), and the detection performance is enhanced with a weighted distance, assigning greater importance to features from deeper layers. Additionally, we propose a preprocessing approach to handle noisy and incomplete data points. The final framework was tested with five volcanoes, which have different deformation characteristics and its performance was compared against the supervised learning method for volcanic deformation detection.
title Anomaly detection for the identification of volcanic unrest in satellite imagery
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2405.18487