research-article

Open access

Variational Autoencoder Anomaly-Detection of Avalanche Deposits in Satellite SAR Imagery

Authors:

Sophie Giffard-Roisin,

Michael Deschatres,

Nicolas Eckert,

Cécile Coléou,

Claire MonteleoniAuthors Info & Claims

CI2020: Proceedings of the 10th International Conference on Climate Informatics

Pages 113 - 119

https://doi.org/10.1145/3429309.3429326

Published: 11 January 2021 Publication History

Abstract

This work demonstrates that deep unsupervised learning holds much promise for rare event detection, even when labeled data is limited. Rare event detection is challenging for traditional supervised learning approaches due to high class-imbalance. We demonstrate the efficacy of deep unsupervised learning, in particular a variational autoencoder (VAE), when used for anomaly detection, in an application to avalanche detection in the French Alps, from satellite SAR imagery and a limited on-the-ground survey. Remarkably, our results demonstrate that supervision (i.e., access to labeled data) is only needed in the validation phase of our training pipeline, to tune a hyper-parameter: the threshold on reconstruction error of the VAE (trained in an unsupervised fashion) that will be used to designate an observation as an anomaly, i.e., an avalanche in this context.

Our method outperforms previous benchmarks in avalanche detection, including supervised learning a convolutional neural network on an artificially balanced version of the same data. To the best of our knowledge, this is the first step in exploring the potential of applying deep unsupervised learning methods to detect avalanche deposits. Our proposed semi-supervised learning pipeline is also promising for real-world settings in which the data is very unbalanced and labels are limited.

References

[1]

Haleh Akrami, Anand A. Joshi, Jian Li, and Richard M. Leahy. 2019. Robust Variational Autoencoder. CoRR abs/1905.09961(2019). arxiv:1905.09961http://arxiv.org/abs/1905.09961

[2]

Jinwon An and Sungzoon Cho. 2015. Variational autoencoder based anomaly detection using reconstruction probability. Special Lecture on IE 2, 1 (2015).

[3]

Filippo Maria Bianchi, Jakob Grahn, Markus Eckerstorfer, Eirik Malnes, and Hannah Vickers. 2019. Snow avalanche segmentation in SAR images with Fully Convolutional Neural Networks. arXiv preprint arXiv:1910.05411(2019).

[4]

Christopher M Bishop. 2006. Pattern recognition and machine learning. Springer Science+ Business Media.

Digital Library

[5]

Gilles Blanchard, Gyemin Lee, and Clayton Scott. 2010. Semi-supervised novelty detection. Journal of Machine Learning Research 11, Nov (2010), 2973–3009.

[6]

Varun Chandola, Arindam Banerjee, and Vipin Kumar. 2009. Anomaly detection: A survey. ACM computing surveys (CSUR) 41, 3 (2009), 15.

Digital Library

[7]

Xiaoran Chen and Ender Konukoglu. 2018. Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders. arXiv preprint arXiv:1806.04972(2018).

[8]

Lucas Deecke, Robert Vandermeulen, Lukas Ruff, Stephan Mandt, and Marius Kloft. 2018. Anomaly detection with generative adversarial networks. (2018).

[9]

Markus Eckerstorfer, Yves Bühler, Regula Frauenfelder, and Eirik Malnes. 2016. Remote sensing of snow avalanches: Recent advances, potential, and limitations. Cold Regions Science and Technology 121 (2016), 126–140.

[10]

Markus Eckerstorfer and Eirik Malnes. 2015. Manual detection of snow avalanche debris using high-resolution Radarsat-2 SAR images. Cold Regions Science and Technology 120 (2015), 205–218.

[11]

Markus Eckerstorfer, Eirik Malnes, and Karsten Müller. 2017. A complete snow avalanche activity record from a Norwegian forecasting region using Sentinel-1 satellite-radar data. Cold regions science and technology 144 (2017), 39–51.

[12]

Jie Geng, Jianchao Fan, Hongyu Wang, Xiaorui Ma, Baoming Li, and Fuliang Chen. 2015. High-resolution SAR image classification via deep convolutional autoencoders. IEEE Geoscience and Remote Sensing Letters 12, 11 (2015), 2351–2355.

[13]

Izhak Golan and Ran El-Yaniv. 2018. Deep anomaly detection using geometric transformations. In Advances in Neural Information Processing Systems. 9758–9769.

[14]

Jarle Bauck Hamar, Arnt-Børre Salberg, and Florina Ardelean. 2016. Automatic detection and mapping of avalanches in sar images. In 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). IEEE, 689–692.

[15]

Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. 2017. beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework.ICLR 2, 5 (2017), 6.

[16]

Michael Kampffmeyer, Arnt-Borre Salberg, and Robert Jenssen. 2016. Semantic segmentation of small objects and modeling of uncertainty in urban remote sensing images using deep convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 1–9.

[17]

Fatima Karbou, Cécile Coléou, Maxime Lefort, Michael Deschatres, Nicolas Eckert, Rémy Martin, Gilles Charvet, and Anne Dufour. 2018. Monitoring avalanche debris in the French mountains using SAR observations from Sentinel-1 satellites. In International snow science workshop (ISSW).

[18]

Fatima Karbou, Maxime Lefort, Marie Dumont, Nicolas Eckert, Michael Deschrtres, and Rémy Martin. 2018. Multi-temporal avalanche debris mapping in the French mountains using synthetic aperture radar observations from Sentinel-1. In EGU General Assembly Conference Abstracts, Vol. 20. 18024.

[19]

Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114(2013).

[20]

B Kiran, Dilip Thomas, and Ranjith Parakkal. 2018. An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos. Journal of Imaging 4, 2 (2018), 36.

[21]

Per Egil Kummervold, Eirik Malnes, Markus Eckerstorfer, Ingar M Arntzen, and Fillipo Bianchi. 2018. Avalanche detection in Sentinel-1 radar images using convolutional neural networks. In Proceedings of the International Snow Science Workshop. 377–381.

[22]

Fei Tony Liu, Kai Ming Ting, and Zhi-Hua Zhou. 2012. Isolation-based anomaly detection. ACM Transactions on Knowledge Discovery from Data (TKDD) 6, 1(2012), 3.

[23]

Yuchen Lu and Peng Xu. 2018. Anomaly detection for skin disease images using variational autoencoder. arXiv preprint arXiv:1807.01349(2018).

[24]

Luigi T Luppino, Filippo M Bianchi, Gabriele Moser, and Stian N Anfinsen. 2019. Unsupervised image regression for heterogeneous change detection. arXiv preprint arXiv:1909.05948(2019).

[25]

Alireza Makhzani, Jonathon Shlens, Navdeep Jaitly, Ian Goodfellow, and Brendan Frey. 2015. Adversarial autoencoders. arXiv preprint arXiv:1511.05644(2015).

[26]

Otávio AB Penatti, Keiller Nogueira, and Jefersson A Dos Santos. 2015. Do deep features generalize from everyday objects to remote sensing and aerial scenes domains?. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops. 44–51.

[27]

Yu Qi, Yueming Wang, Xiaoxiang Zheng, and Zhaohui Wu. 2014. Robust feature learning by stacked autoencoder with maximum correntropy criterion. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 6716–6720.

[28]

Alec Radford, Luke Metz, and Soumith Chintala. 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv preprint arXiv:1511.06434(2015).

[29]

Mohammad Sabokrou, Mohammad Khalooei, and Ehsan Adeli. 2019. Self-Supervised Representation Learning via Neighborhood-Relational Encoding. In Proceedings of the IEEE International Conference on Computer Vision. 8010–8019.

[30]

Mayu Sakurada and Takehisa Yairi. 2014. Anomaly detection using autoencoders with nonlinear dimensionality reduction. In Proceedings of the MLSDA 2014 2nd Workshop on Machine Learning for Sensory Data Analysis. ACM, 4.

Digital Library

[31]

Thomas Schlegl, Philipp Seeböck, Sebastian M Waldstein, Ursula Schmidt-Erfurth, and Georg Langs. 2017. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. In International Conference on Information Processing in Medical Imaging. Springer, 146–157.

[32]

Bernhard Schölkopf, Robert C Williamson, Alex J Smola, John Shawe-Taylor, and John C Platt. 2000. Support vector method for novelty detection. In Advances in neural information processing systems. 582–588.

[33]

Saumya Sinha, Sophie Giffard-Roisin, Fatima Karbou, Michaël Deschatres, Anna Karas, Nicolas Eckert, Cécile Coléou, and Claire Monteleoni. 2019. Can avalanche deposits be effectively detected by deep learning on sentinel-1 satellite sar images?. In Climate Informatics.

[34]

Ilya Tolstikhin, Olivier Bousquet, Sylvain Gelly, and Bernhard Schoelkopf. 2017. Wasserstein auto-encoders. arXiv preprint arXiv:1711.01558(2017).

[35]

Pascal Vincent, Hugo Larochelle, Yoshua Bengio, and Pierre-Antoine Manzagol. 2008. Extracting and composing robust features with denoising autoencoders. In Proceedings of the 25th international conference on Machine learning. ACM, 1096–1103.

Digital Library

[36]

Anders U Waldeland, Jarle Hamar Reksten, and Arnt-Borre Salberg. 2018. Avalanche Detection in Sar Images Using Deep Learning. In IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2386–2389.

[37]

Dieuwertje S Wesselink, Eirik Malnes, Markus Eckerstorfer, and Roderik C Lindenbergh. 2017. Automatic detection of snow avalanche debris in central Svalbard using C-band SAR data. Polar Research 36, 1 (2017), 1333236.

[38]

David Wingate and Theophane Weber. 2013. Automated variational inference in probabilistic programming. arXiv preprint arXiv:1301.1299(2013).

[39]

Yan Xia, Xudong Cao, Fang Wen, Gang Hua, and Jian Sun. 2015. Learning discriminative reconstructions for unsupervised outlier removal. In Proceedings of the IEEE International Conference on Computer Vision. 1511–1519.

Digital Library

[40]

Chong Zhou and Randy C Paffenroth. 2017. Anomaly detection with robust deep autoencoders. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 665–674.

Digital Library

Cited By

Choi JJeon BJeon C(2024)Scalable Learning Framework for Detecting New Types of Twitter Spam with Misuse and Anomaly DetectionSensors10.3390/s2407226324:7(2263)Online publication date: 2-Apr-2024
https://doi.org/10.3390/s24072263
Li JWang XZhao HZhong Y(2024)Learning a Cross-Modality Anomaly Detector for Remote Sensing ImageryIEEE Transactions on Image Processing10.1109/TIP.2024.349089433(6607-6621)Online publication date: 2024
https://doi.org/10.1109/TIP.2024.3490894
Li JZhong YZhao HGao ZWang X(2024)Segmenting Remote Sensing Anomalies at Instance Level via Anomaly Map-Guided AdaptationIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2024.343949162(1-16)Online publication date: 2024
https://doi.org/10.1109/TGRS.2024.3439491
Show More Cited By

Variational Autoencoder Anomaly-Detection of Avalanche Deposits in Satellite SAR Imagery
1. Computing methodologies

Recommendations

Self-adversarial variational autoencoder with spectral residual for time series anomaly detection
Abstract
Detecting anomalies accurately in time series data has been receiving considerable attention due to its enormous potential for a wide array of applications. Numerous unsupervised anomaly detection methods for time series have been developed ...
Semisupervised SAR image change detection based on a siamese variational autoencoder
Abstract
In synthetic aperture radar (SAR) image change detection, the deep learning has attracted increasingly more attention because the difference images (DIs) of traditional unsupervised technology are vulnerable to speckle noise. However, ...
Highlights
- This method introduces the variational autoencoder (VAE) for feature learning.
- ...
Autoencoding Binary Classifiers for Supervised Anomaly Detection
PRICAI 2019: Trends in Artificial Intelligence
Abstract
We propose the Autoencoding Binary Classifiers (ABC), a novel supervised anomaly detector based on the Autoencoder (AE). There are two main approaches in anomaly detection: supervised and unsupervised. The supervised approach accurately detects ...

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences

CI2020: Proceedings of the 10th International Conference on Climate Informatics

September 2020

138 pages

ISBN:9781450388481

DOI:10.1145/3429309

Copyright © 2020 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 11 January 2021

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Conference

CI2020

CI2020: 10th International Conference on Climate Informatics

September 22 - 25, 2020

virtual, United Kingdom

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
1,151
Total Downloads

Downloads (Last 12 months)238
Downloads (Last 6 weeks)32

Reflects downloads up to 27 Feb 2025

Other Metrics

View Author Metrics

Citations

Cited By

Choi JJeon BJeon C(2024)Scalable Learning Framework for Detecting New Types of Twitter Spam with Misuse and Anomaly DetectionSensors10.3390/s2407226324:7(2263)Online publication date: 2-Apr-2024
https://doi.org/10.3390/s24072263
Li JWang XZhao HZhong Y(2024)Learning a Cross-Modality Anomaly Detector for Remote Sensing ImageryIEEE Transactions on Image Processing10.1109/TIP.2024.349089433(6607-6621)Online publication date: 2024
https://doi.org/10.1109/TIP.2024.3490894
Li JZhong YZhao HGao ZWang X(2024)Segmenting Remote Sensing Anomalies at Instance Level via Anomaly Map-Guided AdaptationIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2024.343949162(1-16)Online publication date: 2024
https://doi.org/10.1109/TGRS.2024.3439491
Gella GGangloff HWendt LTiede DLang S(2024)Self-Supervised Variational Autoencoder for Unsupervised Object Counting from Very-High-Resolution Satellite Imagery: Applications in Dwelling Extraction in FDP Settlement AreasIEEE Transactions on Geoscience and Remote Sensing10.1109/TGRS.2023.334517962(1-18)Online publication date: 2024
https://doi.org/10.1109/TGRS.2023.3345179
Schlaffer SSchlögl M(2024)Snow Avalanche Debris Analysis Using Time Series of Dual-Polarimetric Synthetic Aperture Radar DataIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing10.1109/JSTARS.2024.342340317(12567-12578)Online publication date: 2024
https://doi.org/10.1109/JSTARS.2024.3423403
Hao JHuang KChen CMao J(2024)Dual-student knowledge distillation for visual anomaly detectionComplex & Intelligent Systems10.1007/s40747-024-01412-410:4(4853-4865)Online publication date: 9-Apr-2024
https://doi.org/10.1007/s40747-024-01412-4
Ma ZMei GXu N(2024)Generative deep learning for data generation in natural hazard analysis: motivations, advances, challenges, and opportunitiesArtificial Intelligence Review10.1007/s10462-024-10764-957:6Online publication date: 30-May-2024
https://doi.org/10.1007/s10462-024-10764-9
Khan SMishra PYe BNewman KIaboni AMihailidis A(2023)Empirical Thresholding on Spatio-Temporal Autoencoders Trained on Surveillance Videos in a Dementia Care Unit2023 20th Conference on Robots and Vision (CRV)10.1109/CRV60082.2023.00041(265-272)Online publication date: Jun-2023
https://doi.org/10.1109/CRV60082.2023.00041
Muzeau MRen CAngelliaume SDatcu MOvarlez J(2022)Self-Supervised Learning Based Anomaly Detection in Synthetic Aperture Radar ImagingIEEE Open Journal of Signal Processing10.1109/OJSP.2022.32296183(440-449)Online publication date: 2022
https://doi.org/10.1109/OJSP.2022.3229618
Wu YZhao ZPang XLiu J(2022)Clustering memory-guided anomaly detection model for large-scale screening of esophageal endoscopic imagesJournal of Computational Design and Engineering10.1093/jcde/qwac0739:4(1525-1537)Online publication date: 1-Aug-2022
https://doi.org/10.1093/jcde/qwac073
Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Figures

Tables

Media

View Table of Conten