Articles | Volume 8, issue 3
https://doi.org/10.5194/esd-8-677-2017
https://doi.org/10.5194/esd-8-677-2017
Research article
 | 
08 Aug 2017
Research article |  | 08 Aug 2017

Multivariate anomaly detection for Earth observations: a comparison of algorithms and feature extraction techniques

Milan Flach, Fabian Gans, Alexander Brenning, Joachim Denzler, Markus Reichstein, Erik Rodner, Sebastian Bathiany, Paul Bodesheim, Yanira Guanche, Sebastian Sippel, and Miguel D. Mahecha

Viewed

Total article views: 6,275 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
3,611 2,416 248 6,275 256 168 179
  • HTML: 3,611
  • PDF: 2,416
  • XML: 248
  • Total: 6,275
  • Supplement: 256
  • BibTeX: 168
  • EndNote: 179
Views and downloads (calculated since 02 Nov 2016)
Cumulative views and downloads (calculated since 02 Nov 2016)

Viewed (geographical distribution)

Total article views: 6,275 (including HTML, PDF, and XML) Thereof 5,996 with geography defined and 279 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Latest update: 14 Dec 2024
Download
Short summary
Anomalies and extremes are often detected using univariate peak-over-threshold approaches in the geoscience community. The Earth system is highly multivariate. We compare eight multivariate anomaly detection algorithms and combinations of data preprocessing. We identify three anomaly detection algorithms that outperform univariate extreme event detection approaches. The workflows have the potential to reveal novelties in data. Remarks on their application to real Earth observations are provided.
Altmetrics
Final-revised paper
Preprint