Articles | Volume 8, issue 3
https://doi.org/10.5194/esd-8-677-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 3.0 License.
the Creative Commons Attribution 3.0 License.
https://doi.org/10.5194/esd-8-677-2017
© Author(s) 2017. This work is distributed under
the Creative Commons Attribution 3.0 License.
the Creative Commons Attribution 3.0 License.
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
CORRESPONDING AUTHOR
Max Planck Institute for Biogeochemistry, Department Biogeochemical Integration, P.O. Box 10 01 64, 07701 Jena, Germany
Fabian Gans
Max Planck Institute for Biogeochemistry, Department Biogeochemical Integration, P.O. Box 10 01 64, 07701 Jena, Germany
Alexander Brenning
Friedrich Schiller University Jena, Department of Geography, Jena, Germany
Michael Stifel Center Jena for Data-driven and Simulation Science, Jena, Germany
Joachim Denzler
Friedrich Schiller University of Jena, Department of Mathematics and Computer Sciences, Computer Vision Group, Jena, Germany
Michael Stifel Center Jena for Data-driven and Simulation Science, Jena, Germany
German Centre for Integrative Biodiversity Research (iDiv), Leipzig, Germany
Markus Reichstein
Max Planck Institute for Biogeochemistry, Department Biogeochemical Integration, P.O. Box 10 01 64, 07701 Jena, Germany
Michael Stifel Center Jena for Data-driven and Simulation Science, Jena, Germany
German Centre for Integrative Biodiversity Research (iDiv), Leipzig, Germany
Erik Rodner
Friedrich Schiller University of Jena, Department of Mathematics and Computer Sciences, Computer Vision Group, Jena, Germany
Michael Stifel Center Jena for Data-driven and Simulation Science, Jena, Germany
Sebastian Bathiany
Wageningen University, Department of Environmental Sciences, Wageningen, the Netherlands
Paul Bodesheim
Max Planck Institute for Biogeochemistry, Department Biogeochemical Integration, P.O. Box 10 01 64, 07701 Jena, Germany
Yanira Guanche
Friedrich Schiller University of Jena, Department of Mathematics and Computer Sciences, Computer Vision Group, Jena, Germany
Michael Stifel Center Jena for Data-driven and Simulation Science, Jena, Germany
Sebastian Sippel
Max Planck Institute for Biogeochemistry, Department Biogeochemical Integration, P.O. Box 10 01 64, 07701 Jena, Germany
Miguel D. Mahecha
Max Planck Institute for Biogeochemistry, Department Biogeochemical Integration, P.O. Box 10 01 64, 07701 Jena, Germany
Michael Stifel Center Jena for Data-driven and Simulation Science, Jena, Germany
German Centre for Integrative Biodiversity Research (iDiv), Leipzig, Germany
Viewed
Total article views: 5,694 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 02 Nov 2016)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 3,242 | 2,235 | 217 | 5,694 | 232 | 142 | 157 |
- HTML: 3,242
- PDF: 2,235
- XML: 217
- Total: 5,694
- Supplement: 232
- BibTeX: 142
- EndNote: 157
Total article views: 3,996 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 08 Aug 2017)
| HTML | XML | Total | Supplement | BibTeX | EndNote | |
|---|---|---|---|---|---|---|
| 2,403 | 1,407 | 186 | 3,996 | 232 | 133 | 129 |
- HTML: 2,403
- PDF: 1,407
- XML: 186
- Total: 3,996
- Supplement: 232
- BibTeX: 133
- EndNote: 129
Total article views: 1,698 (including HTML, PDF, and XML)
Cumulative views and downloads
(calculated since 02 Nov 2016)
| HTML | XML | Total | BibTeX | EndNote | |
|---|---|---|---|---|---|
| 839 | 828 | 31 | 1,698 | 9 | 28 |
- HTML: 839
- PDF: 828
- XML: 31
- Total: 1,698
- BibTeX: 9
- EndNote: 28
Viewed (geographical distribution)
Total article views: 5,694 (including HTML, PDF, and XML)
Thereof 5,429 with geography defined
and 265 with unknown origin.
Total article views: 3,996 (including HTML, PDF, and XML)
Thereof 3,765 with geography defined
and 231 with unknown origin.
Total article views: 1,698 (including HTML, PDF, and XML)
Thereof 1,664 with geography defined
and 34 with unknown origin.
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Country | # | Views | % |
|---|
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
| Total: | 0 |
| HTML: | 0 |
| PDF: | 0 |
| XML: | 0 |
- 1
1
Cited
21 citations as recorded by crossref.
- Edge Detection Reveals Abrupt and Extreme Climate Events S. Bathiany et al. 10.1175/JCLI-D-19-0449.1
- A Unifying Review of Deep and Shallow Anomaly Detection L. Ruff et al. 10.1109/JPROC.2021.3052449
- Vegetation modulates the impact of climate extremes on gross primary production M. Flach et al. 10.5194/bg-18-39-2021
- Summarizing the state of the terrestrial biosphere in few dimensions G. Kraemer et al. 10.5194/bg-17-2397-2020
- Drought, Heat, and the Carbon Cycle: a Review S. Sippel et al. 10.1007/s40641-018-0103-4
- An In-Memory Data-Cube Aware Distributed Data Discovery Across Clouds for Remote Sensing Big Data J. Song et al. 10.1109/JSTARS.2023.3267118
- Contrasting biosphere responses to hydrometeorological extremes: revisiting the 2010 western Russian heatwave M. Flach et al. 10.5194/bg-15-6067-2018
- A typology of compound weather and climate events J. Zscheischler et al. 10.1038/s43017-020-0060-z
- On Equivalence of Anomaly Detection Algorithms C. Jerez et al. 10.1145/3536428
- Detecting impacts of extreme events with ecological in situ monitoring networks M. Mahecha et al. 10.5194/bg-14-4255-2017
- Earth system data cubes unravel global multivariate dynamics M. Mahecha et al. 10.5194/esd-11-201-2020
- Water rationalization in Brazilian irrigated agriculture F. Viana et al. 10.33158/ASB.r154.v8.2022
- Regional asymmetry in the response of global vegetation growth to springtime compound climate events J. Li et al. 10.1038/s43247-022-00455-0
- Impacts of droughts and extreme-temperature events on gross primary production and ecosystem respiration: a systematic assessment across ecosystems and climate zones J. von Buttlar et al. 10.5194/bg-15-1293-2018
- Compound droughts and hot extremes: Characteristics, drivers, changes, and impacts Z. Hao et al. 10.1016/j.earscirev.2022.104241
- ACVAE: A novel self-adversarial variational auto-encoder combined with contrast learning for time series anomaly detection X. Zhang et al. 10.1016/j.neunet.2023.12.023
- Past abrupt changes, tipping points and cascading impacts in the Earth system V. Brovkin et al. 10.1038/s41561-021-00790-5
- The effects of varying drought-heat signatures on terrestrial carbon dynamics and vegetation composition E. Tschumi et al. 10.5194/bg-19-1979-2022
- Wetter summers can intensify departures from natural variability in a warming climate C. Mahony & A. Cannon 10.1038/s41467-018-03132-z
- Extreme anomaly event detection in biosphere using linear regression and a spatiotemporal MRF model Y. Guanche García et al. 10.1007/s11069-018-3415-8
- Building an Earth Observations Data Cube: lessons learned from the Swiss Data Cube (SDC) on generating Analysis Ready Data (ARD) G. Giuliani et al. 10.1080/20964471.2017.1398903
20 citations as recorded by crossref.
- Edge Detection Reveals Abrupt and Extreme Climate Events S. Bathiany et al. 10.1175/JCLI-D-19-0449.1
- A Unifying Review of Deep and Shallow Anomaly Detection L. Ruff et al. 10.1109/JPROC.2021.3052449
- Vegetation modulates the impact of climate extremes on gross primary production M. Flach et al. 10.5194/bg-18-39-2021
- Summarizing the state of the terrestrial biosphere in few dimensions G. Kraemer et al. 10.5194/bg-17-2397-2020
- Drought, Heat, and the Carbon Cycle: a Review S. Sippel et al. 10.1007/s40641-018-0103-4
- An In-Memory Data-Cube Aware Distributed Data Discovery Across Clouds for Remote Sensing Big Data J. Song et al. 10.1109/JSTARS.2023.3267118
- Contrasting biosphere responses to hydrometeorological extremes: revisiting the 2010 western Russian heatwave M. Flach et al. 10.5194/bg-15-6067-2018
- A typology of compound weather and climate events J. Zscheischler et al. 10.1038/s43017-020-0060-z
- On Equivalence of Anomaly Detection Algorithms C. Jerez et al. 10.1145/3536428
- Detecting impacts of extreme events with ecological in situ monitoring networks M. Mahecha et al. 10.5194/bg-14-4255-2017
- Earth system data cubes unravel global multivariate dynamics M. Mahecha et al. 10.5194/esd-11-201-2020
- Water rationalization in Brazilian irrigated agriculture F. Viana et al. 10.33158/ASB.r154.v8.2022
- Regional asymmetry in the response of global vegetation growth to springtime compound climate events J. Li et al. 10.1038/s43247-022-00455-0
- Impacts of droughts and extreme-temperature events on gross primary production and ecosystem respiration: a systematic assessment across ecosystems and climate zones J. von Buttlar et al. 10.5194/bg-15-1293-2018
- Compound droughts and hot extremes: Characteristics, drivers, changes, and impacts Z. Hao et al. 10.1016/j.earscirev.2022.104241
- ACVAE: A novel self-adversarial variational auto-encoder combined with contrast learning for time series anomaly detection X. Zhang et al. 10.1016/j.neunet.2023.12.023
- Past abrupt changes, tipping points and cascading impacts in the Earth system V. Brovkin et al. 10.1038/s41561-021-00790-5
- The effects of varying drought-heat signatures on terrestrial carbon dynamics and vegetation composition E. Tschumi et al. 10.5194/bg-19-1979-2022
- Wetter summers can intensify departures from natural variability in a warming climate C. Mahony & A. Cannon 10.1038/s41467-018-03132-z
- Extreme anomaly event detection in biosphere using linear regression and a spatiotemporal MRF model Y. Guanche García et al. 10.1007/s11069-018-3415-8
Latest update: 17 Apr 2024
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.
Anomalies and extremes are often detected using univariate peak-over-threshold approaches in the...
Altmetrics
Final-revised paper
Preprint