A pattern-based method for handling confidence measures while mining satellite displacement field time series. Application to Greenland ice sheet and Alpine glaciers

Tuan Nguyen; Nicolas Méger; Christophe Rigotti; Catherine Pothier; Emmanuel Trouvé; Noel Gourmelen; Jean-Louis Mugnier

A pattern-based method for handling confidence measures while mining satellite displacement field time series. Application to Greenland ice sheet and Alpine glaciers

Tuan Nguyen ^{1, 2, 3, 4} Nicolas Méger ^{1, 2, 3} Christophe Rigotti ^{5, 4, 6} Catherine Pothier ⁷ Emmanuel Trouvé ^{1, 2, 3} Noel Gourmelen ⁸ Jean-Louis Mugnier ^{1, 9, 10}

1 USMB [Université de Savoie] [Université de Chambéry] - Université Savoie Mont Blanc

2 EPU [Ecole Polytechnique Universitaire de l'Université de Savoie] - Polytech Annecy-Chambéry

3 LISTIC - Laboratoire d'Informatique, Systèmes, Traitement de l'Information et de la Connaissance

4 DM2L - Data Mining and Machine Learning

LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information

5 LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information

6 BEAGLE - Artificial Evolution and Computational Biology

LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information, Inria Grenoble - Rhône-Alpes, LBBE - Laboratoire de Biométrie et Biologie Evolutive - UMR 5558

7 imagine - Extraction de Caractéristiques et Identification

LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information

8 School of Geosciences [Edinburgh]

9 CNRS - Centre National de la Recherche Scientifique

10 ISTerre - Institut des Sciences de la Terre

Abstract : For more than 40 years, Earth observation satellites have been regularly providing images of glaciers that can be used to derive surface displacement fields and study their dynamics. In the context of global warming, the analysis of Displacement Field Time Series (DFTS) can provide useful information. Efficient data mining techniques are thus required to extract meaningful displacement evolutions from such large and complex datasets. In this paper, a pattern-based data mining approach which handles confidence measures is proposed to analyze DFTS. In order to focus on the most reliable measurements, a displacement evolution reliability measure is defined. It is aimed at assessing the quality of each evolution and pruning the search space. Experiments on two different DFTS (annual displacement fields derived from optical data over Greenland ice sheet and 11-day displacement fields derived from SAR data over Alpine glaciers) show the potential of the proposed approach.

Keywords : climate change glacier dynamics Satellite image time series (SITS) confidence measure displacement field time series (DFTS) data mining

Document type :

Journal articles

Domain :

Computer Science [cs] / Machine Learning [cs.LG]

Sciences of the Universe [physics] / Earth Sciences

Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01912708
Contributor : Nicolas Méger <>
Submitted on : Tuesday, November 6, 2018 - 11:24:26 AM
Last modification on : Friday, April 5, 2019 - 8:21:16 PM
Long-term archiving on : Thursday, February 7, 2019 - 12:35:45 PM

main.pdf

Files produced by the author(s)

A pattern-based method for handling confidence measures while mining satellite displacement field time series. Application to Greenland ice sheet and Alpine glaciers

File

Identifiers

Collections

Citation

Export

Metrics

315

86

Contact

A pattern-based method for handling confidence measures while mining satellite displacement field time series. Application to Greenland ice sheet and Alpine glaciers

File

Identifiers

Collections

Citation

Export

Share

Metrics

315

86

Contact