explore satellite image time series
SITS-P2miner: for extracting and ranking maximal Grouped Frequent Sequential patterns (GFS-patterns) from Satellite Image Times Series (SITS). It includes SPATPAM and also implements our latest ranking procedures (swap randomization, normalized mutual information). A quantization procedure (equal frequency bucketting) and a pattern clustering module (hierarchical, Levenshtein distance) are embodied. A running example is made available. It relies on an NDVI SITS kindly provided by Rémi Andreoli (Bluecham SAS).
Ranking Evolution Maps for Satellite Image Time Series Exploration – Application to Crustal Deformation and Environmental Monitoring. N. Méger, C. Rigotti, C. Pothier, T. Nguyen, F. Lodge, L. Gueguen, R. Andréoli, M-P. Doin and M. Datcu. Data Mining and Knowledge Discovery, 33 (1), pp. 131-167, January 2019.
SITS-P2miner: Pattern-Based Mining of Satellite Image Time Series. Tuan Nguyen, Nicolas Méger, Christophe Rigotti, Catherine Pothier, Rémi Andréoli. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD) Demo, pp.63-66. Riva del Garda, Italy, September 2016.