An automatic clustering technique applied to the study of vegetation fire patterns distribution in the African continent
The aim of this work is to develop and evaluate the capability of an automatic clustering technique, in recognising and quantitatively describing vegetation fire patterns as derived from NOAA-AVHRR GAC data. A refinement of moment preserving clustering technique is proposed: the algorithm is validated on synthetic test data, and applied to the analysis of vegetation fire patterns distribution at regional and continental scale in Africa. The effect of scaling process on clustering is also discussed, and parametrisation concerning the relative disposition of fire clusters and the size and shape of the clusters is proposed.
Bibliographic Reference: Paper presented: IGARSS '95, Qualitative Remote Sensing for Science Applications, Firenze (IT), July 10-14, 1995
Availability: Available from (1) as Paper EN 39211 ORA
Record Number: 199511244 / Last updated on: 1995-10-13
Original language: en
Available languages: en