%0 Journal Article
%9 ACL : Articles dans des revues avec comité de lecture répertoriées par l'AERES
%A Grinand, C.
%A Rakotomalala, F.
%A Gond, V.
%A Vaudry, R.
%A Bernoux, Martial
%A Vieilledent, G.
%T Estimating deforestation in tropical humid and dry forests in Madagascar from 2000 to 2010 using multi-date Land sat satellite images and the random farests classifier
%D 2013
%L fdi:010061471
%G ENG
%J Remote Sensing of Environment
%@ 0034-4257
%K Deforestation ; Change detection ; Classification ; Land cover ; Landsat TM ; Machine learning ; Madagascar ; Random forests ; REDD
%K MADAGASCAR
%M ISI:000329417700007
%P 68-80
%R 10.1016/j.rse.2013.07.008
%U https://www.documentation.ird.fr/hor/fdi:010061471
%> https://www.documentation.ird.fr/intranet/publi/2014/02/010061471.pdf
%V 139
%W Horizon (IRD)
%X High resolution and low uncertainty deforestation maps covering large spatial areas in tropical countries are needed to plan efficient forest conservation and management programs such as REDD+ (Reducing Emissions from Deforestation and Forest Degradation). Using an open-source free software (R, GRASS and QGis) and an original statistical approach combining multi-date land cover observations based on Landsat satellite images and the random forests classifier, we obtained up-to-date deforestation maps for the periods 2000-2005 and 2005-2010 with a minimum mapping unit of 036 ha for 7.7 M hectares, i.e. 40.3% of the tropical humid forest and 20.6% of the tropical dry forest in Madagascar. Uncertainty in deforestation on the maps was calculated by comparing the results of the classification to more than 30,000 visual interpretation points on a regular grid. We assessed accuracy on a per-pixel basis (confusion matrix) and by measuring the relative surface difference between wall-to-wall approach and point sampling. At the pixel level, user accuracy was 84.7% for stable land cover and 60.7% for land cover change. On average for the whole study area, we obtained a relative difference of 2% for stable land cover categories and 21.1% land cover change categories respectively between the wall-to-wall and the point sampling approach. Depending on the study area, our conservative assessment of annual deforestation rates ranged from 0.93 to 233%.yr(-1) for the humid forest and from 0.46 to 1.17%.yr(-1) for the dry forest. Here we describe an approach to obtain deforestation maps with reliable uncertainty estimates that can be transposed to other regions in the tropical world.
%$ 082 ; 126