Machine learning (or neural-network), is a bio-inspired technology which emulates the basic mechanism of a brain.
To find a pattern in noisy dataset
To apply these patterns to new dataset
Methodology As required by the ARD algorithm, each input and the hidden output is a weights class with its own α α 0 α c INPUTS : Past NDVI (MODIS 3b42) Previous rainfall (TRMM) Temperature (WorldClim) OUTPUT : 16 day predicted NDVI NDVI t Precipitation (t) Temperature (t) … … w 0 w 1 w 2 NDVI (t-1) NDVI (t-2) NDVI (t-n) w p1 w p2 w p3 w o1 w o2 w o3
The satellite images of 2004 and 2006 used to compare the two models are extracted from images
Mosaico LandSat 2004 (AMZ)
Mosaico LandSat 2006 (AMZ)
Also provide by the Deter project website.
HUMANE true positives 2004 2006 Parasid model is, sometimes more sensitive, and detects events that Deter doesn’t detect.
HUMANE True Positives It seems Parasid model detects quite small and isolate events which Deter doesn’t detect. 2006 2004
HUMANE False positives On the other hand, Parasid is more sensitive to false positives. Here, around a river. 2004 2006
HUMANE False Positives In this example, Parasid doesn’t detect as well as Deter the big new field (red circle) but, is more precise to detect the small fields on the top right corner (blue circle) . 2004 2006
The marked areas show that most of the differences are due to the changes which happened between 2000 and 2004.
Parasid can’t detect these changes as it started detecting in 2004.
NDVI 2000.02.18 NDVI 2004.01.01 PARASID - FORMA
Detailed comparison Top FORMA Bottom PARASID Images from google earth PARASID - FORMA Maybe due to the rescaled pixel size from 250 [m] to 500 [m], FORMA model doesn’t fit perfectly some fields (the red bound around the fields on the comparison map).
Detailed comparison Top FORMA Bottom PARASID Images from google earth PARASID - FORMA Parasid is a bit more sensitive.
Detailed comparison Clear change in 2006 Softer change in 2008 Maybe vegetation degradation The pixel plotted is shown in red on the map .