he Nam Et-Phou Louey National Protected Area covers 
almost 600,000 hectares (about 2,300 mi


) of mountain-

ous terrain in northern Lao People’s Democratic Republic 

(Laos).  Its forests have been home to about 40 threatened spe-
cies, including one of the last tiger populations in Indochina. 
The forests, like their inhabitants, urgently need protection. 

Preserving Biodiversity
The Wildlife Conservation Society (WCS) in Lao PDR and the 
local Nam Et Phou Louey management unit joined forces in the 
Lao–German Climate Protection through Avoided Deforesta-
tion (CliPAD) project. They wanted to develop the protected 
area as a Reducing Emissions from Deforestation and Forest 
Degradation (REDD) project for the voluntary carbon market. 
REDD works to establish economic incentives via carbon 
credits, making the forests worth more standing than the land 
would be if cleared or burned. 

Planet Action, a non-profit initiative fighting climate change, 
supported WCS by providing Landsat imagery as well as image 
analysis software. These tools helped WCS perform an exten-
sive feasibility study and facilitated an in-depth assessment of 
the issues facing the Nam Et-Phou Louey region.

Image Anaysis
To identify the location and rate of deforestation, WCS collected 
Landsat imagery for the protected area for the years 2000, 
2004, 2006, and 2010. They also obtained Trimble eCognition 
software, an advanced image analysis solution for geospatial 
applications. The software enables users to integrate and 
analyze geospatial data for quantifying features and detecting 
changes over time. WCS used eCognition to segment and clas-
sify images into forested and non-forested areas.

“The tools provided by Planet Action were invaluable,” said 
Colin Moore, regional advisor on REDD and climate change on 
behalf of WCS in Laos. “Manually classifying 600,000 hectares 
of heterogenous forests, for four time periods, would not have 
been possible within the project’s timeframe.” 

Trimble eCognition’s object-based image analysis technology 
helped to overcome image interpretation challenges such 
as shade, seasonal conditions and forest types. The rule set 
developed to extract accurate geoinformation (forested vs. 
non-forested land) incorporates satellite data and topographic 
maps to consider the variable terrain. In reference to high-res-
olution Spot 5 image data, a mapping accuracy of 80 percent  
could be assessed for the overall area. 

Changing Tack For A Broader Approach With Larger Impact
Based on the data, the WCS team discovered that deforesta-
tion rates in the protected area were too low to sustain a REDD 
project. So a different approach was needed. 

With CliPAD and the government of Laos, WCS designed a new 
project encompassing the entire province, not just the pro-
tected area. This new project focuses on developing suitable 
pilot models for effective provincial forest conservation, which 
could ultimately extend nationally.

Trimble eCognition is again being used to track deforestation 
across this massive area, and it will remain an essential tool for 
projects and governments as they move ahead with future 
REDD endeavours. 

See feature in Earth Imaging Journal’s September issue: www.eij.com

To Save a Fragile 

Forest, Carbon 

Credits Talk

Protecting Critical Wildlife Habitats through Geospatial Technology




Left and top right © Colin Moore / WCS and DFRM Lao PDR; bottom right © WCS and DFRM Lao PDR