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.
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.
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
See feature in Earth Imaging Journal’s September issue: www.eij.com
To Save a Fragile
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