For today’s top stories, visit
SN Today at www.sciencenews.org
researchers to probe whether particular
fixed variables, such as proximity to
the Pakistan border, could be used
to strengthen the computer program’s
predictive power. Both population density and closeness to a major city were
associated strongly enough with an
uptick in conflict intensity that knowing
those variables improved the program’s
predictions. Terrain type and elevation,
on the other hand, weren’t especially
linked to activity. And while insurgents
are known to seek refuge in Pakistan,
considering the proximity of activity to
the Pakistan border didn’t help refine
the program’s estimates overall. Such a
border effect may have been canceled
out by low levels of activity in some bordering provinces, such as the relatively
quiet Nimruz in the southwest, compared with others with more activity.
Even though the incidents reported
in the War Diary logs were extremely
variable and in many cases nonviolent,
the computer program succeeded at
tapping into and making something of
the data, a feat that even the scientists
didn’t expect.
“I was very surprised, actually,” says
Zammit-Mangion. He had considered
breaking the incidents down into different types, but that would have led to
fewer data points per type, compared
with one enormous dataset. “I was
thinking of refining it later but found
we didn’t need to.”
Reports per week
50 30 20 10 1
Intense geography
A snapshot of insurgent
activity in March 2008
reveals hot spots in the
southern and eastern
parts of Afghanistan,
with the most intense
activity centering on the
main cities of Kabul and
Kandahar. The information comes from secret
military logs leaked
online in 2010.
tion comes from secret
SOURCE: A. ZAMMIT-MANGION E T AL/PNAS 2012
Including additional data, such as
information on U.S. military troop
movements, could make the simulation
perform even better, Sanguinetti says.
The real strength of the simulation is
that it highlights regions where it’s difficult to predict future activity, says statistical epidemiologist Peter Diggle of
Lancaster University and the University
of Liverpool, both in England.
“It delivers best guesses with honest
estimates of how good those guesses are
so you don’t have to be dogmatic,” says
Diggle. “This is a very nice and imagi-
native application of this modeling
approach. It’s a good piece of work.”
Such simulations nicely comple-
ment approaches that look at the
social dynamics of a conflict and the
demographics and history of the peo-
ple involved, says John O’Loughlin, an
expert in the geography of conflict at the
University of Colorado Boulder.
Back Story | PUTTING WIKILEAKS ON THE MAP
While the secret U.S. military logs released by WikiLeaks in 2010 contain
little in the way of intelligence, the data are still revealing, says political geographer John O’Loughlin of the University of Colorado Boulder. Three-dimensional mapping of more than 46,000 violent events recorded in the leaked
documents, for example, shows a hefty uptick in
violence after 2006 that increases dramatically
in 2009 (pictured, as viewed from the north). The
;ne-grained analysis by O’Loughlin and colleagues,
published in 2010 in Eurasian Geography and
Economics, pinpoints the cities of Kandahar and
Lashkar Gah as growing hotbeds of violence,
along with the Korangal Valley (known to American
troops as “The Valley of Death”). Their analysis
also reveals the spread of insurgency violence over
time. Until mid-2009, about 46 percent of violent
events took place within 100 kilometers of the
border with Pakistan, an important refuge for insurgents. The violence then creeps beyond that buffer
zone, illustrating the diffusion of insurgents beyond
standard Taliban strongholds. — Rachel Ehrenberg
Violent events, 2009
Lashkar
Gah
Kandahar
Korangal
Valley
