Predictive software to identify indicators of deforestation risk from satellites imagery
Monitoring global deforestation can be a tedious process of analysing individual satellite images from a handful of government spacecraft and trying to infer trends from relatively blurry pixels. Even so, recent advances have yielded clues about shifting hotspots of deforestation, including tropical nations and industrialised countries.
The mini-boom in the private sector satellite and satellite data processing industries, however, may soon yield a dramatically different deforestation monitoring regime. In fact, it may soon be possible to predict where deforestation is about to occur, according to James Crawford, founder of Orbital Insight, a Silicon Valley company that uses a technique called deep learning to analyse massive data sets.
Orbital Insight is partnering with the World Resources Institute (WRI), a nonpartisan Washington environmental group, to contribute to WRI's ground-breaking Global Forest Watch program.
Under the partnership, Orbital Insight will analyse high resolution satellite images of tens of millions of acres of forest to discover patterns that identify indicators of deforestation risk, such as the building of new roads into sections of tropical rainforests.
Click here for source (Mashable)
Photo: Planet Labs