For decades, scientists, businesses, government agencies, universities and private organizations worldwide have relied on Landsat satellite imagery to track changes in the Earth’s forests, fields, cities, coasts and elsewhere. Landsat images were worth an estimated $2 billion to users in 2011.
An IITF scientist and collaborator demonstrated a new, highly accurate, automated way to detect clouds and their shadows from satellite images over unusually cloudy places, like tropical rainforests, which will allow more accurate automated mapping of tropical deforestation and forest regrowth. The new method also permits, for the first time, scientists to accurately and automatically detect clouds and shadows in satellite images lacking thermal image data. Unlike prior work, the method accurately detects clouds and shadows in imagery from a new European satellite mission, Sentinel 2, and from the 1970s. This advantage extends the period of observation back to the 1970s instead of the 1980s, and increases the frequency of satellite image observations that are usable for automated tropical forest monitoring starting in 2015, when Sentinal 2 was launched. Combining Landsat with Sentinel 2 imagery will give users images every 2-3 days instead of every 16 days for Landsat alone. Increased frequency of observations will also allow more frequent monitoring of forest and agricultural productivity. Automatically detecting clouds and their shadows in satellite images without a thermal channel has long been a holy grail of tracking tropical deforestation. This is especially true for tropical rainforests known as cloud forests, which get their name because they are on mountains where much of the time they are immersed in clouds and mist. One of the study’s test sites was Puerto Rico, where the U.S. National Forest known as El Yunque has extensive cloud forests.