Missing Maps Hackathon: Detection of vegetation loss

0

Recently, I participated in the first hackathon organized by Missing Maps together with Doctors Without Borders, and other supporters. The mission of the event was to kick-start some early ideas and develop them into proof-of-concept solutions that might help in the main effort of Missing Maps, that is:

to provide map sources for places vulnerable to natural disasters, conflicts, and disease epidemics

.

I chose to work with satellite images (despite not having much prior experience with image processing) and what a fun! The task was to create methods to identify rural locations with increasing population growth. In a tiny team of two, with Jakub Matějka, we did some reasearch and hacked together a Jupyter notebook tool to visualize and quantify loss of vegetation (github) as a proxy to expanding population and human activity in an area. Expansion of population in certain area is almost always accompanied with side effects such as increased number of houses and consequent emergence of paths among them, loss of trees in nearby forests (used for heating or cooking), or degradation of natural environment due to the industrial growth. A common denominator of all of these effects is a decrease of vegetation mass. Our aim, therefore, is to provide simple yet effective methods to detect loss of greenery and analyze its rate.

Example output

Visual and quantitative analysis of rapidly growing Kutupalong refugee camp (map/wiki) inhabited mostly by Rohingya refugees that fled from Myanmar:

Analysis of deforestation (population growth) in Rohynga camp in Bangladesh

Spotting vegetation from space

Trying to distinguish vegetation based on color in visible spectrum might work for some areas (lush grasslands), but not for others (autumn tundra). Much better way of vegetation remote-sensing is to understanding that plants, in order to produce sugar via photosynthesis, do absorb solar radiation of certain wavelengths while they reflect other ranges not to overheat. SENTINEL-2 is well-equipped to capture images in red and near-infrared spectrum, and those are the wavelenght ranges needed to calculate NDVI: Normalized difference vegetation index. High values of NDVI index represent rich vegetation, low values suggest lack of greenery. The index is computed as: NDVI=(NIR – RED)/(NIR + RED), where NIR is near-infrared spectrum and RED is red (visible) spectrum.

Deforestation in Amazon over time

Identified difference in deforestation

The event

It should be said that the event was excellent. It took place in Tech Heaven which turned out to be just the right place for this kind of over-the-weekend happenings. Can’t wait for the next one…