Orbital Insight looks down from space and trains computers to measure population and indicators of economic growth from satellite images.
Census data is crucial to measuring national population, housing counts and even agriculture, business, and traffic. These are supplemented by household surveys that collect income or expenditure data. However, the process of manually acquiring this type of information is expensive and time consuming and is often most inaccurate precisely in the parts of the world most in need of international assistance. Surveys are processed slowly and poverty data often is released 12 to 18 months after it was collected. But census data is fraught in countries where violence makes data collection a dangerous mission. Orbital Insight generates more frequent and timely data by complementing traditional surveys with satellite data.
Who needs our help
Over 3 billion people globally live in poverty, earning less than $2.50 per day. In many regions of the world where poverty prevails, there is a significant lack of data related to conditions on the ground. Orbital Insight seeks to fill this data gap by creating a tool that can measure development levels across a wide expanse. The market for this data will include any organizations working in the field of international development as they seek to develop programs that can target impoverished groups with a higher degree of efficiency.
In a developing country, there are many visual measures of economic health that can best be seen from space. For instance, comparing satellite pictures of a city from 2010 to 2015, Orbital Insight’s algorithms can count more cars on the roads and taller buildings, suggesting an increase in the income and prosperity of the area. Other indications of growth can come from monitoring the rate at which new buildings are constructed, roads are built, nighttime lights or cultivated land spreads.
Combining Four Signals to Create one Product
Orbital Insight poverty mapping combines results from proven algorithms to generate one cohesive picture of poverty in specific regions. The Orbital Insight poverty map includes data generated from the car-counting algorithm, the shadow detection classifier (as a proxy for building height), the development classifier (as a proxy for % coverage of human construction), and agricultural productivity estimates. The combination of data from these sources provides a more defined picture as to the extent of poverty and development in a region.
For more information on Orbital Insight’s work with the World Bank see the full World Bank “case study” by clicking the link below.
Processing millions of images at a time, Orbital Insight uses machine vision and pattern recognition to detect houses in Sri Lanka and track the rate of housing growth
Source: DigitalGlobe Inc.