Conducting economic surveys requires huge resources; thus, modern means of acquiring this information using publicly available data and open source technologies create the possibilities of replacing current processes. Satellite images can act as a proxy for existing data collection techniques such as surveys and census to predict the economic well-being of a region. The aim of the project is to build on a prototype that was created using Census data and LandSat data for India. In the next iteration, opportunities for Demographic Health Surveys, Open Street Map, Sentinel and nightlight data will be explored. The initial prototype created a model that had an accuracy of almost 70 percent. The aim is to create a model for India that can be adapted and scaled to other countries.
As the UN Decade for Ecosystem Restoration approaches in 2021, it is essential to create baselines from which to monitor change. As well as understanding tree cover loss and gain, it is essential to measure the impact restoration is having on communities. In order to do that, baseline well-being data layers need to be created. However, when compared to satellite data, which identifies tree cover loss and gain in near real time, on the ground surveys are conducted over a period of a few years and involve huge manpower and expenditure. A geospatial data layer of well-being is needed to overlay on tree cover loss and gain layers. The aim is that changes in vegetation and well-being can be charted over time. Any correlations between data layers can be investigated to understand if there are relationships between tree cover and well-being.
A prototype of a well-being data layer was created by Omdena (https://omdena.com/blog/ai-economic-well-being/). This used open source imagery and was limited to LandSat 2011 and Census 2011. In the next iteration, there is higher resolution Sentinel data available as well as other ground truth sources such as Demographic Heath Surveys and Open Street Map Data. WRI would welcome volunteers with coding and GIS expertise to help develop the prototype for scaling.
This data layer will be used as a baseline for monitoring well-being change related to tree cover loss and gain. Although it is difficult to ascertain cause and effect and impact from such data layers, it is important to simultaneously monitor to change. Too little attention is paid to the impact the environment has on people. The aim is that we can chart progress simultaneously and seek to understand relationships.
The team would have the support of the restoration monitoring team.
Kathleen Buckingham, Senior Manager, Social Research, Data and Innovation