Ensuring the utility of EO for SDGs for targeting of development assistance  Seminar

There is an increasing interest in the use of geospatial data such as remotely sensed earth observation (EO) satellite imagery to predict socioeconomic conditions to support development monitoring and poverty mapping. Data on socioeconomic conditions collected through household surveys and census are time consuming to collect and expensive, meaning that this type of data is collected less frequently than is often required for targeting assistance and development policy. Commissioning more household surveys or more frequent census can be prohibitive because of the costs involved. Recent advances in AI and machine learning have led to a series of papers reporting high predictive accuracies when using geospatial data to predict aspects of poverty/wellbeing/livelihoods. In this presentation, I examine the utility of these outputs for development practitioners. I discuss how a multi-resolution and focused approach of building thematic models of how households pursue their livelihoods is required to identify decision useful metrics that can be derived from earth observation data. I will review recent publications and examine the utility of these approaches for contributing to mapping and monitoring of the socioeconomic SDGs.  

Speaker Information

Dr Gary Watmough - Associate Professor/Senior Lecturer in Land Use and Socioecological Systems, School of Geosciences , The University of Edinburgh.

Link to join in