Dr Essa Chanie Mussa is a ROSETTA postdoctoral fellow with University of Galway and is undertaking his fellowship under the supervision of Dr Edel Doherty.

Essa earned his PhD in Development Economics from University of Bonn, an MSc in Globalization and Development from University of Antwerp, and a collaborative MSc in Agricultural and Applied Economics from Egerton University and University of Pretoria. His research has been published in leading journals such as Social Science & Medicine, PLOS ONE, BMC Health Services Research, SSM – Population Health, SSM – Health Systems, BMC Public Health, and the International Journal of Educational Development.

Essa is a Development Economist and has extensive experience across academia, consultancy, and international development. He has worked with UNICEF Innocenti – Global Office of Research and Foresight, UNICEF Evaluation Office, UNICEF Ethiopia, CARE Ethiopia, the YADAM Foundation, and the Centre for Evaluation and Development (C4ED) on high-impact projects in several low- and middle-income countries, including Ethiopia, Burkina Faso, Sudan, and Cambodia. He previously served as Assistant Professor at the University of Gondar and as a Visiting Scholar at the University of Antwerp, and he is currently an Adjunct Faculty member at the University of Gondar.

Essa’s ROSETTA project, titled, “SoProChild-Ethiopia“, integrates development economics, data science, and public policy, harnessing emerging digital technologies and innovative research methods to advance evidence-based policymaking, reduce poverty, and improve child health outcomes in Africa and beyond.

Ethiopia faces one of the world’s highest burdens of multidimensional child poverty, with 88% of children under 18 experiencing deprivations in health, education, and living standards. One in four children also suffers from stunted growth due to chronic malnutrition. To address these challenges, Ethiopia has rolled out large-scale social protection programs such as the Productive Safety Net Programme (PSNP) and Community-Based Health Insurance (CBHI). Yet, critical questions remain about their effectiveness in reducing multidimensional poverty and improving child health outcomes, particularly due to persistent challenges in targeting and resource allocation.

The SoProChild-Ethiopia project will apply advanced Machine Learning (ML) techniques to predict child poverty and nutrition outcomes and to map hotspot areas of poverty and stunting across the country using socioeconomic and satellite imagery datasets. This innovative approach goes beyond traditional econometric methods by capturing complex, non-linear relationships between poverty, health, and environmental factors. While the evidence generated will directly inform the design and targeting of Ethiopia’s social protection interventions, the models developed will also offer adaptable tools for other low- and middle-income countries facing similar challenges.

The project aims to chart a new path for the ethical and effective integration and use of emerging digital technologies in development policy, ensuring that development interventions become more equitable, better targeted, and more impactful for the most vulnerable children. The project directly contributes to several Sustainable Development Goals, including SDG 1 (No Poverty), SDG 2 (Zero Hunger), and SDG 3 (Good Health and Well-being).