Rutgers School of Social Work Assistant Professor Dr. Woojin Jung has beenselected as a recipient of the Collaborative Multidisciplinary Award of $18,000. This grant is given through the Rutgers Research Council, a popular and competitive internal funding mechanism. As a partner, the Research Council is committed to empowering researchers to use creative and interdisciplinary work to solve complex intellectual and social problems. The grant will support Dr. Jung’s latest project in Zambia to develop an AI-informed vulnerability index to target the food security pack (FSP) program.
“I’m so excited to find a group of scholars to share and develop research ideas and implement them." says Dr. Jung. "What I really like about this funding opportunity is that it facilitates interdisciplinary partnerships across departments, campus, and ranks. We have social science, computer/data science, and geospatial expertise. This project also brings together scholars and practitioners across countries and organizations. We formalized a partnership with the Innovations for Poverty Action (IPA) in Zambia, a research and policy think tank specializing in impact evaluations, connecting us with key country development actors, such as the Ministry of Community Development and Social Services.”
Dr. Jung has been recognized for her innovative research initiative that applies AI and machine learning techniques to the field of international development. This utilizes an innovative method for generating unbiased geographic data and identifying areas of extreme poverty, which policymakers can adopt to prioritize development aid allocations.
Her current focus is on developing scalable algorithms to inform humanitarian responses to Africa’s food crisis. In response to surging food insecurity in the wake of COVID-19, the Zambian government plans to triple the FSP to the vulnerable population. However, identifying areas of extreme poverty has high exclusion and inclusion errors, given the sparsity of the ground-truth surveys. This issue highlights the need for systematic, fine-grained, and rapid geographic targeting by harnessing AI/ML techniques.
The Research Council’s Collaborative Multidisciplinary Award will support Dr. Jung’s latest research project to develop an AI-informed vulnerability index to assess food insecure communities in Zambia and shape aid distribution. This study aims to generate robust wealth estimates at a granular level, combining satellite imagery, social media, and spatial analysis. Dr. Jung and her research team, composed of computer/data scientists and social scientists, work in partnership with the Innovation for Poverty Action (IPA) in Zambia. The team is developing this method to expand the coverage of food assistance programs in Zambia. The novel model has three stages:
- Assess the current machine learning model
- Develop new algorithms with a wider application
- Share this new field-tested and evaluated approach with policymakers
Dr. Jung’s research is expected to have high global impact by offering enhanced data for key development actors to reach people and regions with extreme poverty. This project's outputs, such as high-resolution poverty maps, will be shared with the IPA and the Ministry of Community Development and Social Services to expand the FSP programs. These maps can be updated as new data becomes available to decision-makers in near real time. After this project validates its performance in Zambia, the model can be applied to the Republic of Congo, a neighboring country without the DHS wealth data and in an even more challenging data environment. This work could potentially address misinformation and current criticisms of AI that miss out on the bottom billion, thereby addressing diversity, equity, and inclusion.