Scalable Multimodal Approaches

Identifying Vulnerable Populations in

The Republic of Congo

Image by Imani Bahati
Image by Imani Bahati

Image by Imani Bahati
Image by Imani Bahati

1/1

Artificial intelligence (AI) and machine learning (ML) techniques can generate unbiased geographical data and identify areas of extreme poverty, which policymakers can adopt to prioritize development aid allocations. This innovative method can help develop scalable algorithms to inform humanitarian responses to Africa's food crisis. In the Republic of the Congo (RoC), one out of two people live below poverty, and the pre-COVID level of food insecurity of 10% has surged to 30% during the pandemic. Thus far, governments have responded to this crisis by doubling social protection programs. However, the current targeting methods do not provide enough information on eligible communities and are too slow to mitigate transitory shocks. This issue highlights the need for a systemic, fine-grained, and rapid geographic targeting technique. 

This current project aims to develop a multimodal approach that combines daytime satellite imagery, nighttime luminosity, and social media to estimate the wealth and livelihood of regions and shape aid distribution.

..................................................................................................................................................................................

FOOD INSECURITY IN CONGO PRE-COVID

FOOD INSECURITY IN CONGO DURING COVID

10%.png

FOOD

SECURITY

90%

FOOD

INSECURITY

10%

30%.png

FOOD

INSECURITY

30%

FOOD

SECURITY

70%

Republic of Congo Food Insecurity.jpg

Research

.................................................

 

Dr. Jung's latest research project aims to develop a multimodal approach that combines daytime satellite imagery and social media to estimate the wealth and livelihood of regions and shape aid distribution.

              PARTNERS             ....................................................

logo%20-%20WFP%20-world-food-program_edi

      3 STAGES        ..........................................................

  1. Assess the current machine learning model

  2. Develop new algorithms with a wider application

  3. Share this new field-tested and evaluated approach with policymakers

This project received Microsoft's AI for Humanitarian Action Project Initiatives'  $25,000 Azure Grant. 

Microsoft logo.png

              PARTNERS             ....................................................

Republic of Congo Women
Republic of Congo Women

Republic of Congo Women
Republic of Congo Women

1/1

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 WFP and the Ministry of Social Affairs to scale up social protection programs. These maps can be updated as new data becomes available to decision-makers in near real time. This work could potentially address misinformation and current criticisms of AI that miss out on the bottom billion, thereby addressing diversity, equity, and inclusion.

Research Duration

.................................................

 

March 2021 - March 22

In March 2021, the research design and team was finalized and partnership agreements were made. The study is slated to conclude in March 2022 with the dissemination of findings to policymakers.

            RESEARCH TEAM       .................................................................​​

The team consists of computer/data scientists

and social scientsts:

  • Jordan Steiner - Rutgers University

  • Alisha Cupid - Rutgers University

  • Melissa Yu - Rutgers University

  • Matthre Purri - Rutgers University

  • Lily Lin - Microsoft

  • Koubouana Felix - Marien Ngouabi University