Submission ID 118589
| Issue/Objective | Dharavi, Mumbai, is India's largest slum, housing over one million people in 2.1 km² who face chronic food insecurity. Despite India's Public Distribution System and over $500 million from NGOs, ration leakage, poor dietary diversity, and exclusion of undocumented residents persist. A 2022 survey found 83% of toddlers rely on ultra-processed foods due to high produce costs and time constraints. In 2024, 13.5% of children under five were malnourished, and 44.19% of those over two were underweight. To address these gaps, we propose HarThali as a potential food security intervention that uses blockchain to improve food distribution transparency and geospatial AI to identify hunger hotspots. This digital, community-led initiative promotes equitable access to food and targets malnutrition in urban slums, aligning with global health and nutrition goals. |
|---|---|
| Methodology/Approach | HarThali is a five-year, six-phase intervention in Dharavi using a consortium blockchain with Practical Byzantine Fault Tolerance (PBFT) to secure food transactions. The project will operate in Dharavi, starting with community education and registration via Aadhaar ID, followed by onboarding of local food vendors, NGOs, and farmers. After six months of data collection, AI-driven heat mapping will visualize food flow and detect underserved areas. Vulnerable populations without documentation are included, and real-time feedback loops inform continuous adaptation. |
| Results | HarThali aims to enroll 70% of Dharavi's population and partner with 22+ NGOs and food providers. It targets a 50% drop in corruption-related diversion and reduction of food loss from 60% to 30%. AI-driven geospatial tracking will identify food-insecure zones and guide resource redistribution. Over five years, the project expects to distribute $35-40 million in food and support targeted, locally responsive interventions. |
| Discussion/Conclusion | HarThali demonstrates how innovation can bridge the digital divide in marginalized urban settings through scalable, data-driven design. By leveraging artificial intelligence, blockchain, and existing digital ID systems, the model offers a sustainable, tech-enabled pathway to improve global food security and health equity. The project also provides a policy blueprint for adaptive governance, enabling targeted interventions and resource reallocation in real-time, and is designed for replication in other low-income, high-density urban areas. |
| Presenters and affiliations | Nikita Chopra Queen's University Julia Apolot Queen's University Heeya Patel Queen's University |
