Our Work

The Conflict Nutrition Intelligence Network (CNIN) is an AI-powered platform combining open-source satellite data, humanitarian reports, and machine learning to forecast caloric deficits in real time. CNIN bridges humanitarian decision-making with predictive analytics, enabling faster and more equitable food aid distribution in war-torn regions.

Key Features:

• Predictive hunger modeling (14-day forecasts)

• Real-time aid equity scoring

• Integration with FAO, WFP, UNICEF, and OCHA data pipelines

• Transparent and auditable analytics

GAZA

Population: 2.1 million
Summary: CNIN identified severe misallocation of aid resources following the 2025 ceasefire.

Key Findings:

• 70% of aid tonnage delivered to areas with only 35% of unmet caloric need.
• Rafah received 41% of its required aid coverage, while Gaza City received 89%.
• CNIN simulations showed that rebalancing shipments could increase caloric equity by 28% within one week.
• Predicted deficit reduction: 400 kcal/person/day in under-served areas.

Visualization Suggestion: Gaza district heatmap showing caloric gap intensity.

UKRAINE

Conflict-driven agricultural disruption, market shocks, and displacement are reshaping food access in Ukraine. According to data analysis, by 2024 key regions such as Zaporizhzhia, Donetsk and Kharkiv experienced significant land loss and crop harvest stress: for example, one study reports that winter cereal production in those areas declined due to conflict-induced factors. PEJ+4Nature+4Open Knowledge Repository+4
Simultaneously, structural issues such as irrigation loss (for example in Kherson Oblast following the destruction of the Kakhovka Dam) indicate long-term agronomic risks. Wikipedia
For CNIN, this presents multiple pathways for impact:

By fusing satellite-derived vegetation indices (NDVI/EVI) with conflict and displacement layers, CNIN could identify agricultural zones at high risk of yield loss before harvest time, enabling early support to farmers or advance procurement of staple foods.
By tracking market data and logistics disruption, CNIN could estimate affordability shocks, locating communities where food access is at risk even when production remains moderate.
By modelling reforestation or land-rehabilitation needs (where land is abandoned or mined), CNIN could support medium-term recovery planning — not just emergency aid.
In practice: suppose CNIN’s algorithm flags a cluster of rural districts where NDVI fell by 20% and displacement inflows exceeded 10 % of the local population. A humanitarian partner could pre-position cereals, diversify staple sourcing, or invest in irrigation repairs. Over time this becomes not only about supplying food, but enabling the agricultural system to recover faster and with less waste.

SUDAN

In Sudan, conflict, economic collapse and climate stress have combined to produce one of the largest hunger crises globally. For example, one report notes that Sudan had the largest number of people facing extreme food shortages in 2023, driven by lost production and access disruptions. The Guardian
CNIN’s value in this environment emerges in several dimensions:

Satellite based monitoring of cropland abandonment, desertification and irrigation failure can feed into an agricultural recovery model: identifying where rehabilitation, crop reseeding or reforestation efforts will yield the highest return in food availability.
Market access and food price inflation data, combined with conflict mapping, can produce a region-by-region access risk index: where food is physically present but inaccessible.
By modelling the kinetic interplay between access, production and population displacement, CNIN may support pre-positioning of relief shipments and plant-recovery efforts — allowing agencies to act before large-scale malnutrition sets in rather than after.
In short: in Sudan’s complex terrain, CNIN’s integration of agricultural recovery, forest/land rehabilitation and humanitarian delivery modelling offers a unified tool to serve both immediate relief and longer-term food system restoration.

YEMEN

Yemen continues to be among the world’s most severe food crisis contexts: as of mid-2025 nearly half the population in government-controlled areas are acutely food insecure. World Food Programme+1
In this context of civil war, pipeline failures, climate stress and desertification, CNIN’s tool can serve multiple roles:

By combining remote sensing of evapotranspiration, vegetation stress, and land-use change with market pricing data, CNIN can highlight regions where agricultural production collapse is imminent, and where reforestation or soil rehabilitation would have high pay-off.
By overlaying humanitarian delivery pipeline data with satellite-observed damage and access constraints, CNIN could model where aid is likely to fall short and propose alternate logistics or cash-transfer mechanisms ahead of time.
For example, communities in southern Yemen with disrupted roads and rising staple prices could be forecasted as “high nutritional risk” zones even before field survey data catches up.
By equipping aid agencies and agricultural recovery programmes with this foresight, CNIN helps pivot from reactive crisis relief toward strategic resilience building in agriculture and reforestation.