ML-powered system predicting landmine risk with interactive geospatial visualization and explainable AI for humanitarian demining.
Offline AI for emergencies with local context and cited answers from community Knowledge Packs.
Explainable food-security forecasting with OpenTSLM, combining conflict, rainfall, market prices, and shipping data to predict district-level risk.
Apple MobileCLIP2-S0 local-first image triage for disaster response, housing recovery, accessibility audits, and field ops.
Compawss AI — An AI-powered humanitarian rescue platform built for Indian stray animals and emergency animal welfare response. Uses real-time location intelligence, community alerts, AI-assisted reporting, nearby vet/NGO discovery, and rapid rescue coordination to connect animals in distress with the closest available help across India.
Context-conditioned normalising flows for subnational refinement of sparse humanitarian surveys (arXiv:2605.31489)
Trustworthy multilingual and multimodal AI for crisis intelligence, uncertainty-aware disaster classification, human review, reproducible research and production-grade MLOps.
ML prototype for classifying humanitarian crisis messages using TF-IDF, Logistic Regression and Streamlit.
Explainable NLP triage for humanitarian crisis messages using TF-IDF, balanced Logistic Regression and Streamlit.
WhatsApp-integrated humanitarian field assistant using FastAPI, Anthropic Claude, WhatsApp Cloud API, SQLite memory, prompt guardrails, and golden-set evals.
Forecast district-level food insecurity three months ahead using hybrid temporal and language models with transparent, inspectable explanations.
Responsible AI dashboard and portfolio case study for humanitarian needs analysis, community feedback triage, and decision-support briefs in Sudan.
Clean Drop: edge-AI water reporting and triage built on Gemma 4 for mapping water stress
MAMA AI Clinic: $170 fully-offline AI health assistant for Raspberry Pi 5. WHO IMNCI triage, essential medicines dosing, CHW training. Built to hand to IRC/UNICEF/DNDi. Apache 2.0.
Autonomous Sentinel-1 SAR flood inundation mapping & topological road isolation routing for disaster rescue dispatch
Calibrated Early-warning and Risk Estimation System: Automated probabilistic forecasting system for acute food insecurity. Generates 90-day ahead probability estimates of IPC Phase 3+, 4+, and 5 conditions for 43 high-risk countries, updated weekly. Fuses six data streams. Free for humanitarian and academic use.
Agentic system for situation report, secondary reviews, weekly bulletin, proposal writing and more
To associate your repository with the humanitarian-ai topic, visit your repo's landing page and select "manage topics."