Global Conflict Monitor

Global Conflict Monitor is a personal, artistic project. It was built in a period of growing conflict — a time when wars that once felt distant became part of everyday conversation, appearing in feeds and notifications alongside everything else. This is an attempt to make that weight visible: to collect the signals, map them, and sit with what the picture looks like.

The project aggregates RSS feeds from twenty international news outlets and research organisations, processes the articles through an AI model, and groups related stories into unified events. Each event is geolocated on a map, assigned an estimated impact score, and stored alongside the entities — people, locations, organisations — that appear in the coverage.

This is not a news room. It is not a verification service. The pipeline is fully automated: an AI reads the headlines, clusters what seems related, invents a short synthesis, and scores the severity. The model will hallucinate, conflate, or miss context. Some feeds are more credible than others. Some conflicts are systematically underreported and will appear as quiet zones on the map despite ongoing violence. The aesthetic of precision — the coordinates, the percentages, the amber glow — should not be mistaken for accuracy.

What you are looking at is a meta-analysis constructed from public information. It reflects what twenty sources chose to publish on a given day, filtered through an AI that has its own biases and gaps. It is a representation, not a record. It cannot and should not be used as a journalistic source, cited as evidence, or treated as ground truth.

The impulse behind it is something closer to cartography as witness. Maps have always been partial — shaped by who drew them, what they chose to include, what they left out. This is no different. But the act of drawing, of aggregating, of refusing to look away, still feels like it means something.

Built with Next.js, Prisma, Leaflet, and OpenAI GPT-4o-mini for event synthesis. Context panels draw on Wikipedia, Wikidata, REST Countries, World Bank, and ReliefWeb — all free and open APIs. Data is refreshed once daily.