stpanirudh/ai-based-detection-and-classification-of-industrial-fires-and-persistent-thermal-sources ? reverse-engineered prompt

Build me a local Python prototype that detects and classifies industrial fire like thermal hotspots from FIRMS style CSV data and shows everything on an interactive map.

I want it to load sample hotspot data and industrial facility locations, clean and validate the coordinates, check how close each event is to nearby industrial sites, and then label events into a few simple categories like potential industrial fire, persistent thermal source, natural fire, or uncertain. It should also look for hotspots that keep appearing in about the same place over time, give each event a simple risk score and priority, and show the results in a clean dark themed dashboard with map layers and filters.

Please make it easy to run locally with one command, and include a small terminal report mode too. If you need to look up current docs online for FastAPI, Leaflet, or any library details, go ahead. Keep it lightweight and demo friendly, since this is just a working prototype and not a production system.