About the project

Riyadh is one of the hottest large cities in the world, and summer surface temperatures regularly pass 50 °C. That heat is not shared equally: dense, paved districts with few trees trap far more of it than neighbourhoods along the green Wadi Hanifa corridor or around well-planted parks. This dashboard maps land surface temperature from Landsat, vegetation from Sentinel-2, and tree canopy and parks from satellite and OpenStreetMap data, then scores every built-up cell for tree canopy equity: how much vegetation its residents can reach compared with how much heat they face. Cells that are hot, dense and poorly served by trees become priority zones for planting and cooling interventions, directly relevant to city greening efforts such as the Green Riyadh programme.

The analysis runs entirely in your browser. Satellite mosaics, land cover, terrain, climate records and OSM features are fetched from public APIs, decoded pixel by pixel and processed on a ~70 m grid: k-means clustering finds heat hotspots, exact distance transforms measure how far each cell is from tree canopy and parks, and a TensorFlow.js model weighs heat, building density and lack of vegetation into a heat-risk score. Note that by day Riyadh's desert surroundings heat up faster than the city itself, so the analysis compares districts within the built-up area rather than the city with the desert. Change the imagery window or the model weights and press Recompute Equity to explore the result, or click any location to see the values behind it. It is a screening tool for planning conversations, not a substitute for field surveys.