SolarMap.PH

SolarMap.PH · your roof from space

What can your roof do?

Drop your address. We pull a satellite picture of your specific roof, measure it, and tell you whether solar is worth it for you.

Free. No signup. SolarMap.PH runs no backend; the address you type is queried against third-party geocoders directly (Photon, Nominatim, Overpass, Esri tiles, PVGIS) and never reaches a server we control. Built for Filipino homeowners on Meralco. What gets seen by whom →

Try:

We'll tell you whether you can install solar on your roof, what it would save you, and what your block's grid saturation means for approval. Address is not stored.

why this exists

PH solar is too important to leave to opaque sales pitches.

Most Filipino homeowners considering solar have to navigate three asymmetries at once. Installer quotes vary 5x for the same system. LGU permit fees range ₱16K-153K for the same project. Net-metering has a 100 kW cap, a 10-day approval target, and uneven LGU adoption of the new 3-day fast-track. Useful, neutral information is hard to come by.

The tool reads your address, finds your building from OpenStreetMap, measures your roof from satellite, runs the payback math against the current residential rate, and tells you what to do. It surfaces nearby rooftops where our computer-vision survey already detected solar, the local LGU's permit cost where verified, and the safety-and-process steps that make a real difference.

No installer is paid to recommend their system. No data leaves your browser. The math is open-source and reproducible. How we computed everything →

research backplane

The map

A computer-vision survey of rooftop solar across 41 cities in Greater Metro Manila. 515 detections, 280 high-confidence above a 0.85 score; 384 buildings with per-roof panel polygons after segmentation. Calibrated to 96% precision on a held-out validation set.

Open the map →

how it works

Methodology

How the model was trained, calibrated, and validated. Active-learning rounds, encoder ablation, and the SAM segmentation step that turns tile-level detections into per-building panel polygons.

Read methodology →