Projects | EIES-Lab

Shadow-aware rooftop PV model

Mon, 01 Sep 2025 00:00:00 +0000

Model structure

The model takes a height map of the surrounding buildings and the sun position, and predicts the shading on each roof for every hour of the year. A temporal branch then turns hourly shading and weather into PV output.

Why it is fast

Ray-traced shading has to be recomputed for every hour and every building. The learned model replaces that step, which is what makes city-wide runs about 158 times faster than simulation.

Inputs and outputs

Inputs: building heights, roof geometry, sun position, hourly weather.
Outputs: hourly shading masks and rooftop PV potential per building.

Global facade & rooftop PV potential dataset

Sun, 01 Jun 2025 00:00:00 +0000

What it contains

For every building in each city, the dataset gives annual and hourly solar irradiation on the roof and on each facade, the usable area after windows and obstructions are removed, and the resulting PV generation potential.

How it is built

Building footprints and heights come from open 3D city models.
Facade elements (windows, walls) are parsed from street-view images.
Hourly irradiation uses local meteorology and the shading cast by neighbouring buildings.

Research uses

The dataset supports city-level planning of building-integrated PV, comparisons between cities, and training data for faster learned models.

Facade parsing toolkit

Sat, 01 Mar 2025 00:00:00 +0000