Emissiv · Remote Sensing · UK Study AOI

The Roof
Albedo Report

Roof material classification and solar-reflectance estimation from satellite imagery, an honest evaluation of separate, hybrid and recommended approaches, and how the model inches toward quality.

Measured, not asserted. Cited, not guessed.
Why this matters to Emissiv →
live · sentinel-2 l2a scene 2026-05-25 · cloud 0.002% 184 roofs · 1.13 km² read the right rail for plain english →
01The journey so far

Where we started, where we are

Every gain below was made on free data alone. No labels bought, no third parties waited on. All figures MEASURED this run.

02Material classification

The classifier's ceiling

How separable are the 14 material classes under the model's own best case, and how far can cleaner pixels push that ceiling?

Fig 02.a, the dark roofs the model most often mixes up.
Fig 02.b, accuracy vs pixel purity. Cleaner (higher-res) pixels raise the ceiling.
03Solar reflectance

Separate vs hybrid reflectance

Measured on 184 real roofs. Physics (NTB) is material-independent; the lookup table (LUT) inherits every classification error.

Fig 03.a, Albedo distributions. The LUT prior shifts the population brighter than the pixels warrant.
04Imagery resolution

The resolution wall

On real UK building geometry: how many roofs yield a clean pixel at each ground sample distance, and which sensors carry the SWIR albedo needs.

Fig 04.a, Addressable buildings by resolution. ✦ marks SWIR-capable sensors.
The cruelty of the trade-off: the only column with SWIR (Sentinel-2, ✦) resolves almost nothing. Every sensor that resolves the roof loses the bands albedo is built on.
05Databases · APIs · methods

The sourcing cabinet

Imagery, footprints and methods, researched and cited. Recommended rows carry a blue margin.

Imagery, the SWIR / resolution dilemma
Building footprints & attributes
Methods & published accuracy
06New free data, run live today

The free frontier

Three free sources and techniques we had not used, pulled live and sampled at the same real roofs. How far can we get today, with no labels, no paid imagery and no waiting on anyone?

Fig 06.a, Landsat vs Sentinel-2 albedo, same day. Aggregate agreement, per roof scatter from 30m blur.
Fig 06.b, radar brightness by roof group. An axis independent of colour.
07Real labels, free, run live

Closing the loop

The deepest fix, run today: harvest real roof-material labels free from OpenStreetMap, train on those instead of textbook spectra, and fuse the free radar. The first measured accuracy this project has had.

Fig 07.a, accuracy on the same held-out real roofs. Synthetic, to free labels, to free fusion.
Fig 07.b, what the trained model confuses. Slate and tile, both pitched, still blur.
08Recommended architecture

Inching toward quality

The lane-separated architecture and the ordered moves that convert this prototype into a defensible product.

Ordered moves
09Tier-1 product & analysis

To Silicon-Valley tier

Beyond fixing the prototype, the moves that make this a category-defining product, not a script.

10Teach the work

Glossary & sources

Every term, data source and model on this page in plain English, enough to explain what we do to someone new.