Semantic enrichment of 3D city models via roof material classification for urban greening and heat island mitigation

Elmehdi Kanna

doi:10.1016/j.scs.2026.107734

Semantic enrichment of 3D city models via roof material classification for urban greening and heat island mitigation

2026-08-04

0

OA

AI

E

Elmehdi Kanna *

J

Jannik Matijevic

L

Lukas Arzoumanidis

S

Son H. Nguyen

Y

Youness Dehbi

DOI：10.1016/j.scs.2026.107734

Original

Original request for help

Save

Abstract

En 中文

• End-to-end roof-material to CityGML enrichment and citywide UHI screening. • Footprint-masked roof material classifier attains 95.1% top-1, 0.669 macro F1. • Per-building material enrichment of CityGML 2.0 and 3.0 datasets. • Roof greening cools Hamburg by 0.84 K, Paris 0.06–0.16 K, Madrid 0.22–0.60 K.

Keywords:

Roof material classification

Semantic enrichment

CityGML

Urban heat island

Land surface temperature

Semantic enrichment of 3D city models via roof material classification for urban greening and heat island mitigation

Abstract

Journal

Organization

Cited Papers

Citing Papers