[Paper Review] Predicting Local Climate Zones using Urban Morphometrics and Satellite Imagery

Hugo Majer, Martin Fleischmann|arXiv (Cornell University)|Feb 23, 2026

Urban Heat Island Mitigation0 citations

TL;DR

The paper evaluates predicting Local Climate Zones (LCZs) from urban morphometrics alone and in fusion with satellite imagery across five sites, finding inconsistent, site-dependent performance and modest, sometimes negligible gains from fusion.

ABSTRACT

The Local Climate Zone (LCZ) framework is commonly employed to represent urban form in morphological analyses despite its mapping predominantly relies on satellite imagery. Urban morphometrics, describing urban form via numerical measures of physical aspects and spatial relationships of its elements, offers another avenue. This study evaluates the ability of morphometric assessment to predict LCZs using a) a morphometric-based LCZ prediction, and b) a fusion-based LCZ prediction combining morphometrics with satellite imagery. We calculate 321 2D morphometric attributes from building footprints and street networks, covering their various properties at multiple spatial scales. Subsequently, we develop four classification schemes: morphometric-based prediction, baseline image-based prediction, and two techniques fusing morphometrics with imagery. We evaluate them across five sites. Results from the morphometric-based prediction indicate that the correspondence between 2D urban morphometrics and urban LCZ types is selective and inconsistent, rendering the efficacy of this method site-dependent. Nevertheless, it demonstrated that a much broader range of urban form properties is relevant for distinguishing LCZ types compared to standard parameters. Relative to the image-based baseline, the fusion yielded relatively distinct accuracy improvements for urban LCZ types at two sites; however, gains at the remaining sites were negligible or even slightly negative, suggesting that the benefits of fusion are modest and inconsistent. Collectively, these results indicate that the relationship between the LCZs and the measurable, visible aspects of urban form is tenuous, thus the LCZ framework should be used with caution in morphological studies.

Motivation & Objective

• Assess whether 2D urban morphometrics can predict LCZ types.
• Evaluate a baseline image-based LCZ prediction using satellite imagery.
• Test two fusion approaches that combine morphometrics with imagery for LCZ prediction across multiple sites.
• Compare performance across five urban sites to understand generalizability.
• Provide guidance on using LCZ in morphological studies based on observed relationships.

Proposed method

• Compute 321 two-dimensional morphometric attributes from building footprints and street networks at multiple scales.
• Develop four LCZ classification schemes: morphometric-based, baseline image-based, and two morphometrics+imagery fusion approaches.
• Evaluate classification performance across five sites to compare modalities and fusion utilities.
• Analyze the correspondence between morphometrics and LCZ types to assess predictability and site-dependence.

Experimental results

Research questions

• RQ1 Can 2D urban morphometrics alone accurately predict LCZ types across diverse sites?
• RQ2 Does fusing morphometrics with satellite imagery improve LCZ prediction over image-based baselines?
• RQ3 Is the relation between LCZs and visible urban-form attributes consistent across sites?

Key findings

• Morphometric-based LCZ prediction shows selective and inconsistent correspondence with LCZ types and is highly site-dependent.
• A broader set of urban form properties is relevant for distinguishing LCZ types than standard parameters.
• Fusion-based predictions yield relatively distinct accuracy improvements for LCZ types at two sites.
• Fusion gains at the remaining sites are negligible or slightly negative.
• Overall, the relationship between LCZs and visible urban-form attributes is tenuous, suggesting cautious use of LCZ in morphological studies.