A segmented approach to modeling building height
Delineating high-rise and low-rise buildings for enhanced height estimation
Bibliographic Data
| ID | 7150544 |
|---|---|
| Authors | Clinton Stipek (0000-0002-8050-1096, Oak Ridge National Laboratory, corresponding author), Daniel Adams (0000-0001-9695-0577, Oak Ridge National Laboratory), Philipe Dias, Philipe Ambrozio Dias (0000-0001-9427-7112, Oak Ridge National Laboratory), Taylor Hauser (0000-0002-5088-5236, Oak Ridge National Laboratory), Viswadeep Lebakula (0000-0001-5293-5914, Oak Ridge National Laboratory), Alexander Sorokine (Oak Ridge National Laboratory), Justin Epting (0000-0001-5482-6914, Oak Ridge National Laboratory), Jessica Moehl (0000-0001-9579-2562, Oak Ridge National Laboratory), Robert Stewart (0000-0002-6326-915X, Oak Ridge National Laboratory) |
| Year | 2025 |
| Volume | 119 |
| Pages | 102287 |
| Publication date | 2025-07-01 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Computers Environment and Urban Systems (JOURNAL) |
| Journal identifiers | ISSN: 0198-9715 • E-ISSN: 1873-7587 |
| Publisher | Elsevier BV (PUBLISHER) |
| DOI | 10.1016/j.compenvurbsys.2025.102287 |
| OpenAlex | W4409251578 |
| Language | EN |
| Citations received | 1 |
| References cited | 24 |
Understanding building height is imperative to the overall study of energy efficiency, population distribution, urban morphologies, emergency response, among others. Currently, existing approaches for modeling building height at scale are hindered by two pervasive issues. First, there is no consistent approach to quantify what a high-rise building is at a macro scale, leaving researchers unable to accurately compare results across geographies and domains. Second, high-rise buildings represent a small fraction of the built environment, implying data imbalance challenges that negatively affect current approaches. This is a problem of practical relevance since information on high-rise buildings is important for studies on urban heat islands, population dynamics, and pollution dispersion. Here, we introduce a novel approach to map building height which first identifies two distinct distributions within the built environment, with one being composed of low-rise buildings and one composed of high-rise buildings. We then develop an ensemble scheme where discrete specialist models are trained for each subset of low-rise buildings and high-rise buildings to infer building height from morphology features. For experiments mapping heights of 4.85 million buildings in Japan, we show an increase of 34 % in accuracy within 3 m error when compared to the current state-of-the-art when modeling high-rise buildings, which based on KNN experimentation we define as any building > 12 m . Our findings show that such an ensemble framework outperforms the current state-of-the-art approaches, which is especially relevant in relation to inferring height for high-rise buildings, a prominent issue of existing approaches for mapping the built environment. • An ensemble model is developed to address morphological height estimation challenges associated with high-rise buildings • A component model is developed to infer building height classification strictly from planar footprint morphology features • A within -class ML model is developed that outperforms classless estimation models for both high-rise and low-rise buildings • Improved height estimation for tall buildings improves the fidelity of urban 3D models and other built environment analytics
Archaeology · Architectural engineering · Estimation · Geodesy · Geography · High rise · Low-rise · Meteorology · Structural engineering · 3D Surveying and Cultural Heritage · Engineering · Environmental Science · Structural Health Monitoring Techniques · Urban Heat Island Mitigation
| Unique citing works | 1 |
|---|---|
| Citations per year | 1 |
| Citation span | 2025 - 2025 (1) |
| Citation velocity | recent |
| Highly cited | No |
| Citation types | Neutral: 1 |