Decoding Ethiopian Abodes: Towards Classifying Buildings by Occupancy Type Using Footprint Morphology
- ORNL
Building occupancy classification plays a crucial role in urban planning, disaster management, and population modeling. Traditional methods often require extensive field surveys or detailed datasets, which can be time-consuming, expensive, and may yield incomplete or erroneous data. In this paper, we present a novel approach for classifying buildings as residential or non-residential using only building footprint data. By extracting geometric shape derivatives that characterize building morphology, we developed a high-accuracy classification model employing a combination of unsupervised and supervised learning methods. We utilized open-source data from Open Street Map, aggregating it to create binary labels for buildings based on their respective human use type. Our approach demonstrates the potential for scalability without the need for additional data sources other than building footprints and labels, offering a more efficient solution for building occupancy classification.
- Research Organization:
- Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 2329598
- Resource Relation:
- Conference: 2023 International Conference on Machine Learning and Applications (ICMLA) - Jacksonville, Florida, United States of America - 12/15/2023 5:00:00 AM-12/17/2023 5:00:00 AM
- Country of Publication:
- United States
- Language:
- English
Similar Records
Imputation of missing data using machine learning techniques