Search engine for discovering works of Art, research articles, and books related to Art and Culture
ShareThis
Javascript must be enabled to continue!

Application of Data-Driven Approaches to Urban Building Energy Modelling Using Machine Learning

View through CrossRef
This study introduces an innovative data-driven approach to Urban Building Energy Modeling (UBEM) to enhance urban energy efficiency planning, using Dublin, Ireland, as a pilot to demonstrate the applicability and effectiveness of our algorithms. Our methodology integrates diverse geospatial data of buildings and the built environment in Dublin, incorporating environmental and spatial configurations. We utilized four advanced Machine Learning (ML) algorithms including Decision Trees (DT), K-Nearest Neighbors (KNN), Random Forest (RF), and Support Vector Machine (SVM) to model and classify Building Energy Ratings (BER). The performance of four ML models was evaluated compared using advanced statistical metrics including Receiver Operating Characteristic (ROC), Area Under the Curve (AUC), Overall Accuracy (OA), kappa (κ), precision, and recall. RF model emerged as the top performer, achieving the highest accuracy in classifying all BER classes (BER E1 to BER G) with AUC values ranging from 0.77 to 0.83, particularly excelling in Class 3 (BER G). The DT and KNN models followed closely, while the SVM model underperformed with AUC values between 0.37 and 0.49. Class 3 (BER G) consistently showed superior classification results across all models, indicating high building energy rates. Conversely, Class 1 (BER E2) was the least accurately classified. The ML models reveal BER patterns and classifications across different building samples, highlighting the importance of integrating diverse building-specific parameters and urban-scale features to enhance the understanding of BER characteristics. By aligning BER with relevant European International Organization for Standardization (ISO) and European Committee for Standardization (CEN) standards, we can justify the scalability of our approach beyond Dublin. These ISO/CEN standards provide guidelines and specifications for energy performance in buildings, ensuring that our methodology can be uniformly applied across different European contexts. This novel contribution of this paper advances the field beyond the current state of the art by providing a robust methodology for analyzing BER and supporting sustainable urban development.
Title: Application of Data-Driven Approaches to Urban Building Energy Modelling Using Machine Learning
Description:
This study introduces an innovative data-driven approach to Urban Building Energy Modeling (UBEM) to enhance urban energy efficiency planning, using Dublin, Ireland, as a pilot to demonstrate the applicability and effectiveness of our algorithms.
Our methodology integrates diverse geospatial data of buildings and the built environment in Dublin, incorporating environmental and spatial configurations.
We utilized four advanced Machine Learning (ML) algorithms including Decision Trees (DT), K-Nearest Neighbors (KNN), Random Forest (RF), and Support Vector Machine (SVM) to model and classify Building Energy Ratings (BER).
The performance of four ML models was evaluated compared using advanced statistical metrics including Receiver Operating Characteristic (ROC), Area Under the Curve (AUC), Overall Accuracy (OA), kappa (κ), precision, and recall.
RF model emerged as the top performer, achieving the highest accuracy in classifying all BER classes (BER E1 to BER G) with AUC values ranging from 0.
77 to 0.
83, particularly excelling in Class 3 (BER G).
The DT and KNN models followed closely, while the SVM model underperformed with AUC values between 0.
37 and 0.
49.
Class 3 (BER G) consistently showed superior classification results across all models, indicating high building energy rates.
Conversely, Class 1 (BER E2) was the least accurately classified.
The ML models reveal BER patterns and classifications across different building samples, highlighting the importance of integrating diverse building-specific parameters and urban-scale features to enhance the understanding of BER characteristics.
By aligning BER with relevant European International Organization for Standardization (ISO) and European Committee for Standardization (CEN) standards, we can justify the scalability of our approach beyond Dublin.
These ISO/CEN standards provide guidelines and specifications for energy performance in buildings, ensuring that our methodology can be uniformly applied across different European contexts.
This novel contribution of this paper advances the field beyond the current state of the art by providing a robust methodology for analyzing BER and supporting sustainable urban development.

Related Results

Macroeconomic and Social Precursors of Suicide Rates in the Philippines: A Quantitative Analysis (Preprint)
Macroeconomic and Social Precursors of Suicide Rates in the Philippines: A Quantitative Analysis (Preprint)
BACKGROUND Suicide is a complex, serious and multifaceted public health issue that poses significant challenges to societies worldwide. In fact, it represen...
Selection of Injectable Drug Product Composition using Machine Learning Models (Preprint)
Selection of Injectable Drug Product Composition using Machine Learning Models (Preprint)
BACKGROUND As of July 2020, a Web of Science search of “machine learning (ML)” nested within the search of “pharmacokinetics or pharmacodynamics” yielded over 100...
CREATING LEARNING MEDIA IN TEACHING ENGLISH AT SMP MUHAMMADIYAH 2 PAGELARAN ACADEMIC YEAR 2020/2021
CREATING LEARNING MEDIA IN TEACHING ENGLISH AT SMP MUHAMMADIYAH 2 PAGELARAN ACADEMIC YEAR 2020/2021
The pandemic Covid-19 currently demands teachers to be able to use technology in teaching and learning process. But in reality there are still many teachers who have not been able ...
Architecture and adaptation
Architecture and adaptation
«The architectural work transcends the architect, goes beyond the moment in which its construction takes place, and therefore can be contemplated under the changing lights of histo...
Territories -in- between
Territories -in- between
There is an increasing body of literature suggesting that the conventional idea of a gradual transition in spatial structure from urban to rural does not properly reflect contempor...
Energetic Communities
Energetic Communities
The necessity for transition in the energy sector is beyond dispute and high on the political agendas. Climate change, the depletion of fossil fuels and the vulnerability of econom...
De gevel – een intermediair element tussen buiten en binnen
De gevel – een intermediair element tussen buiten en binnen
This study is based on the fact that all people have a basic need for protection from other people (and animals) as well as from the elements (the exterior climate). People need a ...
The post-urbanization of Tokyo
The post-urbanization of Tokyo
The urbanization of the global population could lead human societies to both declining and aging populations. This is because mature urban societies tend to provide urban dwellers,...

Back to Top