File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.buildenv.2023.110960
- Scopus: eid_2-s2.0-85175530723
- WOS: WOS:001107666000001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Combining physical approaches with deep learning techniques for urban building energy modeling: A comprehensive review and future research prospects
| Title | Combining physical approaches with deep learning techniques for urban building energy modeling: A comprehensive review and future research prospects |
|---|---|
| Authors | |
| Keywords | AIGC Data-driven Deep learning Hybrid model Large language model Physics-based urban building energy modeling |
| Issue Date | 1-Jul-2023 |
| Publisher | Elsevier |
| Citation | Building and Environment, 2023, v. 246 How to Cite? |
| Abstract | In recent times, there has been a growing interest in urban building energy modeling (UBEM), owing to its potential benefits for cities. These benefits include aiding city decision-makers in comprehending building energy demand, managing and planning urban energy supply, developing building energy efficiency measures, and analyzing urban building retrofits. The physical approach has historically been a common method for studying energy in urban buildings. Notwithstanding, with the progress of artificial intelligence, powerful deep learning techniques are increasingly being utilized to overcome some of the physical approach's limitations. Consequently, the combination of physical approaches with deep learning algorithms for UBEM research has become a popular area of study. The purpose of this paper is to present an updated review of UBEM studies from three perspectives: model preparation, model simulation, and model calibration. The principal aim of this review is to investigate and analyze the present research status, challenges, obstacles, and research gaps of deep learning techniques in physics-based UBEM. This analysis is followed by a discussion of feasible options. Finally, four distinct viewpoints are provided to explore the future research prospects of deep learning techniques and to propose technically viable pathways for each perspective. |
| Persistent Identifier | http://hdl.handle.net/10722/339072 |
| ISSN | 2023 Impact Factor: 7.1 2023 SCImago Journal Rankings: 1.647 |
| ISI Accession Number ID |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Li, Zheng | - |
| dc.contributor.author | Ma, Jun | - |
| dc.contributor.author | Tan, Yi | - |
| dc.contributor.author | Guo, Cui | - |
| dc.contributor.author | Li, Xiao | - |
| dc.date.accessioned | 2024-03-11T10:33:40Z | - |
| dc.date.available | 2024-03-11T10:33:40Z | - |
| dc.date.issued | 2023-07-01 | - |
| dc.identifier.citation | Building and Environment, 2023, v. 246 | - |
| dc.identifier.issn | 0360-1323 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/339072 | - |
| dc.description.abstract | <p>In recent times, there has been a growing interest in urban building energy modeling (UBEM), owing to its potential benefits for cities. These benefits include aiding city decision-makers in comprehending building energy demand, managing and planning urban energy supply, developing <a href="https://www.sciencedirect.com/topics/engineering/building-energy-efficiency" title="Learn more about building energy efficiency from ScienceDirect's AI-generated Topic Pages">building energy efficiency</a> measures, and analyzing urban <a href="https://www.sciencedirect.com/topics/engineering/building-retrofit" title="Learn more about building retrofits from ScienceDirect's AI-generated Topic Pages">building retrofits</a>. The physical approach has historically been a common method for studying energy in urban buildings. Notwithstanding, with the progress of artificial intelligence, powerful <a href="https://www.sciencedirect.com/topics/engineering/deep-learning" title="Learn more about deep learning from ScienceDirect's AI-generated Topic Pages">deep learning</a> techniques are increasingly being utilized to overcome some of the physical approach's limitations. Consequently, the combination of physical approaches with <a href="https://www.sciencedirect.com/topics/engineering/deep-learning" title="Learn more about deep learning from ScienceDirect's AI-generated Topic Pages">deep learning</a> algorithms for UBEM research has become a popular area of study. The purpose of this paper is to present an updated review of UBEM studies from three perspectives: model preparation, model simulation, and model calibration. The principal aim of this review is to investigate and analyze the present research status, challenges, obstacles, and research gaps of deep learning techniques in physics-based UBEM. This analysis is followed by a discussion of feasible options. Finally, four distinct viewpoints are provided to explore the future research prospects of deep learning techniques and to propose technically viable pathways for each perspective.</p> | - |
| dc.language | eng | - |
| dc.publisher | Elsevier | - |
| dc.relation.ispartof | Building and Environment | - |
| dc.subject | AIGC | - |
| dc.subject | Data-driven | - |
| dc.subject | Deep learning | - |
| dc.subject | Hybrid model | - |
| dc.subject | Large language model | - |
| dc.subject | Physics-based urban building energy modeling | - |
| dc.title | Combining physical approaches with deep learning techniques for urban building energy modeling: A comprehensive review and future research prospects | - |
| dc.type | Article | - |
| dc.identifier.doi | 10.1016/j.buildenv.2023.110960 | - |
| dc.identifier.scopus | eid_2-s2.0-85175530723 | - |
| dc.identifier.volume | 246 | - |
| dc.identifier.eissn | 1873-684X | - |
| dc.identifier.isi | WOS:001107666000001 | - |
| dc.identifier.issnl | 0360-1323 | - |