File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.uclim.2023.101499
- Scopus: eid_2-s2.0-85154609409
- WOS: WOS:001004337900001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: Machine learning applications on air temperature prediction in the urban canopy layer: A critical review of 2011–2022
Title | Machine learning applications on air temperature prediction in the urban canopy layer: A critical review of 2011–2022 |
---|---|
Authors | |
Keywords | Artificial intelligence Machine learning Urban heat island Urban temperature |
Issue Date | 2023 |
Citation | Urban Climate, 2023, v. 49, article no. 101499 How to Cite? |
Abstract | Air temperature within the urban canopy layer is one of the most critical variables that impact the environmental sustainability of cities. With advantages in computational speed, machine learning approaches have been increasingly applied for urban air temperature prediction. Yet the current status and limitations of machine learning applications remain largely unclear. This study critically reviews 45 articles that use machine learning for urban air temperature prediction between 2011 and 2022. By separating the studies into two groups, we find that tree-based models fit for spatial prediction and neural network models work for temporal prediction. For spatial prediction, the root-mean-square error (RMSE) varies from 0.10 to 2.60 °C, and there is no clear relationship between RMSE and spatial resolution. Prediction errors of temporal studies tend to increase with the time horizon, with an RMSE of 1.35 ± 0.60 °C (4.02 ± 0.93 °C) for 4-h (5-days) ahead prediction. We provide three key recommendations to enhance the reliability and performance of future machine learning applications: 1) reporting metadata, quality control process, and model evaluation in detail, 2) fusing the temperature data from different sources and diversifying predictor variables, and 3) improving machine learning by stacking and integration with physical-based models. |
Persistent Identifier | http://hdl.handle.net/10722/330307 |
ISSN | 2021 Impact Factor: 6.663 2020 SCImago Journal Rankings: 1.151 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, Han | - |
dc.contributor.author | Yang, Jiachuan | - |
dc.contributor.author | Chen, Guangzhao | - |
dc.contributor.author | Ren, Chao | - |
dc.contributor.author | Zhang, Jize | - |
dc.date.accessioned | 2023-09-05T12:09:27Z | - |
dc.date.available | 2023-09-05T12:09:27Z | - |
dc.date.issued | 2023 | - |
dc.identifier.citation | Urban Climate, 2023, v. 49, article no. 101499 | - |
dc.identifier.issn | 2212-0955 | - |
dc.identifier.uri | http://hdl.handle.net/10722/330307 | - |
dc.description.abstract | Air temperature within the urban canopy layer is one of the most critical variables that impact the environmental sustainability of cities. With advantages in computational speed, machine learning approaches have been increasingly applied for urban air temperature prediction. Yet the current status and limitations of machine learning applications remain largely unclear. This study critically reviews 45 articles that use machine learning for urban air temperature prediction between 2011 and 2022. By separating the studies into two groups, we find that tree-based models fit for spatial prediction and neural network models work for temporal prediction. For spatial prediction, the root-mean-square error (RMSE) varies from 0.10 to 2.60 °C, and there is no clear relationship between RMSE and spatial resolution. Prediction errors of temporal studies tend to increase with the time horizon, with an RMSE of 1.35 ± 0.60 °C (4.02 ± 0.93 °C) for 4-h (5-days) ahead prediction. We provide three key recommendations to enhance the reliability and performance of future machine learning applications: 1) reporting metadata, quality control process, and model evaluation in detail, 2) fusing the temperature data from different sources and diversifying predictor variables, and 3) improving machine learning by stacking and integration with physical-based models. | - |
dc.language | eng | - |
dc.relation.ispartof | Urban Climate | - |
dc.subject | Artificial intelligence | - |
dc.subject | Machine learning | - |
dc.subject | Urban heat island | - |
dc.subject | Urban temperature | - |
dc.title | Machine learning applications on air temperature prediction in the urban canopy layer: A critical review of 2011–2022 | - |
dc.type | Article | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1016/j.uclim.2023.101499 | - |
dc.identifier.scopus | eid_2-s2.0-85154609409 | - |
dc.identifier.volume | 49 | - |
dc.identifier.spage | article no. 101499 | - |
dc.identifier.epage | article no. 101499 | - |
dc.identifier.isi | WOS:001004337900001 | - |