File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.3390/app10010014
- Scopus: eid_2-s2.0-85077534452
- WOS: WOS:000509398900014
Supplementary
- Citations:
- Appears in Collections:
Article: Prediction of ambient PM2.5 concentrations using a correlation filtered spatial-temporal long short-term memory model
Title | Prediction of ambient PM2.5 concentrations using a correlation filtered spatial-temporal long short-term memory model |
---|---|
Authors | |
Keywords | Deep learning PM2.5 Spatialtemporal correlation Air quality forecasting Long short-term memory |
Issue Date | 2020 |
Citation | Applied Sciences, 2020, v. 10, n. 1, article no. 14 How to Cite? |
Abstract | © 2019 by the authors. Due to the increasingly serious air pollution problem, air quality prediction has been an important approach for air pollution control and prevention. Many prediction methods have been proposed in recent years to improve the prediction accuracy. However, most of the existing methods either did not consider the spatial relationships between monitoring stations or overlooked the strength of the correlation. Excluding the spatial correlation or including too much weak spatial inputs could influence the modeling and reduce the prediction accuracy. To overcome the limitation, this paper proposes a correlation filtered spatial-temporal long short-term memory (CFST-LSTM) model for air quality prediction. The model is designed based on the original LSTM model and is equipped with a spatial-temporal filter (STF) layer. This layer not only takes into account the spatial influence between stations, but also can extract highly correlated sequential data and drop weaker ones. To evaluate the proposed CFST-LSTM model, hourly PM2.5 concentration data of California are collected and preprocessed. Several experiments are conducted. The experimental results show that the CFST-LSTM model can effectively improve the prediction accuracy and has great generalization. |
Persistent Identifier | http://hdl.handle.net/10722/287012 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ding, Yuexiong | - |
dc.contributor.author | Li, Zheng | - |
dc.contributor.author | Zhang, Chengdian | - |
dc.contributor.author | Ma, Jun | - |
dc.date.accessioned | 2020-09-07T11:46:15Z | - |
dc.date.available | 2020-09-07T11:46:15Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Applied Sciences, 2020, v. 10, n. 1, article no. 14 | - |
dc.identifier.uri | http://hdl.handle.net/10722/287012 | - |
dc.description.abstract | © 2019 by the authors. Due to the increasingly serious air pollution problem, air quality prediction has been an important approach for air pollution control and prevention. Many prediction methods have been proposed in recent years to improve the prediction accuracy. However, most of the existing methods either did not consider the spatial relationships between monitoring stations or overlooked the strength of the correlation. Excluding the spatial correlation or including too much weak spatial inputs could influence the modeling and reduce the prediction accuracy. To overcome the limitation, this paper proposes a correlation filtered spatial-temporal long short-term memory (CFST-LSTM) model for air quality prediction. The model is designed based on the original LSTM model and is equipped with a spatial-temporal filter (STF) layer. This layer not only takes into account the spatial influence between stations, but also can extract highly correlated sequential data and drop weaker ones. To evaluate the proposed CFST-LSTM model, hourly PM2.5 concentration data of California are collected and preprocessed. Several experiments are conducted. The experimental results show that the CFST-LSTM model can effectively improve the prediction accuracy and has great generalization. | - |
dc.language | eng | - |
dc.relation.ispartof | Applied Sciences | - |
dc.rights | This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License. | - |
dc.subject | Deep learning | - |
dc.subject | PM2.5 | - |
dc.subject | Spatialtemporal correlation | - |
dc.subject | Air quality forecasting | - |
dc.subject | Long short-term memory | - |
dc.title | Prediction of ambient PM2.5 concentrations using a correlation filtered spatial-temporal long short-term memory model | - |
dc.type | Article | - |
dc.description.nature | published_or_final_version | - |
dc.identifier.doi | 10.3390/app10010014 | - |
dc.identifier.scopus | eid_2-s2.0-85077534452 | - |
dc.identifier.volume | 10 | - |
dc.identifier.issue | 1 | - |
dc.identifier.spage | article no. 14 | - |
dc.identifier.epage | article no. 14 | - |
dc.identifier.eissn | 2076-3417 | - |
dc.identifier.isi | WOS:000509398900014 | - |
dc.identifier.issnl | 2076-3417 | - |