A novel Encoder-Decoder model based on read-first LSTM for air pollutant prediction

Accurate air pollutant prediction allows effective environment management to reduce the impact of pollution and prevent pollution incidents. Existing studies of air pollutant prediction are mostly interdisciplinary involving environmental science and computer science where the problem is formulated...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:The Science of the total environment Jg. 765; S. 144507
Hauptverfasser: Zhang, Bo, Zou, Guojian, Qin, Dongming, Lu, Yunjie, Jin, Yupeng, Wang, Hui
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Netherlands Elsevier B.V 15.04.2021
Schlagworte:
Air pollutant prediction
air pollutants
computer science
Deep learning
Encoder-Decoder model
environment
Long short term memory
neural networks
Numerical analysis
prediction
Recurrent neural networks
time series analysis
Deep learning
Air pollutant prediction
Recurrent neural networks
Encoder-Decoder model
Numerical analysis
Long short term memory
ISSN:0048-9697, 1879-1026, 1879-1026
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Accurate air pollutant prediction allows effective environment management to reduce the impact of pollution and prevent pollution incidents. Existing studies of air pollutant prediction are mostly interdisciplinary involving environmental science and computer science where the problem is formulated as time series prediction. A prevalent recent approach to time series prediction is the Encoder-Decoder model, which is based on recurrent neural networks (RNN) such as long short-term memory (LSTM), and great potential has been demonstrated. An LSTM network relies on various gate units, but in most existing studies the correlation between gate units is ignored. This correlation is important for establishing the relationship of the random variables in a time series as the stronger is this correlation, the stronger is the relationship between the random variables. In this paper we propose an improved LSTM, named Read-first LSTM or RLSTM for short, which is a more powerful temporal feature extractor than RNN, LSTM and Gated Recurrent Unit (GRU). RLSTM has some useful properties: (1) enables better store and remember capabilities in longer time series and (2) overcomes the problem of dependency between gate units. Since RLSTM is good at long term feature extraction, it is expected to perform well in time series prediction. Therefore, we use RLSTM as the Encoder and LSTM as the Decoder to build an Encoder-Decoder model (EDSModel) for pollutant prediction in this paper. Our experimental results show, for 1 to 24 h prediction, the proposed prediction model performed well with a root mean square error of 30.218. The effectiveness and superiority of RLSTM and the prediction model have been demonstrated. [Display omitted] •The review highlights model prediction performance improvement and solving long time series prediction problem.•RLSTM effectively solving the problem of insufficient extraction of pollutants and meteorological data features.•EDSModel yields higher-accuracy predictions by fully extracting data features, and overcomes long-term dependency.•EDSModel has been applied as one of the practical auxiliary models in the national urban pollution prediction tasks.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:0048-9697
1879-1026
1879-1026
DOI:10.1016/j.scitotenv.2020.144507