A Daily Air Pollutant Concentration Prediction Framework Combining Successive Variational Mode Decomposition and Bidirectional Long Short-Term Memory Network DOI Open Access
Zhong Huang, Linna Li, Guorong Ding

et al.

Sustainability, Journal Year: 2023, Volume and Issue: 15(13), P. 10660 - 10660

Published: July 6, 2023

Precise and efficient air quality prediction plays a vital role in safeguarding public health informing policy-making. Fine particulate matter, specifically PM2.5 PM10, serves as crucial indicator for assessing managing pollution levels. In this paper, daily concentration model combining successive variational mode decomposition (SVMD) bidirectional long short-term memory (BiLSTM) neural network is proposed. Firstly, SVMD used an unsupervised feature-learning method to divide data into intrinsic functions (IMFs) extract frequency features improve trend prediction. Secondly, the BiLSTM introduced supervised learning capture small changes pollutant sequence perform of decomposed sequence. Furthermore, Bayesian optimization (BO) algorithm employed identify optimal key parameters model. Lastly, predicted values are reconstructed generate final results PM10 datasets. The performance proposed validated using datasets collected from China Environmental Monitoring Center Tianshui, Gansu, Wuhan, Hubei. show that can smooth original series more effectively than other methods, BO-BiLSTM better LSTM-based models, thereby proving has excellent feasibility accuracy.

Language: Английский

A novel carbon price forecasting method based on model matching, adaptive decomposition, and reinforcement learning ensemble strategy DOI

Zijie Cao,

Hui Liu

Environmental Science and Pollution Research, Journal Year: 2022, Volume and Issue: 30(13), P. 36044 - 36067

Published: Dec. 21, 2022

Language: Английский

Citations

10
Ensemble water quality forecasting based on decomposition, sub-model selection, and adaptive interval DOI
Tianxiang Liu, Wen Liu, Zihan Liu

et al.

Environmental Research, Journal Year: 2023, Volume and Issue: 237, P. 116938 - 116938

Published: Aug. 22, 2023

Language: Английский

Citations

6
Predicting PM2.5 in the Northeast China Heavy Industrial Zone: A Semi-Supervised Learning with Spatiotemporal Features DOI Creative Commons
Hongxun Jiang, Xiaotong Wang, Caihong Sun

et al.

Atmosphere, Journal Year: 2022, Volume and Issue: 13(11), P. 1744 - 1744

Published: Oct. 23, 2022

Particulate matter PM2.5 pollution affects the Chinese population, particularly in cities such as Shenyang northeastern China, which occupies a number of traditional heavy industries. This paper proposes semi-supervised learning model used for predicting concentrations. The incorporates rich data from real world, including 11 air quality monitoring stations and nearby cities. There are three types data: monitoring, meteorological data, spatiotemporal information (such effects emissions diffusion across different geographical regions). consists two classifiers: genetic programming (GP) to forecast concentrations support vector classification (SVC) predict trends. experimental results show that proposed performs better than baseline models accuracy, 3% 18% over classic multivariate linear regression (MLR), 1% 11% multi-layer perceptron neural network (MLP-ANN), 21% 68% (SVR). Furthermore, GP approach provides an intuitive contribution analysis factors backtracking points adjacent other critical forecasting shorter time intervals (1 h). Wind speeds more important longer (6 24

Language: Английский

Citations

9
A new decomposition-integrated air quality index prediction model DOI
Xiaolei Sun, Zhongda Tian, Zhijia Zhang

et al.

Earth Science Informatics, Journal Year: 2023, Volume and Issue: 16(3), P. 2307 - 2321

Published: June 26, 2023

Language: Английский

Citations

4
A Daily Air Pollutant Concentration Prediction Framework Combining Successive Variational Mode Decomposition and Bidirectional Long Short-Term Memory Network DOI Open Access
Zhong Huang, Linna Li, Guorong Ding

et al.

Sustainability, Journal Year: 2023, Volume and Issue: 15(13), P. 10660 - 10660

Published: July 6, 2023

Precise and efficient air quality prediction plays a vital role in safeguarding public health informing policy-making. Fine particulate matter, specifically PM2.5 PM10, serves as crucial indicator for assessing managing pollution levels. In this paper, daily concentration model combining successive variational mode decomposition (SVMD) bidirectional long short-term memory (BiLSTM) neural network is proposed. Firstly, SVMD used an unsupervised feature-learning method to divide data into intrinsic functions (IMFs) extract frequency features improve trend prediction. Secondly, the BiLSTM introduced supervised learning capture small changes pollutant sequence perform of decomposed sequence. Furthermore, Bayesian optimization (BO) algorithm employed identify optimal key parameters model. Lastly, predicted values are reconstructed generate final results PM10 datasets. The performance proposed validated using datasets collected from China Environmental Monitoring Center Tianshui, Gansu, Wuhan, Hubei. show that can smooth original series more effectively than other methods, BO-BiLSTM better LSTM-based models, thereby proving has excellent feasibility accuracy.

Language: Английский

Citations

4