Abstract
Fine particulate matter (\( PM_{2.5}\)) poses a significant threat to human life and health, and therefore, accurately predicting \( PM_{2.5}\) concentration is critical for controlling air pollution. Two improved types of recurrent neural networks (RNNs), the long short-term memory (LSTM) and gated recurrent unit (GRU), have been widely used in time series data prediction due to their ability to capture temporal features. However, both degrade into random guessing as the time length increases. In order to enhance the accuracy of \( PM_{2.5}\) concentration prediction and address the issue of random guessing in RNNs neural networks, this study introduces a TCN-biGRU neural network model. This model is a hybrid prediction approach based on combining temporal convolutional networks (TCN) and bidirectional gated recurrent units (bi-GRU). TCN extracts higher-level feature information from longer time series data of \( PM_{2.5}\) concentrations, while bi-GRU captures features from past and future data to achieve more accurate predictive outcomes. This case study utilizes data from monitoring stations in Beijing in 2021 for conducting \( PM_{2.5}\) prediction experiments. The TCN-biGRU model achieves an average absolute error, root mean square error, and \( R^{2}\) of 4.20, 7.71, and 0.961 in its predictive outcomes. When compared to the predictive outcomes of individual LSTM, GRU, and bi-GRU models, it is evident that the TCN-biGRU model exhibits smaller errors and superior predictive performance.
Similar content being viewed by others
Data availability
Not applicable
References
Ackerson JM, Dave R, Seliya N (2021) Applications of recurrent neural network for biometric authentication & anomaly detection. arXiv:2109.05701
Bai S, Kolter JZ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv:1803.01271
Cho K, Van Merriënboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv:1406.1078
Ding W, Zhu Y (2022) Prediction of PM2.5 concentration in Ningxia Hui autonomous region based on PCA-Attention-LSTM. Atmosphere, 13:1444
Dong F, Yu B, Pan Y (2019) Examining the synergistic effect of CO2 emissions on PM2.5 emissions reduction: evidence from China. J Clean Prod 223:759–771
Flores JHF, Engel PM, Pinto RC (2012) Autocorrelation and partial autocorrelation functions to improve neural networks models on univariate time series forecasting. In: The 2012 international joint conference on neural networks (IJCNN), IEEE, pp 1–8
Gao Y, Li Y (2022) Prediction of rainfall-type debris flow in Jiangjiagou based on LSTM-Attention. 2022 3rd International conference on computer vision, image and deep learning & international conference on computer engineering and applications (CVIDL & ICCEA), IEEE, pp 1–6
Ge L, Zhou A, Li H, Liu J (2019) Spatially fine-grained air quality prediction based on DBU-LSTM. In: Proceedings of the 16th ACM international conference on computing frontiers, pp 202–205
Hu C, Cheng F, Ma L, Li B (2022) State of charge estimation for lithium-ion batteries based on TCN-LSTM neural networks. J Electrochem Soc 169(3):030544
Huang G, Li X, Zhang B, Ren J (2021) PM2.5 concentration forecasting at surface monitoring sites using GRU neural network based on empirical mode decomposition. Sci Total Environ 768:144516
Kim J, Lee Y (2020) Accelerating RNN transducer inference via one-step constrained beam search. arXiv:2002.03577
Li M, Xiang Q, Chen Z, Wang M (2018) A unified neural network for quality estimation of machine translation. IEICE Trans Inf Syst 101(9):2417–2421
Li R, Kou X, Geng H, Xie J, Yang Z, Zhang Y, Cai Z, Dong C (2015) Effect of ambient PM2.5 on lung mitochondrial damage and fusion/fission gene expression in rats. Chem Res Toxicol 28(3):408–418
Li W, Wei Y, An D, Jiao Y, Wei Q (2022) LSTM-TCN: dissolved oxygen prediction in aquaculture, based on combined model of long short-term memory network and temporal convolutional network. Environ Sci Pollut Res Int 29(26):39545–39556
Li X, Li L, Chen L, Zhang T, Xiao J, Chen L (2022b) Random forest estimation and trend analysis of PM2. 5 concentration over the Huaihai economic zone, China (2000–2020). Sustainability 14(14):8520
Li Y, Zhu Z, Xin C, Chen Z, Wang S, Liang Z, Zou X (2022c) Research on the spatiotemporal characteristics and concentration prediction model of PM2.5 during Winter in Jiangbei New District, Nanjing, China. Atmosphere, 13:1542
Liang R, Chang X, Jia P, Xu C (2020) Mine gas concentration forecasting model based on an optimized BiGRU network. ACS omega 5(44):28579–28586
Liang C, Jiang Y, Zhang T, Ji Y, Zhang Y, Sun Y, Li S, Qi Y, Wang Y, Cai Y et al (2023) Atmospheric particulate matter impairs cognition by modulating synaptic function via the nose-to-brain route. Sci Total Environ 857:159600
Liu Y, Ma J, Tao Y, Shi L, Wei L, Li L (2020) Hybrid neural network text classification combining TCN and GRU. In: 2020 IEEE 23rd international conference on computational science and engineering (CSE), pp 30–35
Liu F, Liu C, Liu Y, Wang J, Wang Y, Yan B (2023) Neurotoxicity of the air-borne particles: from molecular events to human diseases. J Hazard Mater 131827
Mansouri M, Dhibi K, Hajji M, Bouzara K, Nounou H, Nounou M (2022) Interval-valued reduced RNN for fault detection and diagnosis for wind energy conversion systems. IEEE Sensors J 22(13):13581–13588
Ortega-Bueno R, Rosso P, Pagola JEM (2019) UO UPV2 at HAHA 2019: BiGRU neural network informed with linguistic features for humor recognition. In: Proceedings of the Iberian languages evaluation forum (IberLEF 2019). CEUR Workshop Proceedings, CEUR-WS, Bilbao, Spain (9 2019)
Park S-Y, Yoon D-K, Park S-H, Jeon J-I, Lee J-M, Yang W-H, Cho Y-S, Kwon J, Lee C-M (2023) Proposal of a methodology for prediction of indoor PM2. 5 concentration using sensor-based residential environments monitoring data and time-divided multiple linear regression model. Toxics 11(6):526
Pearson, K (1900) Mathematical contributions to the theory of evolution. VIII. On the correlation of characters not quantitatively measurable. Proceedings of the Royal Society of London 66(424-433):241–244
Popescu M, Mihalache SF, Oprea M (2017) Air pollutants and meteorological parameters influence on PM2.5 forecasting and performance assessment of the developed artificial intelligence-based forecasting model. Revista De Chimie 68:864–868
Qi Z, Song Y, Ding Q, Liao X, Li R, Liu G, Tsang S, Cai Z (2019) Water soluble and insoluble components of PM2.5 and their functional cardiotoxicities on neonatal rat cardiomyocytes in vitro. Ecotoxicol Environ Saf 168:378–387
Shi P, Fang X, Ni J, Zhu J (2021) An improved attention-based integrated deep neural network for PM2.5 concentration prediction. Appl Sci 11:4001
Song Y-Z, Yang H-L, Peng J-H, Song Y-R, Sun Q, Li Y (2015) Estimating PM2. 5 concentrations in Xi’an city using a generalized additive model with multi-source monitoring data. PloS one 10(11):e0142149
Song C, He J, Wu L, Jin T, Chen X, Li R, Ren P, Zhang L, Mao H (2017) Health burden attributable to ambient PM2.5 in China. Environ Pollut 223:575–586
Tanaka T, Nambu I, Maruyama Y, Wada Y (2022) Sliding-window normalization to improve the performance of machine-learning models for real-time motion prediction using electromyography. Sensors 22(13):5005
Wang B, Kong W, Zhao P (2021) An air quality forecasting model based on improved convnet and RNN. Soft Comput 25(14):9209–9218
Wu X, Zhang C, Zhu J, Zhang X (2022) Research on PM2.5 concentration prediction based on the CE-AGA-LSTM model. Appl Sci 12(14):7009
Xie Y, Chen X, Zhang L (2023) Prediction of PM2. 5 concentration based on CNNLSTM deep learning model. 2023 Asia-Europe conference on electronics, data processing and informatics (ACEDPI), IEEE, pp 229–233
Yan J, Mu L, Wang L, Ranjan R, Zomaya AY (2020) Temporal convolutional networks for the advance prediction of ENSO. Sci Rep 10(1):1–15
Younan D, Petkus AJ, Widaman KF, Xinhui W, Ramon C, Espeland MA, Margaret G, Henderson VW, Manson JE, Rapp SR, Sachs BC, Serre ML, Gaussoin SA, Barnard R, Saldana S, Vizuete W, Beavers DP, Salinas JA, Chui HC, Resnick SM, Shumaker SA, Chen JC (2020) Particulate matter and episodic memory decline mediated by early neuroanatomic biomarkers of Alzheimer’s disease. Brain 143(1):289–302
Yule GU (1927) On a method of investigating periodicities in distributed series, with special reference to Wolfer’s sunspot numbers. Phil Trans R Soc London A 226:267–298
Zhang B, Jia M, Xu J, Zhao W, Deng L (2022a) Network security situation prediction model based on EMD and ELPSO optimized BiGRU neural network. Computational Intelligence and Neuroscience, 2022
Zhang M, Wu D, Xue R (2021) Hourly prediction of PM 2.5 concentration in Beijing based on Bi-LSTM neural network. Multimed Tools Appl 80:24455–24468
Zhang P, Xue J, Lan C, Zeng W, Gao Z, Zheng N (2019) EleAtt-RNN: adding attentiveness to neurons in recurrent neural networks. IEEE Trans Image Process 29:1061–1073
Zhang P, Xue J, Lan C, Zeng W, Gao Z, Zheng N (2019) EleAtt-RNN: adding attentiveness to neurons in recurrent neural networks. IEEE Trans Image Process 99:1–1
Zhang X, Fan Y, Wei S, Wang H, Zhang J (2021) Spatiotemporal distribution of PM2.5 and its correlation with other air pollutants in winter during, (2016) 2018 in Xi’an. China. Pol J Environ Stud 30(2):1457–1464
Zhang Z, Zhang S, Zhao X, Chen L, Yao J (2022b) Temporal difference-based graph transformer networks for air quality PM2.5 prediction: a case study in China. Front Environ Sci 10:924986. https://doi.org/10.3389/fenvs.2022.924986
Zhou X, Xu J, Zeng P, Meng X (2019) Air pollutant concentration prediction based on GRU method. J Phys Conf Ser 1168(3):032058
Zhu J, Jiang Q, Shen Y, Qian C, Xu F, Zhu Q (2022) Application of recurrent neural network to mechanical fault diagnosis: a review. J Mech Sci Technol 36:527–542
Zou Y, Jin C, Su Y, Li J, Zhu B (2016) Water soluble and insoluble components of urban PM2.5 and their cytotoxic effects on epithelial cells (A549) in vitro. Environ Pollut 212:627–635
Funding
This work was supported in part by the Organization Department of Beijing Municipal Committee under Grant Z2020549, in part by the Ministry of Education of China under Grant 202102341001, 202102165002, in part by the National Science Foundation of China under Grant 62273011 and Grant 62076013, and in part by the Beijing Natural Science Foundation under Grant JQ21014.
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection, and analysis were performed by WY and AQ. The first draft of the manuscript was written by PL. TS helped perform the analysis with constructive discussions, and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethical approval
Not applicable
Consent to participate
Not applicable
Consent for publication
Not applicable
Competing interests
The authors declare no competing interests.
Additional information
Responsible editor: Marcus Schulz.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Shi, T., Li, P., Yang, W. et al. Application of TCN-biGRU neural network in \( PM_{2.5}\) concentration prediction. Environ Sci Pollut Res 30, 119506–119517 (2023). https://doi.org/10.1007/s11356-023-30354-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11356-023-30354-6