{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T18:23:45Z","timestamp":1784053425206,"version":"3.55.0"},"reference-count":26,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2021,7,13]],"date-time":"2021-07-13T00:00:00Z","timestamp":1626134400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["51939001 and 61976033"],"award-info":[{"award-number":["51939001 and 61976033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Liaoning Revitalization Talents Program","award":["XLYC1907084"],"award-info":[{"award-number":["XLYC1907084"]}]},{"name":"the Science &amp; Technology Innovation Funds of Dalian","award":["2018J11CY022"],"award-info":[{"award-number":["2018J11CY022"]}]},{"name":"the China Postdoctoral Science Foundation","award":["2016M591421"],"award-info":[{"award-number":["2016M591421"]}]},{"name":"the Fundamental Research Funds for the Central Universities","award":["3132019353, 3132021273 and 3132021274"],"award-info":[{"award-number":["3132019353, 3132021273 and 3132021274"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>The concentration of PM2.5 is an important index to measure the degree of air pollution. When it exceeds the standard value, it is considered to cause pollution and lower the air quality, which is harmful to human health and can cause a variety of diseases, i.e., asthma, chronic bronchitis, etc. Therefore, the prediction of PM2.5 concentration is helpful to reduce its harm. In this paper, a hybrid model called CNN-BiLSTM-Attention is proposed to predict the PM2.5 concentration over the next two days. First, we select the PM2.5 concentration data in hours from January 2013 to February 2017 of Shunyi District, Beijing. The auxiliary data includes air quality data and meteorological data. We use the sliding window method for preprocessing and dividing the corresponding data into a training set, a validation set, and a test set. Second, CNN-BiLSTM-Attention is composed of the convolutional neural network, bidirectional long short-term memory neural network, and attention mechanism. The parameters of this network structure are determined by the minimum error in the training process, including the size of the convolution kernel, activation function, batch size, dropout rate, learning rate, etc. We determine the feature size of the input and output by evaluating the performance of the model, finding out the best output for the next 48 h. Third, in the experimental part, we use the test set to check the performance of the proposed CNN-BiLSTM-Attention on PM2.5 prediction, which is compared by other comparison models, i.e., lasso regression, ridge regression, XGBOOST, SVR, CNN-LSTM, and CNN-BiLSTM. We conduct short-term prediction (48 h) and long-term prediction (72 h, 96 h, 120 h, 144 h), respectively. The results demonstrate that even the predictions of the next 144 h with CNN-BiLSTM-Attention is better than the predictions of the next 48 h with the comparison models in terms of mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2).<\/jats:p>","DOI":"10.3390\/a14070208","type":"journal-article","created":{"date-parts":[[2021,7,13]],"date-time":"2021-07-13T22:25:31Z","timestamp":1626215131000},"page":"208","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":34,"title":["PM2.5 Concentration Prediction Based on CNN-BiLSTM and Attention Mechanism"],"prefix":"10.3390","volume":"14","author":[{"given":"Jinsong","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongtao","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taoying","family":"Li","sequence":"additional","affiliation":[{"name":"School of Maritime Economics and Management, Dalian Maritime University, Dalian 116026, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,7,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"143001","DOI":"10.1016\/j.scitotenv.2020.143001","article-title":"Sources, species and secondary formation of atmospheric aerosols and gaseous precursors in the suburb of Kitakyushu, Japan","volume":"763","author":"Zhang","year":"2021","journal-title":"Sci. Total Environ."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"2655","DOI":"10.1161\/01.CIR.0000128587.30041.C8","article-title":"Air Pollution and Cardiovascular Disease: A Statement for Healthcare Professionals From the Expert Panel on Population and Prevention Science of the American Heart Association","volume":"109","author":"Brook","year":"2004","journal-title":"Circulation"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"128134","DOI":"10.1016\/j.chemosphere.2020.128134","article-title":"Global burden of ischemic heart disease attributable to ambient PM2.5 pollution from 1990 to 2017","volume":"263","author":"Wang","year":"2021","journal-title":"Chemosphere"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"110339","DOI":"10.1016\/j.envres.2020.110339","article-title":"Suspended fine particulate matter (PM2.5), microplastics (MPs), and polycyclic aromatic hydrocarbons (PAHs) in air: Their possible relationships and health implications","volume":"192","author":"Akhbarizadeh","year":"2021","journal-title":"Environ. Res."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.envpol.2017.04.075","article-title":"Air pollution in China: Status and spatiotemporal variations","volume":"227","author":"Song","year":"2017","journal-title":"Environ. Pollut."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Khan, M.R., and Sarkar, B. (2019). Change Point Detection for Diversely Distributed Stochastic Processes Using a Probabilistic Method. Invention, 4.","DOI":"10.3390\/inventions4030042"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Khan, M.R., and Sarkar, B. (2019). Change Point Detection for Airborne Particulate Matter (PM2.5, PM10) by Using the Bayesian Approach. Mathematics, 7.","DOI":"10.3390\/math7050474"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"384","DOI":"10.1016\/j.atmosenv.2016.10.016","article-title":"Arunachalam, S. Multiscale predictions of aviation-attributable PM 2.5 for U.S. airports modeled using CMAQ with plume-in-grid and an aircraft-specific 1-D emission model","volume":"147","author":"Woody","year":"2016","journal-title":"Atmos. Environ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.rse.2015.05.016","article-title":"Estimating long-term PM 2.5 concentrations in China using satellite-based aerosol optical depth and a chemical transport model","volume":"166","author":"Geng","year":"2015","journal-title":"Remote Sens. Environ."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"9046","DOI":"10.1016\/j.eswa.2008.12.017","article-title":"PM 2.5 concentration prediction using hidden semi-Markov model-based times series data mining","volume":"369","author":"Dong","year":"2009","journal-title":"Expert Syst. Appl."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100473","DOI":"10.1016\/j.uclim.2019.100473","article-title":"Forecasting concentrations of air pollutants using support vector regression improved with particle swarm optimization: Case study in Aburr\u00e1 Valley, Colombia","volume":"29","author":"Correa","year":"2019","journal-title":"Urban Clim."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1039\/c3em30890a","article-title":"Predicting submicron air pollution indicators: A machine learning approach","volume":"15","author":"Pandey","year":"2013","journal-title":"Environ. Sci. Process. Impacts"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2554","DOI":"10.1073\/pnas.79.8.2554","article-title":"Neural Networks and Physical Systems with Emergent Collective Computational Abilities","volume":"79","author":"Hopfield","year":"1982","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short-Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"15320","DOI":"10.1021\/acs.est.0c02549","article-title":"Predicting PM2.5 in Well-Mixed Indoor Air for a Large Office Building Using Regression and Artificial Neural Network Models","volume":"54","author":"Lagesse","year":"2020","journal-title":"Environ. Sci. Technol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1016\/j.neunet.2005.06.042","article-title":"Framewise phoneme classification with bidirectional LSTM and other neural network architectures","volume":"18","author":"Graves","year":"2005","journal-title":"Neural Netw."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.neucom.2020.01.006","article-title":"Bidirectional LSTM with self-attention mechanism and multi-channel features for sentiment classification","volume":"387","author":"Li","year":"2020","journal-title":"Neurocomputing"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Rathor, S., and Agrawal, S. (2021). A robust model for domain recognition of acoustic communication using Bidirectional LSTM and deep neural network. Neural Comput. Appl., 1\u201310. in press.","DOI":"10.1007\/s00521-020-05569-0"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"266","DOI":"10.1016\/j.ins.2019.12.054","article-title":"A hybrid multi-resolution multi-objective ensemble model and its application for forecasting of daily PM2.5 concentrations","volume":"516","author":"Liu","year":"2020","journal-title":"Inf. Sci."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"105940","DOI":"10.1016\/j.cmpb.2021.105940","article-title":"Convolutional and recurrent neural networks for the detection of valvular heart diseases in phonocardiogram recordings","volume":"200","author":"Alkhodari","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"949","DOI":"10.1109\/TPAMI.2019.2944806","article-title":"MFQE 2.0: A New Approach for Multi-frame Quality Enhancement on Compressed Video","volume":"43","author":"Guan","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"106912","DOI":"10.1016\/j.asoc.2020.106912","article-title":"CNN-based transfer learning\u2013BiLSTM network: A novel approach for COVID-19 infection detection","volume":"98","author":"Aslan","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"145082","DOI":"10.1016\/j.scitotenv.2021.145082","article-title":"Attention-based parallel network (APNet) for PM2.5 spatiotemporal prediction","volume":"769","author":"Zhu","year":"2021","journal-title":"Sci. Total Environ."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"104600","DOI":"10.1016\/j.envsoft.2019.104600","article-title":"Constructing a PM 2.5 concentration prediction model by combining auto-encoder with Bi-LSTM neural networks","volume":"124","author":"Zhang","year":"2020","journal-title":"Environ. Model. Softw."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"106829","DOI":"10.1016\/j.asoc.2020.106829","article-title":"Interpreting network knowledge with attention mechanism for bearing fault diagnosis","volume":"97","author":"Yang","year":"2020","journal-title":"Appl. Soft Comput."},{"key":"ref_26","unstructured":"Bahdanau, D., Cho, K.H., and Bengio, Y. (2015, January 7\u20139). Neural Machine Translation by Jointly Learning to Align and Translate. Proceedings of the 3rd International Conference on Learning Representations (ICLR2015), San Diego, CA, USA."}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/14\/7\/208\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:29:47Z","timestamp":1760164187000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/14\/7\/208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,13]]},"references-count":26,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021,7]]}},"alternative-id":["a14070208"],"URL":"https:\/\/doi.org\/10.3390\/a14070208","relation":{},"ISSN":["1999-4893"],"issn-type":[{"value":"1999-4893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,13]]}}}