Prediction of PM2.5 Concentration Based on CNN-BiGRU Model
DOI:
https://doi.org/10.54097/ajst.v5i3.7347Keywords:
PM2.5, CNN, GRU, Combination Model.Abstract
The issue of air pollution has always been a concern. Bad smog weather not only brings inconvenience to people's travel, but also poses a threat to people's health. PM2.5 concentration is an important indicator of air conditions. Therefore, it is of long-term significance to analyze and predict the concentration of PM2.5. Aiming at the problem that a single machine learning model cannot consider the impact of multiple factors on PM2.5 concentration changes, and the data characteristics are complex, which cannot better capture all the characteristics of the data, and cannot highlight the regularity of PM2.5 changes over time, the construction of a combined model further improves the prediction accuracy. Firstly, based on the PM2.5 concentration values, air quality data, and meteorological data at various stations in New Taipei City, Taiwan Province, through analyzing the spatiotemporal distribution characteristics of the PM2.5 concentration at the target station, as well as the correlation with various pollutant factors and meteorological factors, Spearman correlation analysis is used for feature selection. The combined model CNN-BiGRU constructed in this paper utilizes its unique convolution operation to extract features from one-dimensional data, and combines the circular neural network BiGRU with bidirectional transmission function to model and predict PM2.5 concentration based on the functional advantages of both parties.
Downloads
References
Chen Z, Chen D, Zhao C, et al. Influence of meteorological conditions on PM2. 5 concentrations across China: A review of methodology and mechanism[J]. Environment international, 2020, 139: 105558.
Rajagopalan S, Al-Kindi S G, Brook R D. Air pollution and cardiovascular disease: JACC state-of-the-art review[J]. Journal of the American College of Cardiology, 2018, 72(17): 2054-2070.
Hogrefe C, Lynn B, Goldberg R, et al. A combined model–observation approach to estimate historic gridded fields of PM2. 5 mass and species concentrations[J]. Atmospheric Environment, 2009, 43(16): 2561-2570.
Zhang Y, Pun B, Wu S Y, et al. Application and evaluation of two air quality models for particulate matter for a southeastern US episode[J]. Journal of the Air & Waste Management Association, 2004, 54(12): 1478-1493.
Chuang M T, Fu J S, Jang C J, et al. Simulation of long-range transport aerosols from the Asian Continent to Taiwan by a Southward Asian high-pressure system[J]. Science of the total environment, 2008, 406(1-2): 168-179.
San José R, Pérez J L, Morant J L, et al. Improved modelling experiment for elevated PM10 and PM2. 5 concentrations in Europe with MM5-CMAQ and WRF/CHEM[J]. Air Pollution, 2009: 377-86.
Lee D G. Comparison between Atmospheric Chemistry Model and Observations Utilizing the RAQMS-CMAQ Linkage, Part II: Impact on PM2. 5 Mass Concentrations Simulated[J]. Asian Journal of Atmospheric Environment, 2014, 8(2): 108-114.
Jiang X, Yoo E. The importance of spatial resolutions of Community Multiscale Air Quality (CMAQ) models on health impact assessment[J]. Science of the Total Environment, 2018, 627: 1528-1543.
Wang W, Wu T,Zhang Z. PM2. 5 prediction of Hangzhou based on ARIMA model [J]. Journal of Natural Sciences, Harbin Normal University, 2018, 34(3): 49-55.
Wang J. Prediction of PM2. 5 based on multiple regression analysis [J]. Microcomputer application, 2020, 3.
Wang J,Cao C. PM_(2.5) prediction of Beijing based on Bayesian hierarchical autoregressive spatio-temporal model [J]. Journal of Nanjing University of Information Science & Technology (Natural Science),2023,15(01):34-41.
Masood A, Ahmad K. A model for particulate matter (PM2. 5) prediction for Delhi based on machine learning approaches[J]. Procedia Computer Science, 2020, 167: 2101-2110.
Chen G, Li S, Knibbs L D, et al. A machine learning method to estimate PM2. 5 concentrations across China with remote sensing, meteorological and land use information[J]. Science of the Total Environment, 2018, 636: 52-60.
Zamani Joharestani M, Cao C, Ni X, et al. PM2. 5 prediction based on random forest, XGBoost, and deep learning using multisource remote sensing data[J]. Atmosphere, 2019, 10(7): 373.
Liang Y,Li Z,Jin Y, et al . Comparison of PM_(2.5) prediction effect in Beijing based on tree model [J]. Environmental engineering:1-13[2023-03-13].
Kong Y,Wang H,Zhang H,et al. PM2.5 concentration prediction based on integrated learning algorithm [J]. Environmental protection science,2021,47(4):17-23.I
Ding C, Wang G, Zhang X, et al. A hybrid CNN-LSTM model for predicting PM2. 5 in Beijing based on spatiotemporal correlation[J]. Environmental and Ecological Statistics, 2021, 28(3): 503-522.
Di Q, Amini H, Shi L, et al. An ensemble-based model of PM2. 5 concentration across the contiguous United States with high spatiotemporal resolution[J]. Environment international, 2019, 130: 104909.
Niu M, Wang Y, Sun S, et al. A novel hybrid decomposition-and-ensemble model based on CEEMD and GWO for short-term PM2. 5 concentration forecasting[J]. Atmospheric Environment, 2016, 134: 168-180.
Zhou F,Jin L,Dong J. Review of Convolutional Neural Network [J]. Journal of Computer Science,2017,40(6):1229-1251.
Liang R, Chang X, Jia P, et al. Mine gas concentration forecasting model based on an optimized BiGRU network[J]. ACS omega, 2020, 5(44): 28579-28586.
Zhang B, Jia M, Xu J, et al. Network Security Situation Prediction Model Based on EMD and ELPSO Optimized BiGRU Neural Network[J]. Computational Intelligence and Neuroscience, 2022, 2022.
Zhang H, Wang Y, Hu J, et al. Relationships between meteorological parameters and criteria air pollutants in three megacities in China[J]. Environmental research, 2015, 140: 242-254.
Rojas N, Galvis B. Relationship between PM2. 5 and PM10 in Bogotá[J]. Revista de Ingeniería, 2005 (22): 54-60.
Liu D, Cho S Y, Sun D, et al. A Spearman correlation coefficient ranking for matching-score fusion on speaker recognition[C]. in TENCON 2010-2010 IEEE Region 10 Conference. IEEE, 2010: 736-741.