Abstract
This paper aims to model the daily evolution for particulate matter concentrations of less than 1 μm (PM1), 2.5 μm (PM2.5), 4 μm (PM4), 10 μm (PM10), and PM-Total, based on weather factors (WF), by using the hybrid dragonfly-SVMr algorithm. Hourly data on atmospheric concentrations of PMi and WF were recorded simultaneously at an automatic air quality check station located at an urban site in Algiers, using the fine dust measurement device, Fidas® 200. The number of data collected on PM was 540 measurements. In this study, the meta-heuristic dragonfly algorithm (DA) was used in order to select the optimal hyper-parameters of the Support Vector Machine model. For this, a MATLAB® program based on the dragonfly optimization algorithm coupled with the SVM regression algorithm has been written in order to correlate for the PMi concentrations. The obtained results show that the established model has good predictive performance, with a coefficient of determination R2 = 0.98 and root of the mean square error RMSE = 1.9261.
Similar content being viewed by others
Data availability
We used the FIDAS200 sensor from the Renewable Energy Research Center (CDER) to measure the concentrations of PM1, PM2.5, PM4, PM10, PM-Totals, as well as temperature and relative humidity. In addition, we obtained the wind speed and cumulative precipitation data from the National Meteorological Office (NMO) to create the database.
References
Amroune M, Bouktir T, Musirin I (2018) Power system voltage stability assessment using a hybrid approach combining dragonfly optimization algorithm and support vector regression. Arab J Sci Eng 43:3023–3036
Bai Y, Li Y, Wang X, Xie J, Li C (2016) Air pollutants concentrations forecasting using back propagation neural network based on wavelet decomposition with meteorological conditions. Atmos Pollut Res 7:557–566
Benimam H, Si-Moussa C, Laidi M, Hanini S (2020a) Modeling the activity coefficient at infinite dilution of water in ionic liquids using artificial neural networks and support vector machines. Neural Comput & Applic 32:8635–8653
Benimam H, Si-Moussa C, Hentabli M, Hanini S, Laidi M (2020b) Dragonfly-support vector machine for regression modeling of the activity coefficient at infinite dilution of solutes in imidazolium ionic liquids using σ-profile descriptors. J Chem Eng Data 65:3161–3172
Brokamp C, Jandarov R, Hossain M, Ryan P (2018) Predicting daily urban fine particulate matter concentrations using a random forest model. Environ Sci Technol 52:4173–4179
Çaydaş U, Hasçalık A, Ekici S (2009) An adaptive neuro-fuzzy inference system (ANFIS) model for wire-EDM. Expert Syst Appl 36:6135–6139
Elbayoumi M, Ramli NA, Md Yusof NFF, Yahaya ASB, Al Madhoun W, Ul-Saufie AZ (2014) Multivariate methods for indoor PM10 and PM2.5 modelling in naturally ventilated schools buildings. Atmos Environ 94:11–21
Fan G-F, Peng L-L, Hong W-C, Sun F (2016) Electric load forecasting by the SVR model with differential empirical mode decomposition and auto regression. Neurocomputing 173:958–970
Gan K, Sun S, Wang S, Wei Y (2018) A secondary-decomposition-ensemble learning paradigm for forecasting PM2.5 concentration. Atmos Pollut Res 9:989–999
Geoba (Offers facts, statistics and information about any city or place worldwide) (2019) http://www.geoba.se/. Accessed in 2019
He Z, Wen X, Liu H, Du J (2014) A comparative study of artificial neural network, adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semiarid mountain region. J Hydrol 509:379–386
Heal MR, Kumar P, Harrison RM (2012) Particles, air quality, policy and health. Chem Soc Rev 41:6606–6630
Hong W-C (2011) Electric load forecasting by seasonal recurrent SVR (support vector regression) with chaotic artificial bee colony algorithm. Energy 36:5568–5578
Hong W-C, Fan G-F (2019) Hybrid empirical mode decomposition with support vector regression model for short term load forecasting. Energies 12:1093
Hong W-C, Dong Y, Zheng F, Lai C-Y (2011) Forecasting urban traffic flow by SVR with continuous ACO. Appl Math Model 35:1282–1291
Hong W-C, Dong Y, Zhang WY, Chen L-Y, Panigrahi KB (2013) Cyclic electric load forecasting by seasonal SVR with chaotic genetic algorithm. Int J Electr Power Energy Syst 44:604–614
Izhar S, Goel A, Chakraborty A, Gupta T (2016) Annual trends in occurrence of submicron particles in ambient air and health risk posed by particle bound metals. Chemosphere 146:582–590
Jovašević-Stojanović M, Bartonova A, Topalović D, Lazović I, Pokrić B, Ristovski Z (2015) On the use of small and cheaper sensors and devices for indicative citizen-based monitoring of respirable particulate matter. Environ Pollut 206:696–704
Keskes S, Hanini S, Hentabli M, Laidi M (2020) Artificial intelligence and mathematical modelling of the drying kinetics of pharmaceutical powders. Kemija u Industriji 69:137–152
Kurt A, Oktay AB (2010) Forecasting air pollutant indicator levels with geographic models 3 days in advance using neural networks. Expert Syst Appl 37:7986–7992
Li X, Zhang X (2019) Predicting ground-level PM2.5 concentrations in the Beijing-Tianjin-Hebei region: a hybrid remote sensing and machine learning approach. Environ Pollut 249:735–749
Li X, Li L, Zhang B, Guo Q (2013) Hybrid self-adaptive learning based particle swarm optimization and support vector regression model for grade estimation. Neurocomputing 118:179–190
Li R, Mao H, Wu L, He J, Ren P, Li X (2016) The evaluation of emission control to PM concentration during Beijing APEC in 2014. Atmos Pollut Res 7:363–369
Li M-W, Geng J, Hong W-C, Zhang L-D (2019a) Periodogram estimation based on LSSVR-CCPSO compensation for forecasting ship motion. Nonlinear Dyn 97:2579–2594
Li N, Han W, Wei X, Shen M, Sun S (2019b) Chemical characteristics and human health assessment of PM1 during the Chinese Spring Festival in Changchun, Northeast China. Atmos Pollut Res 10:1823–1831
Li Z, Xie Y, Li X, Zhao W (2019c) Prediction and application of porosity based on support vector regression model optimized by adaptive dragonfly algorithm. Energy Sources A 1–14
Lin G-F, Lin H-Y, Wu M-C (2012) Development of a support-vector-machine-based model for daily pan evaporation estimation. Hydrol Process 27:3115–3127
Liu H, Dong S (2020) A novel hybrid ensemble model for hourly PM2.5 forecasting using multiple neural networks: a case study in China. Air Qual Atmos Health
Liu T, Wu MP, Zhang KD, Liu Y, Zhong J (2014) Correlation analysis and control scheme research on PM2.5. Appl Mech Mater 590:888–894
Liu H, Zheng J, Qu C, Zhang J, Wang Y, Zhan C, Yao R, Cao J (2017) Characteristics and source analysis of water-soluble inorganic ions in PM10 in a typical mining city, Central China. Atmosphere 8:74
Mafarja M, Heidari AA, Faris H, Mirjalili S, Aljarah I (2020) Dragonfly Algorithm: theory, literature review, and application in feature selection. In: Mirjalili S, Song Dong J, Lewis A (eds) Nature-Inspired Optimizers. Studies in Computational Intelligence. Springer, Cham, pp 47–67
MEER (Ministry of the Environment and Renewable Energies) (2019) http://www.meer.gov.dz/a/?page_id = 173/. Accessed in 2019
Mehdipour V, Stevenson DS, Memarianfard M, Sihag P (2018) Comparing different methods for statistical modeling of particulate matter in Tehran, Iran. Air Qual Atmos Health 11:1155–1165
Min J, Lee Y (2005) Bankruptcy prediction using support vector machine with optimal choice of kernel function parameters. Expert Syst Appl 28:603–614
Mirjalili S (2016) Dragonfly algorithm: a new meta-heuristic optimization technique for solving single-objective, discrete, and multi-objective problems. Neural Comput & Applic 27:1053–1073
Niu M, Wang Y, Sun S, Li Y (2016) A novel hybrid decomposition-and-ensemble model based on CEEMD and GWO for short-term PM2.5 concentration forecasting. Atmos Environ 134:168–180
ONM (National Meteorological Office) (2019) https://www.meteo.dz/historique.php/. Accessed in 2019
Palas (Fine dust measurement device Fidas® 200) (2020) https://www.palas.de/en/product/fidas200s. Accessed in 2020
Pio C, Cerqueira M, Harrison RM, Nunes T, Mirante F, Alves C, Oliveira C, Sanchez de la Campa A, Artíñano B, Matos M (2011) OC/EC ratio observations in Europe: re-thinking the approach for apportionment between primary and secondary organic carbon. Atmos Environ 45:6121–6132
Qi C, Zhou W, Lu X, Luo H, Pham BT, Yaseen ZM (2020) Particulate matter concentration from open-cut coal mines: a hybrid machine learning estimation. Environ Pollut 263:114517
Racherla PN, Adams PJ (2006) Sensitivity of global tropospheric ozone and fine particulate matter concentrations to climate change. J Geophys Res 111:1–11
Ranjini SKS, Murugan S (2017) Memory based hybrid dragonfly algorithm for numerical optimization problems. Expert Syst Appl 83:63–78
Sarti E, Pasti L, Scaroni I, Casali P, Cavazzini A, Rossi M (2017) Determination of n-alkanes, PAHs and nitro-PAHs in PM2.5 and PM1 sampled in the surroundings of a municipal waste incinerator. Atmos Environ 149:12–23
Sayed GI, Tharwat A, Hassanien AE (2019) Chaotic dragonfly algorithm: an improved metaheuristic algorithm for feature selection. Appl Intell 49:188–205
Scholkopf B, Smola AJ (2001) Learning with kernels: support vector machines, regularization, optimization, and beyond. The MIT Press, Cambridge
Shen GF, Yuan SY, Xie YN, Xia SJ, Li L, Yao YK, Qiao YZ, Zhang J, Zhao QY, Ding AJ, Li B, Wu HS (2014) Ambient levels and temporal variations of PM 2.5 and PM 10 at a residential site in the mega-city, Nanjing, in the western Yangtze River Delta, China. J Environ Sci Health A 49:171–178
Sun W, Sun J (2017) Daily PM 2.5 concentration prediction based on principal component analysis and LSSVM optimized by cuckoo search algorithm. J Environ Manag 188:144–152
Suresh V, Sreejith S (2017) Generation dispatch of combined solar thermal systems using dragonfly algorithm. Computing 99:59–80
Suykens JAK, Vandewalle J (1998) Nonlinear Modeling. Springer, US
Talbi A, Kerchich Y, Kerbachi R, Boughedaoui M (2018) Assessment of annual air pollution levels with PM1, PM2.5, PM10 and associated heavy metals in Algiers, Algeria. Environ Pollut 232:252–263
Tang Z, Chai M, Cheng J, Jin J, Yang Y, Nie Z, Huang Q, Li Y (2017) Contamination and health risks of heavy metals in street dust from a coal-mining city in eastern China. Ecotoxicol Environ Saf 138:83–91
Tao Y, Yan H, Gao H, Sun Y, Li G (2019) Application of SVR optimized by modified simulated annealing (MSA-SVR) air conditioning load prediction model. J Ind Inf Integr 15:247–251
Tharwat A, Gabel T, Hassanien A E (2018) Parameter optimization of support vector machine using dragonfly algorithm. Proceedings of the 3rd International Conference on Advanced Intelligent Systems and Informatics, September 9-11, 2017, Cairo, Egypt, pp 309–319
Tsai P-J, Young L-H, Hwang B-F, Lin M-Y, Chen Y-C, Hsu H-T (2020) Source and health risk apportionment for PM2.5 collected in Sha-Lu area, Taiwan. Atmos Pollut Res 11:851–858
Vapnik VN (1995) The Nature of Statistical Learning Theory. Springer, New York
Vapnik VN (1998) Statistical learning theory. Wiley, New York
Ventura LMB, de Oliveira Pinto F, Soares LM, Luna AS, Gioda A (2019) Forecast of daily PM2.5 concentrations applying artificial neural networks and Holt–Winters models. Air Qual Atmos Health 12:317–325
Wang W, Ren L, Zhang Y, Chen J, Liu H, Bao L, Fan S, Tang D (2008) Aircraft measurements of gaseous pollutants and particulate matter over Pearl River Delta in China. Atmos Environ 42:6187–6202
Zhang Z, Hong W-C (2019) Electric load forecasting by complete ensemble empirical mode decomposition adaptive noise and support vector regression with quantum-based dragonfly algorithm. Nonlinear Dyn 98:1107–1136
Zhang X, Wang P, Liang D, Fan C, Li C (2015) A soft self-repairing for FBG sensor network in SHM system based on PSO–SVR model reconstruction. Opt Commun 343:38–46
Zhang L, Lin J, Qiu R, Hu X, Zhang H, Chen Q, Tan H, Lin D, Wang J (2018) Trend analysis and forecast of PM2.5 in Fuzhou, China using the ARIMA model. Ecol Indic 95:702–710
Zhang A, Zhang P, Feng Y (2019a) Short-term load forecasting for microgrids based on DA-SVM. COMPEL Int J Comput Math Electr Electron Eng 38:68–80
Zhang Z, Ding S, Jia W (2019b) A hybrid optimization algorithm based on cuckoo search and differential evolution for solving constrained engineering problems. Eng Appl Artif Intell 85:254–268
Zhang Z, Ding S, Sun Y (2020) A support vector regression model hybridized with chaotic krill herd algorithm and empirical mode decomposition for regression task. Neurocomputing 410:185–201
Zheng Z, Xu G, Li Q, Chen C, Li J (2019) Effect of precipitation on reducing atmospheric pollutant over Beijing. Atmos Pollut Res 10:1443–1453
Zhu S, Lian X, Wei L, Che J, Shen X, Yang L, Qiu X, Liu X, Gao W, Ren X, Li J (2018) PM2.5 forecasting using SVR with PSOGSA algorithm based on CEEMD, GRNN and GCA considering meteorological factors. Atmos Environ 183:20–32
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflicts of interest
The authors declare that they have no conflict of interest.
Code availability
We used the MATLAB software for modeling fine particulate matter (PM) concentrations through our dragonfly code coupled with Support Vector Machine (DA-SVM).
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
ESM 1
(DOCX 2354 kb)
Rights and permissions
About this article
Cite this article
Ibrir, A., Kerchich, Y., Hadidi, N. et al. Prediction of the concentrations of PM1, PM2.5, PM4, and PM10 by using the hybrid dragonfly-SVM algorithm. Air Qual Atmos Health 14, 313–323 (2021). https://doi.org/10.1007/s11869-020-00936-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11869-020-00936-1