Prediction of the concentrations of PM1, PM2.5, PM4, and PM10 by using the hybrid dragonfly-SVM algorithm
- PDF / 1,134,550 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 20 Downloads / 204 Views
Prediction of the concentrations of PM1, PM2.5, PM4, and PM10 by using the hybrid dragonfly-SVM algorithm Abdellah Ibrir 1
&
Yacine Kerchich 2 & Noureddine Hadidi 1 & Hamza Merabet 3 & Mohamed Hentabli 4,5
Received: 6 August 2020 / Accepted: 1 September 2020 # Springer Nature B.V. 2020
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. Keywords Particulate matter . Urban site . Support Vector Machine . Dragonfly . Pollution . Air
Introduction Fine particulate matter (PM) with diameters 1 μm (PM1), 2.5 μm (PM2.5), 4 μm (PM4), and 10 μm (PM10) represents a significant fraction in the tropospheric layer (Wang et al. 2008). Their concentrations in the atmosphere can increase or decrease rapidly depending on the ambient conditions
Electronic supplementary material The online version of this article (https://doi.org/10.1007/s11869-020-00936-1) contains supplementary material, which is available to authorized users. * Abdellah Ibrir [email protected] 1
Materials and Environment Laboratory (LME), Faculty of Technology, Yahia Fares University, 26000 Medea, Algeria
2
Environmental Sciences and Techniques Laboratory, National Polytechnic School (ENP), 16200 El Harrach, Algeria
3
Centre de Développement des Energies Renouvelables, CDER, BP 62, Route de l’Observatoire, Bouzaréah 16340, Algiers, Algeria
4
Biomaterials and Transport Phenomena Laboratory (LBMPT), Faculty of Technology, Yahia Fares University, 26000 Medea, Algeria
5
Quality Control Laboratory, SAIDAL Complex of Medea, 26000 Medea, Algeria
(Jovašević-Stojanović et al. 2015; Racherla and Adams 2006; Zheng et al. 2019) such as rainfall, wind speed, relative humidity, and temperature (Talbi et al. 2018; Li et al. 2019b). Studies have shown that these PMs may contain, depending on their emission source, very toxic species, like heavy metals, organic compounds from combustion processes, secondary particles due to gas-particle conversion, and mineral elements linked to soil erosion and re-suspension of dust (Hongxia Liu et al. 2017; Pio et al. 2011; Sarti et al. 2017; Shen et
Data Loading...
