Forecasting Daily of Surface Ozone Concentration in the Grand Casablanca Region Using Parametric and Nonparametric Statistical Models

Halima Oufdou,Lise Bellanger,Amal Bergam,Kenza Khomsi

doi:10.3390/atmos12060666

Abstract

Forecasting concentration levels is important for planning atmospheric protection strategies. In this paper, we focus on the daily average surface ozone (O3) concentration with a short-time resolution (one day ahead) in the Grand Casablanca Region of Morocco. The database includes previous day O3 concentrations measured at Jahid station and various meteorological explanatory variables for 3 years (2013 to 2015). Taking into account the multicollinearity problem in the data, adapted statistical models based on parametric (SPLS and Lasso) and nonparametric (CART, Bagging, and RF) models were built and compared using the coefficient of determination and the root mean square error. We conclude that the parametric models predict better than nonparametric ones. Finally, from the explanatory variables stored by the SPLS and Lasso parametric models, we deduce that a very simple linear regression with five variables remains the most appropriate for the available data at Jahid station (R2 = 0.86 and RMSE = 9.60). This resulting model, with few explanatory variables to prevent missing data, has good predictive quality and is easily implementable. It is the first to be built to predict ozone pollution in the Grand Casablanca region of Morocco.

Highlights

Over the past decades, several studies have been developed, clearly showing the impact of air pollution on human health [1,2], the environment, the natural resources, and the sustainable development of many regions [3]
The purpose of this study is to propose the simplest statistical model for predicting daily O3 from day i to day (i + 1) taking into account the least number of variables to prevent the problem of missing values
The majority of studies performed to forecast daily ozone have used both parametric and nonparametric statistical models in some way to find a significant relationship between meteorological factors, persistence, and O3 concentrations [3]

Summary

Introduction

Several studies have been developed, clearly showing the impact of air pollution on human health [1,2], the environment, the natural resources, and the sustainable development of many regions [3]. Epidemiological studies have shown that current ambient exposures are associated with reduced basic pulmonary function, exacerbation of asthma, and premature mortality [1,9]. To avoid this problem, the prediction of O3 concentrations remains a crucial and necessary step in controlling pollution and in mitigating its adverse effects. The series of chemical reactions before the emission of ozone into the troposphere during the formation process complicates its forecast [10,11]

Objectives

Methods

Results

Conclusion