Analysis and prediction of $$\mathrm{PM}_{10}$$ concentration levels in Tunisia using statistical learning approaches

Over the past years, the health impact of airborne particulate matter \(\mathrm{PM}_{10}\) has become a very topical subject. Thereby, a lot of research effort in the environmental sciences goes towards the modeling and the prediction of ambient \(\mathrm{PM}_{10}\) concentrations. In this paper, we are interested in the statistical classification of the daily mean \(\mathrm{PM}_{10}\) concentration in Tunisia according to the authority regulation. We consider two monitoring stations: a big industrial station and a traffic station. The main goal of this work is to determine the pertinent predictors of \(\mathrm{PM}_{10}\) concentration within a nonlinear multiclass framework. To do this, we used two popular statistical learning methods; the support vector machines (SVM) and the random forests (RF). The statistical results obtained on the real datasets, show that RF outperform SVM for the purpose of variable selection even with a reduced number of observations compared to the number of explicative variables. It was also demonstrated that the \(\mathrm{PM}_{10}\) concentration measured yesterday is the most relevant predictor of its present-day value. Moreover, we found that the more delayed values of \(\mathrm{PM}_{10}\) concentration may be crucial to get an accurate prediction.     

Analysis of daily and seasonal variation of fine particulate matter (PM2.5) for five cities of China

Environment, Development and Sustainability - Monitoring of air quality is demanding, especially in poor air quality regions. China has been suffering from PM2.5 pollution associated with the fast...     

Does ‘Manna from Heaven’ help? The role of cash transfers in disaster recovery—lessons from Fiji after Tropical Cyclone Winston

This paper contributes to the evidence on the effectiveness of shock-responsive social protection systems in helping affected households recover from the negative consequences of disasters. It evaluates the influence of the top-up cash transfers provided by the Government of Fiji to poor households in the wake of Tropical Cyclone Winston, which struck the Pacific Island country on 20 February 2016. The impact evaluation strategy incorporates a sharp regression discontinuity design to define treatment and control groups, based on the eligibility threshold of the poverty benefit scheme. The results indicate that treatment households—that is, those that received cash transfers—are significantly more likely to report quicker recovery from various shocks. Female-headed households are more likely to recover from the ramifications, whereas households with older heads are less likely to do so. The presence of a functioning market appears to be a major factor aiding the speed of recovery. Finally, the evidence points towards strong district effects on recovery.