Intelligent forecaster of concentrations (PM2.5, PM10, NO2, CO, O3, SO2) caused air pollution (IFCsAP)

Unveiling air pollution patterns in Yemen: a spatial–temporal functional data analysis

“…King et al ( 2018 ) used both B-spline and restricted maximum likelihood (REML) techniques to transform and smooth the PM2.5 data, while Acal et al ( 2022 ) only used B-spline smoothing. In contrast, recent studies have also analyzed PM2.5 pollutant data without any transformation or smoothing, such as Al-Janabi et al ( 2021 ) and Wang et al ( 2022 ).…”

“…However, this pollutant has received some traditional research. Al-Janabi et al ( 2021 ) and Li et al ( 2022d ) currently studied the CO pollutant using different analysis methods in a recent study. As a result, the current study differs from their study in that the data was processed in a discontinuous/discretization form without any transformation or smoothing.…”

“…However, a few studies have analyzed SO 2 pollutant data using vectorized-based methods. For example, the study conducted by Al-Janabi et al ( 2021 ) employed the intelligent prediction method called IFCsAP to handle SO 2 pollutant data along with other pollutant variables. Another study by Kujawska et al ( 2022 ) used an artificial neural network model to forecast sulfur dioxide levels in the air.…”

“…Functional data analysis (FDA) is a powerful technique for working with multi-dimensional air pollutants data. It utilizes additional information, such as the smoothness of the data structure, rate of change, acceleration, and dynamic changes over a large-scale domain, to extract more information from the data compared to traditional vectorial approaches (King et al 2018 ; Al-Janabi et al 2021 ; Reinholdt Jensen et al 2022 ). FDA has been well-established in the literature over the past two decades, with a strong methodological and operational framework.…”

Assessment of urban air quality from Twitter communication using self-attention network and a multilayer classification model

“…However, recent approaches using machine learning (ML) techniques have been found promising for the purpose (Mohammadifar et al 2021 ; Gurajala and Matthews 2018 ; Jackoway et al 2011 ;). Many ML techniques are exploited curiously by new researchers are air quality prediction and forecasting (Xu et al 2020 ; Chang et al, 2020 ; Zhang et al 2021 ; Al-Janabi et al 2020 , 2021 ).…”