Dataset Information

Comparing Methods to Impute Missing Daily Ground-Level PM10 Concentrations between 2010-2017 in South Africa.

ABSTRACT: Good quality and completeness of ambient air quality monitoring data is central in supporting actions towards mitigating the impact of ambient air pollution. In South Africa, however, availability of continuous ground-level air pollution monitoring data is scarce and incomplete. To address this issue, we developed and compared different modeling approaches to impute missing daily average particulate matter (PM10) data between 2010 and 2017 using spatiotemporal predictor variables. The random forest (RF) machine learning method was used to explore the relationship between average daily PM10 concentrations and spatiotemporal predictors like meteorological, land use and source-related variables. National (8 models), provincial (32) and site-specific (44) RF models were developed to impute missing daily PM10 data. The annual national, provincial and site-specific RF cross-validation (CV) models explained on average 78%, 70% and 55% of ground-level PM10 concentrations, respectively. The spatial components of the national and provincial CV RF models explained on average 22% and 48%, while the temporal components of the national, provincial and site-specific CV RF models explained on average 78%, 68% and 57% of ground-level PM10 concentrations, respectively. This study demonstrates a feasible approach based on RF to impute missing measurement data in areas where data collection is sparse and incomplete.

SUBMITTER: Arowosegbe OO

PROVIDER: S-EPMC8037804 | biostudies-literature | 2021 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparing Methods to Impute Missing Daily Ground-Level PM<sub>10</sub> Concentrations between 2010-2017 in South Africa.

Arowosegbe Oluwaseyi Olalekan OO Röösli Martin M Künzli Nino N Saucy Apolline A Adebayo-Ojo Temitope Christina TC Jeebhay Mohamed F MF Dalvie Mohammed Aqiel MA de Hoogh Kees K

International journal of environmental research and public health 20210324 7

Good quality and completeness of ambient air quality monitoring data is central in supporting actions towards mitigating the impact of ambient air pollution. In South Africa, however, availability of continuous ground-level air pollution monitoring data is scarce and incomplete. To address this issue, we developed and compared different modeling approaches to impute missing daily average particulate matter (PM<sub>10</sub>) data between 2010 and 2017 using spatiotemporal predictor variables. The ...[more]

PMID: 33805155

Similar Datasets

Project description:BackgroundMultiple studies have reported a high burden of hypertension in sub-Saharan Africa, but none have examined early stage hypertension. We examined contemporary prevalence of diagnosed, treated, and controlled stage I (130-139/80-89 mm Hg) and II (≥140/90 mm Hg) hypertension in the general population of sub-Saharan Africa.MethodsWe analyzed World Health Organization STEPwise Approach to Noncommunicable Disease Risk Factor Surveillance surveys from 17 sub-Saharan Africa countries including 85 371 respondents representing 85 million individuals from 2010 to 2017. We extracted demographic variables, blood pressure, self-reported hypertension diagnosis/awareness, and treatment status to estimate prevalence of stage I and II hypertension and treatment by country. We examined diagnosis and treatment trends by national sociodemographic index, a marker of development.ResultsStage I hypertension prevalence (regardless of diagnosis/treatment) was >25% in 13 of 17 countries, highest in Sudan (35.3% [95% CI, 33.7%-37.0%]), and lowest in Eritrea (20.2% [18.8%-21.6%]). Combined stages I and II hypertension prevalence was >50% in 13 countries; <20% were diagnosed in every country. Treatment among those diagnosed ranged from 26% to 63%, and control (<140/90 mm Hg) from 4% to 17%. In 8 of 9 countries reporting on behavioral interventions (eg, salt reduction, weight loss, exercise, and smoking cessation), <60% of diagnosed individuals received counseling. Rates of diagnosis, but not treatment, were positively associated with sociodemographic index (P=0.008), although there was substantial variation between countries even at similar levels of development.ConclusionsHypertension is common in sub-Saharan Africa but rates of diagnosis, treatment, and control markedly low. There is a large population with early stage hypertension that may benefit from behavioral counseling to prevent progression. Our analyses suggest that success in population hypertension care may be achieved independently of socioeconomic development, highlighting a need for policymakers to identify best practices in those countries that outperform similar or more developed countries.

Dataset Information

Comparing Methods to Impute Missing Daily Ground-Level PM10 Concentrations between 2010-2017 in South Africa.

Publications

Comparing Methods to Impute Missing Daily Ground-Level PM<sub>10</sub> Concentrations between 2010-2017 in South Africa.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets