ABSTRACT
There is a paucity of air quality data in sub-Saharan African countries to inform science driven air quality management and epidemiological studies. We investigated the use of available remote-sensing aerosol optical depth (AOD) data to develop spatially and temporally resolved models to predict daily particulate matter (PM10) concentrations across four provinces of South Africa (Gauteng, Mpumalanga, KwaZulu-Natal and Western Cape) for the year 2016 in a two-staged approach. In stage 1, a Random Forest (RF) model was used to impute Multiangle Implementation of Atmospheric Correction AOD data for days where it was missing. In stage 2, the machine learner algorithms RF, Gradient Boosting and Support Vector Regression were used to model the relationship between ground-monitored PM10 data, AOD and other spatial and temporal predictors. These were subsequently combined in an ensemble model to predict daily PM10 concentrations at 1 km × 1 km spatial resolution across the four provinces. An out-of-bag R2 of 0.96 was achieved for the first stage model. The stage 2 cross-validated (CV) ensemble model captured 0.84 variability in ground-monitored PM10 with a spatial CV R2 of 0.48 and temporal CV R2 of 0.80. The stage 2 model indicated an optimal performance of the daily predictions when aggregated to monthly and annual means. Our results suggest that a combination of remote sensing data, chemical transport model estimates and other spatiotemporal predictors has the potential to improve air quality exposure data in South Africa's major industrial provinces. In particular, the use of a combined ensemble approach was found to be useful for this area with limited availability of air pollution ground monitoring data.
Subject(s)
Air Pollutants , Air Pollution , Aerosols , Environmental Monitoring , Particulate Matter , Remote Sensing Technology , South AfricaABSTRACT
The north-eastern parts of South Africa, comprising the Limpopo Province, have recorded a sudden rise in the rate of malaria morbidity and mortality in the 2017 malaria season. The epidemiological profiles of malaria, as well as other vector-borne diseases, are strongly associated with climate and environmental conditions. A retrospective understanding of the relationship between climate and the occurrence of malaria may provide insight into the dynamics of the disease's transmission and its persistence in the north-eastern region. In this paper, the association between climatic variables and the occurrence of malaria was studied in the Mutale local municipality in South Africa over a period of 19-year. Time series analysis was conducted on monthly climatic variables and monthly malaria cases in the Mutale municipality for the period of 1998-2017. Spearman correlation analysis was performed and the Seasonal Autoregressive Integrated Moving Average (SARIMA) model was developed. Microsoft Excel was used for data cleaning, and statistical software R was used to analyse the data and develop the model. Results show that both climatic variables' and malaria cases' time series exhibited seasonal patterns, showing a number of peaks and fluctuations. Spearman correlation analysis indicated that monthly total rainfall, mean minimum temperature, mean maximum temperature, mean average temperature, and mean relative humidity were significantly and positively correlated with monthly malaria cases in the study area. Regression analysis showed that monthly total rainfall and monthly mean minimum temperature (R² = 0.65), at a two-month lagged effect, are the most significant climatic predictors of malaria transmission in Mutale local municipality. A SARIMA (2,1,2) (1,1,1) model fitted with only malaria cases has a prediction performance of about 51%, and the SARIMAX (2,1,2) (1,1,1) model with climatic variables as exogenous factors has a prediction performance of about 72% in malaria cases. The model gives a close comparison between the predicted and observed number of malaria cases, hence indicating that the model provides an acceptable fit to predict the number of malaria cases in the municipality. To sum up, the association between the climatic variables and malaria cases provides clues to better understand the dynamics of malaria transmission. The lagged effect detected in this study can help in adequate planning for malaria intervention.
