Vehicle-induced air pollution is an important issue in the 21st century, posing detrimental effects on human health. Prediction of vehicle-emitted air pollutants and evaluation of the diverse factors that contribute to them are of the utmost importance. This study employed advanced tree-based machine learning models to predict vehicle-induced air pollutant levels, with a particular focus on fine particulate matter (PM2.5). In addition to a benchmark statistical model, the models employed were Gradient Boosting (GB), Light Gradient Boosting Machine (LGBM), Extreme Gradient Boosting (XGBoost), Extra Tree (ET), and Random Forest (RF). Regarding the evaluation of PM2.5 predictions, the ET model outperformed the others, as shown by MAE of 1.69, MSE of 5.91, RMSE of 2.43, and R2 of 0.71. Afterward, the optimal ET models were interpreted using SHAP analysis to overcome the ET model's lack of explainability. Based on the SHAP analysis, it was determined that temperature, humidity, and wind speed emerged as the primary determinants in forecasting PM2.5 levels.

This research employed machine learning approaches to classify acceptable or non-acceptable particulate matter (PM_2.5) concentrations using a dataset that was obtained from the Nairobi expressway road corridor. The dataset contained air quality data, traffic volume, and meteorological data. The Boruta Algorithm (BA) was utilized in conjunction with the Random Forests (RF) classifier to select the most appropriate features from the dataset. The findings of the BA analysis indicated that humidity was the most influential factor in determining air quality. This was closely followed by the variables of ‘day_of_week’ and the volume of traffic bound for Nairobi. The temperature of the site was determined to have a lower significance. The comparison among different machine learning classifiers for the classification of acceptable and unacceptable PM_2.5 concentrations revealed that the Extreme Gradient Boosting (XGBoost) classifier displayed superior performance in terms of Sensitivity (0.774), Specificity (0.943), F1-Score (0.833), and AU-ROC (0.874). The Binary Logistic Regression (BLR) model demonstrated comparatively poorer performance in terms of Sensitivity (0.244), Specificity (0.614), F1-Score (0.455), and AU-ROC (0.508) when compared to other ML models. The prediction of PM_2.5 has the potential to provide valuable insights to transport policymakers in their deliberations on urban transport policy formulation.

Vernonia oil obtained by Soxhlet extraction from the seeds of Vernonia galamensis ssp. nairobensis was reacted with 2-aminopyridine, 2-(aminomethyl)pyridine and 2-(aminoethyl)pyridine using a 1:3 mole ratio of vernonia oil to amine at varied temperatures to give the corresponding vernolamides. The expected vernolamide from the reaction of 2-aminopyridine and the oil was not formed. N-(2-pyridinylmethyl)vernolamide and N-(2-pyridinylethyl)vernolamide exhibited antibacterial activity that was shown to be higher against gram-positive (Bacillus subtilis) than gram-negative (Escherichia coli) bacteria. The vernolamides did not show any antifungal activity. KEY WORDS: Vernonia galamensis, 2-Aminopyridine, N-(2-pyridinylmethyl)vernolamide, N-(2-pyridinylethyl)vernolamide, Antimicrobial activity Bull. Chem. Soc. Ethiop. 2007, 21(1), 103-110.

This study was done to assess the physical-chemical properties of some boreholes in Pangani, Dandora and Kayole in Nairobi County, to assess the content of some heavy metals in some boreholes in Pangani, Dandora and Kayole and to determine the bacteriological quality of the water. These were checked for compliance as per the World Health Organization’s guideline values. Borehole water samples were collected from Dandora, Kayole and Pangani. Water parameters determined included electrical conductivity, total suspended solids, total dissolved solids, pH, fluoride, chloride, ammonia, nitrate, Escherichia-coli, total count and analysis of some selected heavy metal ions. The measurements of pH, fluoride, and electrical conductivity were made by an ion-selective electrode. The determinations of total dissolved solids and total suspended solids were made by the gravimetric method. The titration method was used to quantify chloride, while ultraviolet-visible spectrophotometer was used to measure ammonia and nitrate. E. coli and total counts were ascertained by the biological method. Heavy metals were measured using atomic absorption spectrophotometer. All boreholes met the guideline values of WHO with regard to pH, electrical conductivity, total dissolved solids, chloride and ammonia. Total suspended solids were found to be above the recommended limits of WHO. Nitrate values in all the borehole conformed to the WHO guidelines. Escherichia coli conformed to WHO guideline except at Pangani Borehole 2. Total coliforms did not conform to the set WHO limit values. The concentration of zinc conformed with the set limit values except that of Pangani Borehole 1, Pangani Borehole 2 and Pangani Borehole 3. Concentrations of lead and cadmium in all the boreholes did not conform to the WHO guideline values. It is recommended that the boreholes at Dandora, Kayole and Pangani should not be used for drinking by humans since these heavy metal ions found in the boreholes have a detrimental effect on human health.