Road traffic accidents are among the top ten major causes of fatalities in the world, taking millions of lives annually. Machine-learning ensemble classifiers have been frequently used for the prediction of traffic injury severity. However, their inability to comprehend complex models due to their “black box” nature may lead to unrealistic traffic safety judgments. First, in this research, we propose three state-of-the-art Dynamic Ensemble Learning (DES) algorithms including Meta-Learning for Dynamic Ensemble Selection (META-DES), K-Nearest Oracle Elimination (KNORAE), and Dynamic Ensemble Selection Performance (DES-P), with Random Forest (RF), Adaptive Boosting (AdaBoost), Classification and Regression Tree (CART), and Binary Logistic Regression (BLR) as the base learners. The DES algorithm automatically chooses the subset of classifiers most likely to perform well for each new test instance to be classified when generating a prediction, making it more efficient and flexible. The META-DES model using RF as the base learner outperforms other models with accuracy (75%), recall (69%), precision (71%), and F1-score (72%). Afterwards, the risk factors are analyzed with SHapley Additive exPlanations (SHAP). The driver’s age, month of the year, day of the week, and vehicle type influence SHAP estimation the most. Young drivers are at a heightened risk of fatal accidents. Weekends and summer months see the most fatal injuries. The proposed novel META-DES-RF algorithm with SHAP for predicting injury severity may be of interest to traffic safety researchers.
1 June 2024 in Civil and Environmental Engineering
In this study, the vehicular air pollution from the Nairobi Expressway corridor was estimated by simulation using AERMOD dispersion model. The Vehicle Kilometer Travelled (VKT), emission factors, and traffic data were used to estimate the pollutants from vehicular traffic.. The highest modelled 24-hour and annual concentrations of PM2.5 were 0.274 µg/m 3 and 0.152 µg/m 3 , whereas the highest 24-hour and annual concentrations of PM10 were 0.405 µg/m 3 and 0.225 µg/m 3 , respectively. The maximum 24-hour and annual concentrations of Total Volatile Organic Compounds (TVOCs) were 20.8 µg/m 3 and 11.5 µg/m 3 , respectively, whereas the maximum 8-hour and annual concentrations of carbon monoxide (CO) were 319 µg/m 3 and 177 µg/m 3 , respectively. The highest modeled 24-hour and annual concentrations of NO 2 were 28.2 µg/m 3 and 15.7 µg/m 3 , respectively. The 24-hour average measured TVOCs values showed that Nairobi expressway traffic contributed 3.5 percent to the measured TVOCs concentration value, but CO accounted for 55 percent of the measured value. According to the simulated PM 2.5 and PM 10 concentration values, Nairobi expressway traffic contributed 1.1 and 1.6 percent, respectively, to the 24-hour average measured concentration levels.
8 February 2024 in Engineering, Technology & Applied Science Research
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.
17 May 2025 in Civil and Environmental Engineering
Traffic-related air pollution is a major global concern, causing millions of deaths annually and contributing to a range of chronic health conditions. This study explored public perceptions of traffic-related air pollution and health risks along the Nairobi Expressway through a survey and multinomial logistic regression analysis. The findings indicated that higher income, education, and longer exposure correlate with greater awareness of vehicle emissions and health impacts. Many respondents reported health issues due to high pollutant levels from traffic emissions. Age, gender, and marital status did not significantly influence perceptions of traffic-related air pollution. The study also highlights the resilience of communities in adopting behaviors to mitigate pollution impacts. There is general support for initiatives aimed at reducing air pollution. The research emphasizes the need for collaborative efforts from policymakers and the public to address traffic-related air pollution. This study offers valuable insights for policymakers, transport engineers, and stakeholders to develop strategies for reducing traffic-related air pollution and promoting sustainable transport, aligning with the United Nations Sustainable Development Goals.
Fine particulate matter (PM2.5) poses major public health and environmental threats due to its capacity to enter deep respiratory passages and degrade urban air quality. In the Kingdom of Saudi Arabia (KSA), cities such as Riyadh, Dammam, and Jeddah show an elevated level of PM2.5 due to rapid urban growth, dense traffic activity, and wide industrial operations. This study proposes a hybrid Variational Mode Decomposition–Bidirectional Gated Recurrent Unit (VMD–BiGRU) framework for multi-horizon PM2.5 forecasts based on daily data from January 2022 to September 2024. The daily PM2.5 series was split through VMD into Intrinsic Mode Functions (IMFs) that represent multi-scale temporal patterns. A seven-day ahead forecast was carried out, and model performance was compared with VMD–GRU, VMD–LSTM, and VMD–TCN. For Riyadh, RMSE values for t + 1, t + 2, and t + 3 were 9.25, 12.26, and 16.05 µg/m3, with R2 above 0.90 up to the third day. For Dammam, RMSE values for the same horizons were 4.46, 7.24, and 11.34 µg/m3, and R2 remained above 0.90 up to the fourth day. For Jeddah, the corresponding values were 3.97, 6.09, and 9.36 µg/m3, and R2 remained above 0.90 up to the fourth day. The hybrid VMD–BiGRU model achieved higher accuracy for short horizons (t + 1 to t + 3). The study establishes a basis that aids short-term PM2.5 prediction and improves air quality assessment across major urban centers in KSA.
This study focuses on estimating vehicle-related PM2.5 emissions along the Nairobi Expressway using a novel Local Cascade Ensemble - SHapley Additive exPlanations (LCE-SHAP) framework. The datasets utilized in this research include air quality, meteorological, and traffic data collected from sensors located along three key sites of the expressway: Westlands Roundabout, Nyayo Roundabout, and City Cabanas. The key parameters analyzed are traffic volume, average vehicle speed, humidity, wind speed, and temperature. The proposed model is optimized using Tree-structured Parzen Estimator (TPE) and benchmarked against other machine learning models, including Random Forest (RF), XGBoost, and LightGBM. The results demonstrate that the LCE-SHAP model outperforms existing approaches, achieving a Mean Absolute Error (MAE) of 1.561 and Root Mean Squared Error (RMSE) of 4.203 on the training dataset, and an MAE of 1.943 and RMSE of 4.637 on the testing dataset. This represents a significant improvement in predictive accuracy compared to other models, which exhibited lower R² values and higher error rates. Additionally, SHAP analysis provides insight into key contributing factors, identifying location, humidity, and wind speed as the primary influences on PM2.5 concentrations. The integration of SHAP within the LCE framework ensures both high accuracy in PM2.5 prediction and greater model interpretability, providing actionable insights for environmental management strategies.