Super-learner model realizes the transient prediction of CO2 and NOx of diesel trucks: Model development, evaluation and interpretation

Reconstructing missing NOx emissions in heavy-duty diesel vehicle OBD data: A machine learning approach

On-Board Diagnostic (OBD) systems enable real-time monitoring of heavy-duty diesel vehicle operations and NOx emissions. However, existing OBD systems have inherent limitations, including systematic missing values. To address this issue, this study develops a data-driven approach. The method utilizes OBD-recorded upstream and downstream NOx emissions data to build machine learning models for reconstructing real-world OBD data. The modeling results indicate that machine learning models perform well in predicting upstream emissions, achieving an R² above 0.9 on the test set. However, its performance in predicting downstream emissions was highly variable, with R² ranging from 0.05 to 0.98, and showed a positive correlation with fuel-based emission factors. A case study was conducted on a selected vehicle. The total NOx emission associated with missing data for this specific vehicle was estimated at 15,741.3 g, whereas the recorded emission from available data was 6157.3 g. Missing data were then imputed for an additional 31 vehicles, revealing that normal emitters showed significantly higher emission associated with missing data. The proposed approach is highly compatible with existing big data platforms and can be easily extended to other vehicles. This will improve the platform's representation of real-world emission, enabling policymakers to implement more targeted pollution mitigation strategies.

A comprehensive OBD data analysis framework: Identification and factor analysis of high-emission heavy-duty vehicles

On-Board Diagnostic (OBD) systems enable real-time monitoring of NOx emissions from heavy-duty diesel vehicles (HDDVs). However, few studies have focused on the root cause analysis of these emissions using OBD data. To address this gap, this study proposes an integrated analysis framework for HDDV NOx emissions that combines data processing, high-emission vehicle identification, and emission cause analysis. The framework employs a fuel-based window method to identify high-emission vehicles, while binning and machine learning techniques trace the causes of NOx emissions. A case study is conducted using data from 32 vehicles sourced from Tianjin On-Board Diagnostic Platform. Of these, five vehicles were identified as high emitters. A machine learning model was trained for each vehicle, with a detailed analysis conducted on three of them. The analysis involves a preliminary investigation of vehicle emissions status, followed by bin analysis to initially identify the causes of emissions. Finally, machine learning analysis is conducted, including the generation of individual conditional expectation (ICE) plots and multivariable partial dependence plots (PDPs), serving as a supplement to bin analysis when it cannot effectively pinpoint the causes of high emissions. This approach effectively uncovers the underlying factors within OBD big data. Using the analysis framework, we discover the identified causes of high NOx emissions were uneven heating of the Selective Catalytic Reduction (SCR) system and prolonged idling and high-power operation, catalyst degradation at 200-250 °C, and SCR system failure before 425 °C. The proposed framework offers a clear approach for identifying the causes of NOx emissions, aiding policymakers in implementing effective NOx control strategies for HDDVs.

Comparison of vehicular emissions at different altitudes: Characteristics and policy implications

Applying real-world driving emissions (RDE) data to machine learning, this study investigated vehicular emission characteristics and reduction strategies in Tianjin and Xining, two cities at different altitudes. Significant differences in CO₂ and particulate number (PN) emissions were observed, primarily due to altitude-induced changes in air pressure, affecting air resistance and combustion efficiency. Driving conditions and emission standards were identified as key factors influencing emissions, with road grade and air pressure playing crucial roles at high altitudes. Quantitative assessments showed that speed guidance reduced PN emissions by 34.8% in high-altitude areas, while emission standard upgrades consistently reduced CO₂ emissions by 6.1% across altitudes. These results underscore the need for tailored emission control policies that adapt to local environmental and altitude conditions.

Using the super-learner to predict the chemical acute toxicity on rats

With the rapid increase in the number of commercial chemicals, testing methods regarding on median lethal dose (LD50) relying animal experiments face challenges such as high costs and ethical concerns. Classical quantitative structure-activity relationship models relying on single algorithm always lack interpretability and precision, given the complexity of the mechanisms underlying acute toxicity. To address these issues, this study has developed a predictive framework using an ensemble learning model based on Super-learner. Particularly, we first obtained LD50 data for 9843 compounds and constructed 16 meta models using 4 molecular descriptors and machine learning algorithms. The Super-learner model performed well, achieving R² values of 0.61 and 0.64 in five-fold cross-validation and test sets, respectively, with corresponding root mean square errors of 0.55 and 0.64, significantly outperforming the results of individual model. Additionally, we incorporated data filtering and applicability domain methods, which demonstrated that the Super-learner can mitigate the impact of dataset noise to some extent. The model achieved an R² of 0.76 within an applicability domain, ensuring prediction accuracy within the chemical space. Compared to previous studies, the model developed here using Super-learner generally achieved better performance across a larger applicability domain. Finally, we has launched an online tool (http://sltox.hhra.net), allowing users to quickly predict LD50 of compounds, greatly simplifying the chemical safety assessment process. This study not only provides an effective and cost-efficient method for predicting chemical toxicity but also offers technical support and data for risk assessments of chemicals.

Large-scale deployment of intelligent transportation to help achieve low-carbon and clean sustainable transportation

Sustained deep emission reduction in road transportation is encountering bottleneck. The Intelligent Transportation-Speed Guidance System (ITSGS) is anticipated to overcome this challenge and facilitate the achievement of low-carbon and clean transportation. Here, we compiled vehicle emission datasets collected from real-world road experiments and identified the mapping relationships between four pollutants (CO2, CO, NOx, and THC) and their influencing factors through machine learning. We developed random forest models for each pollutant and achieved strong predictive performance, with an R2 exceeding 0.85 on the test dataset for all models. The environmental benefits of ITSGS at the urban scale were quantified by combining emission models with large-scale real trajectory data from Zibo, Shandong Province. Based on temporal and spatial analyses, we found that ITSGS has varying degrees of emission reduction potential during the morning peak, flat peak, and evening peak hours. Values can range from 5.71 %-8.16 % for CO2 emissions, 13.63 %-16.25 % for NOx emissions, 13.69 %-16.45 % for CO emissions, and 4.84-7.07 % for THC emissions, respectively. Additionally, ITSGS can significantly expand the area of low transient emission zones. The best time for achieving maximum environmental benefits from ITSGS is during the workday flat peak. ITSGS limits high-speed and aggressive driving behavior, thereby smoothing the driving trajectory, reducing the frequency of speed switches, and lowering road traffic emissions. The results of the ITSGS environmental benefits evaluation will provide new insights and solutions for sustainable road traffic emission reduction. SYNOPSIS: Large-scale deployment of Intelligent Transportation - Speed Guidance System is a sustainable solution to help achieve low-carbon and clean transportation.

Evaluation of the accuracy of remote emission sensing measurements via real-world vehicle dynamic tests

To evaluate the measurement accuracy of horizontal and vertical remote emission sensing (RES) equipment, a real-world dynamic test was carried out in Chengdu by using electric vehicles equipped with various concentrations of standard gases. In addition, a new Image-based Spectral Processing Algorithm (ISPA) for vertical remote sensing spectral data was developed to improve the measurement capability. The results showed that the ISPA provided a greater percentage of valid data and lower relative errors; thus, our new algorithm could more effectively analyze the spectral data to measure vehicle emission levels. The percentages of valid horizontal and vertical RES data were 71% and 84%, respectively. The mean relative errors of CO2, CO, HC and NO measured by the vertical RES were about 5%, 20%, 20% and 40%, respectively, and those of CO2, CO and NO measured by the horizontal RES were 3%, 13% and 15%, respectively. For the common vehicle emission concentration, the percentage of valid data for the two RES types increased with increasing gas concentration. As the vehicle speed increased, the relative errors of the horizontal RES equipment showed an increasing trend for the same concentration of gas. Furthermore, for the same speed segment, the relative errors of the horizontal RES equipment increased as the simulated emission concentration decreased. The vertical RES equipment did not exhibit a consistent trend in terms of changes. This study provides a data quality reference for further RES applications.

Olfactory Diagnosis Model for Lung Health Evaluation Based on Pyramid Pooling and SHAP-Based Dual Encoders

This study introduces a novel deep learning framework for lung health evaluation using exhaled gas. The framework synergistically integrates pyramid pooling and a dual-encoder network, leveraging SHapley Additive exPlanations (SHAP) derived feature importance to enhance its predictive capability. The framework is specifically designed to effectively distinguish between smokers, individuals with chronic obstructive pulmonary disease (COPD), and control subjects. The pyramid pooling structure aggregates multilevel global information by pooling features at four scales. SHAP assesses feature importance from the eight sensors. Two encoder architectures handle different feature sets based on their importance, optimizing performance. Besides, the model's robustness is enhanced using the sliding window technique and white noise augmentation on the original data. In 5-fold cross-validation, the model achieved an average accuracy of 96.40%, surpassing that of a single encoder pyramid pooling model by 10.77%. Further optimization of filters in the transformer convolutional layer and pooling size in the pyramid module increased the accuracy to 98.46%. This study offers an efficient tool for identifying the effects of smoking and COPD, as well as a novel approach to utilizing deep learning technology to address complex biomedical issues.

Enhancing vehicular emissions monitoring: A GA-GRU-based soft sensors approach for HDDVs

Vehicle emissions have a serious impact on urban air quality and public health, so environmental authorities around the world have introduced increasingly stringent emission regulations to reduce vehicle exhaust emissions. Nowadays, PEMS (Portable Emission Measurement System) is the most widely used method to measure on-road NOx (Nitrogen Oxides) and PN (Particle Number) emissions from HDDVs (Heavy-Duty Diesel Vehicles). However, the use of PEMS requires a lot of workforce and resources, making it both costly and time-consuming. This study proposes a neural network based on a combination of GA (Genetic Algorithm) and GRU (Gated Recurrent Unit), which uses CC (Pearson Correlation Coefficient) to determine and simplify OBD (On-board Diagnosis) data. The GA-GRU model is trained under three real driving conditions of HDDVs, divided by vehicle driving parameters, and then embedded as a soft sensor in the OBD system to monitor real-time emissions of NOx and PN within the OBD system. This research addresses the existing research gap in the development of soft sensors specifically designed for NOx and PN emission monitoring. In this study, it is demonstrated that the described soft sensor has excellent R2 values and outperforms other conventional models. This research highlights the ability of the proposed soft sensor to eliminate outliers accurately and promptly while consistently tracking predictions throughout the vehicle's lifetime. This method is a groundbreaking update to the vehicle's OBD system, permanently adding monitoring data to the vehicle's OBD, thus fundamentally improving the vehicle's self-monitoring capabilities.

Investigating the impact of high-altitude on vehicle carbon emissions: A comprehensive on-road driving study

This study addresses the literature gap concerning accurately identifying vehicle carbon emission characteristics in high-altitude areas. Utilizing a portable emission measurement system (PEMS) for real-world testing, we quantified the influence of altitude on carbon emissions from light-duty gasoline (LDGV) and diesel vehicles (LDDV). The Random Forest (RF) algorithm was employed to analyze the complex nonlinear relationships between altitude, meteorological conditions, driving patterns, and carbon dioxide (CO2) emissions, enabling predictions across different altitudes. The results showed that CO2 emissions progressively increase with elevation. Furthermore, as altitude increases, combustion efficiency declines, and the overall impact of driving conditions on emission rates diminishes. Altitude and meteorological factors significantly contributed to CO2 emissions, whereas driving conditions and road grades contributed less. Compared with the COPERT model, the RF model demonstrates strong accuracy in predicting carbon emissions at different altitudes. Specifically, the CO2 emission rate nearly triples as altitude increases from 2.0 km to 4.5 km. This research bridges a critical gap in the understanding carbon emissions from high-altitude vehicles, offering insights into policy development for emission reduction strategies in such regions. Future studies should integrate diverse testing methodologies and comprehensive surveys to validate and extend the findings.

Exhaust Emissions from Gasoline Vehicles with Different Fuel Detergency and the Prediction Model Using Deep Learning

Enhancing gasoline detergency is pivotal for enhancing fuel efficiency and mitigating exhaust emissions in gasoline vehicles. This study investigated gasoline vehicle emission characteristics with different gasoline detergency, explored synergistic emission reduction potentials, and developed versatile emission prediction models. The results indicate that improved fuel detergency leads to a reduction of 5.1% in fuel consumption, along with decreases of 3.2% in total CO2, 55.4% in CO, and 15.4% in HC emissions. However, during low-speed driving, CO2 and CO emissions reductions are limited, and HC emissions worsen. A synergistic emission reduction was observed, particularly with CO exhibiting a pronounced reduction compared to HC. The developed deep-learning-based vehicle emission model for different gasoline detergency (DPVEM-DGD) enables accurate emission predictions under various fuel detergency conditions. The Pearson correlation coefficients (Pearson's r) between predicted and measured values of CO2, CO, and HC emissions before and after adding detergency agents are 0.913 and 0.934, 0.895 and 0.915, and 0.931 and 0.969, respectively. The predictive performance improves due to reduced peak emissions resulting from improved fuel detergency. Elevated gasoline detergency not only reduces exhaust emissions but also facilitates more refined emission management to a certain extent.

Applying machine learning to construct braking emission model for real-world road driving

Brake emissions from vehicles are increasing as the number of vehicles increases. However, current research on brake emissions, particularly the intensity and characteristics of emissions under real road conditions, is significantly inadequate compared to exhaust emissions. To this end, a dataset of 600 (200 unique real-world braking events simulated using three types of brake pads) real-world braking events (called brake pad segments) was constructed and a mapping function between the average brake emission intensity of PM2.5 from the segments and the segment features was established by five algorithms (multiple linear regression (MLR) and four machine learning algorithms). Based on the five algorithms, the importance of the different features of the fragments was discussed and brake energy intensity (BEI) and metal content (MC) of the brake pad emissions were identified as the most significant factors affecting brake emissions and used as the final modeling features. Among the five algorithms, categorical boosting (CatBoost) had the best prediction performance, with a mean R2 and RMSE of 0.83 and 0.039 respectively for the tenfold cross-validation. In addition, the CatBoost-based model was further compared with the MOVES model to demonstrate its applicability. The CatBoost-based model has better prediction performance than the MOVES model. The MOVES model overpredicts brake fragment emissions for urban roads and underpredicts brake fragment emissions for motorways. Furthermore, the CatBoost-based model was interpreted and visualized by an individual conditional expectation (ICE) plot to break the machine learning "black box", with BEI and MC showing nonlinear monotonic increasing relationships with braking emissions. ICE plot also provides viable technical solutions for controlling brake emissions in the future. Both avoiding aggressive braking driving behavior (e.g., the application of smart transportation technologies) and using brake pads with less metal content (e.g., using ceramic brake pads) can effectively reduce brake emissions. The construction of a machine learning-based brake emission model and the white-boxing of its model provide excellent insights for the future detailed assessment and control of brake emissions.