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.

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

The transient simulation of CO2 and NOX from motor vehicles has essential applications in evaluating vehicular greenhouse gas emissions and pollutant emissions. However, accurately estimating vehicular transient emissions is challenging due to the heterogeneity between different vehicles and the continuous upgrading of vehicle exhaust purification technology. To accurately characterize the transient emissions of motor vehicles, a Super-learner model is used to build CO2 and NOx transient emission models. The actual onboard test data of 9 China VI N2 vehicles were used to train the model, and the test data of another China VI N2 vehicle were selected for further robustness verification. There were significant differences in the emissions between the vehicles, but the constructed transient model could capture the common law of transient emissions from China VI N2 vehicles. The R2 values of CO2 and NOx emission in the test data of the validation vehicle were 0.71 and 0.82, respectively. In addition, to further prove the model's robustness, the training data were synchronously modelled based on the Moves-method. The Super-learner model has a smaller RMSE on the validation set than the model based on the Moves-method, indicating that the Super-learner model has more transient simulation advantages. The marginal contributions of the model characteristics to the model results were analysed by SHapley Additive exPlanation (SHAP) value interpretation, and the marginal contributions of different pollutant characteristic parameters varied. Therefore, when establishing transient models of different pollutants, the selection of the model parameters demands considering the generation and purification process of different pollutants. The present work provides novel insights into the parameter selection, construction, and interpretation of the transient vehicle emission model.

NH3 Sensor Based on 2D Wormlike Polypyrrole/Graphene Heterostructures for a Self-Powered Integrated System.

The rapid development of a NH3 sensor puts forward a great challenge for active materials and integrated sensing systems. In this work, an ultrasensitive NH3 sensor based on two-dimensional (2D) wormlike mesoporous polypyrrole/reduced graphene oxide (w-mPPy@rGO) heterostructures, synthesized by a universal soft template method is reported, revealing the structure-property coupling effect of the w-mPPy/rGO heterostructure for sensing performance improvement, and demonstrates great potential in the integration of a self-powered sensor system. Remarkably, the 2D w-mPPy@rGO heterostructrure exhibits preferable response toward NH3 (ΔR/R0 = 45% for 10 ppm NH3 with a detection limit of 41 ppb) than those of the spherical mesoporous hybrid (s-mPPy@rGO) and the nonporous hybrid (n-PPy@rGO) due to its large specific surface area (193 m2/g), which guarantees fast gas diffusion and transport of carriers. Moreover, the w-mPPy@rGO heterostructures display outstanding selectivity to common volatile organic compounds (VOCs), H2S, and CO, prominent antihumidity inteference superior to most existing chemosensors, superior reversibility and favorable repeatability, providing high potential for practicability. Thus, a self-powered sensor system composed of a nanogenerator, a lithium-ion battery, and a w-mPPy@rGO-based sensor was fabricated to realize wireless, portable, cost-effective, and light-weight NH3 monitoring. Impressively, our self-powered sensor system exhibits high response toward 5-40 mg NH4NO3, which is a common explosive to generate NH3 via alkaline hydrolysis, rendering it a highly prospective technique in a NH3-based sensing field.

[Vehicle Emission Inventory and Scenario Analysis in Liaoning from 2000 to 2030].

Vehicle emissions have become a major source of air pollution in urban cities. The vehicle emission inventory of the Liaoning province from 2000 to 2030 was established based on the COPERT model and ArcGIS, and the temporal and spatial distribution characteristics of six pollutants (CO, NMVOC, NOx, PM10, SO2, and CO2) were analyzed. Taking 2016 as the base year, eight scenarios of control measures were designed based on scenario analysis, and the effects of different scenarios on emission reduction were assessed. Results showed that during 2000-2016, CO, NMVOC, NOx, and PM10 emissions at first exhibited increasing trends, after which they decreased. Emissions of SO2 exhibited fluctuating trends, while the emissions of CO2 showed a continuous increase. Passenger cars and motorcycles were the main contributors of CO and NMVOC emissions. Heavy-duty trucks and buses were the main sources of NOx and PM10 emissions. Passenger cars were the major contributors to SO2 and CO2 emissions. Vehicle emissions were significantly higher in the central and southern in Liaoning Province. At the city level, vehicle emissions were mainly concentrated in Shenyang and Dalian. The scenario analysis showed that the implementation of stricter vehicle emission standards can enhance the emission reduction effect. Moreover, accelerating the implementation of new emission standards was beneficial to reduce emissions. The integrated scenario would achieve the maximum emission reduction, with reduction rates of CO, NMVOC, NOx, PM10, CO2, and SO2 at 30.7%, 14.3%, 81.7%, 29.4%, 12.3%, and 12.1%, respectively.

Emission characteristics and temporal variation of PAHs and their derivatives from an ocean-going cargo vessel.

Polycyclic aromatic hydrocarbons (PAHs), nitro- (NPAHs) and oxy-derivatives (OPAHs) are of considerable concern due to their toxicity and carcinogenic hazards. Ships are recognized as an important emission source of these compounds. Marine diesel oil (MDO) and heavy fuel oil (HFO) are the two most commonly used fuels. The emission characteristics and toxicities of PM2.5-bound PAHs, NPAHs and OPAHs due to HFO and MDO combustion in atypical ocean-going vessel were investigated. The EF variability of polycyclic aromatic compounds (PACs) varied considerably with the fuel formulation (HFO and MDO) and engine loading (20%-100%). The concentration of ΣPACs was 0.63 mg/kWh for MDO and ranged from 2.14 to 9.80 mg/kWh for HFO. Compared to HFO-20%, the EFs of ΣPAHs, ΣNPAHs and ΣOPAHs from MDO-20% were reduced by 97%, 77% and 73%, respectively. As identified through the coefficient of divergence, the profile of HFO-20% was notably different from those under the other three engine loadings for HFO. In addition, the emissions of ΣPAHs and ΣOPAHs showed a significant correlation with PM2.5, while they were relatively weak for ΣNPAHs. However, the CO and PAC emissions were not highly correlated. Furthermore, the BaPeq-ΣPAHs values were 0.010 mg/g for MDO and ranged from 0.092 mg/g to 0.306 mg/g for HFO, and the reduction ranged from 89% to 97% by substituting MDO for HFO. These data highlight the importance of improving fuel quality in close proximity to port areas and are useful for enhancing relevant databases.

Family of Highly Luminescent Pure Ionic Copper(I) Bromide Based Hybrid Materials.

While a number of highly luminescent copper(I) halide based hybrid materials built on coordinate bonds (Cu-L; L = N, P, S-based ligands) have been obtained, the poor structural stability largely limited their commercialization. In contrast, according to the previous studies, the ionic structures (L-free) are more stable than those built on Cu-L coordinate bonds. However, the extremely weak emission hinders their optical applications. Herein, we report a tetra-alkylammonium-cation-induced strategy for the synthesis of stable and highly luminescent ionic CuBr-based hybrid materials. It is interesting to find that the tetra-alkylammonium cations with different chains could induce diverse CuBr-based anions. Moreover, most of these CuBr-based hybrids are highly luminescent, which makes them promising candidates as an alternative to phosphors and with potential applications in sensing.