This article proposes a methodology for the estimation of emissions in real driving conditions, based on board diagnostics data and machine learning, since it has been detected that there are no models for estimating pollutants without large measurement campaigns. For this purpose, driving data are obtained by means of a data logger and emissions through a portable emissions measurement system in a real driving emissions test. The data obtained are used to train artificial neural networks that estimate emissions, having previously estimated the relative importance of variables through random forest techniques. Then, by the application of the K-means algorithm, labels are obtained to implement a classification tree and thereby determine the selected gear by the driver. These models were loaded with a data set generated covering 1218.19 km of driving. The results generated were compared to the ones obtained by applying the international vehicle emissions model and with the results of the real driving emissions test, showing evidence of similar results. The main contribution of this article is that the generated model is stronger in different traffic conditions and presents good results at the speed interval with small differences at low average driving speeds because more than half of the vehicle’s trip occurs in urban areas, in completely random driving conditions. These results can be useful for the estimation of emission factors with potential application in vehicular homologation processes and the estimation of vehicular emission inventories.

The study of road accidents and the adoption of measures to reduce them is one of the most important targets of the Sustainable Development Goals for 2030. To further progress in the improvement of road safety, it is necessary to focus studies on specific groups, such as light trucks and vans. Since 2013 in Spain, there has been an upturn in accidents in these two categories of vehicles and a renewed interest to deepen our understanding of the causes that encourage this behavior. This paper focuses on using machine learning methods to explain driver-injury severity in run-off-roadway and rollover types of accidents. A Random Forest (RF)-classification tree (CART) approach is used to select the relevant categorical variables (driver, vehicle, infrastructure, and environmental factors) to obtain models that classify, explain, and predict the severity of such accidents with good accuracy. A support vector machine and binomial logit models were applied in order to contrast the variable importance ranking and the performance analysis, and the results are convergent with the RF+CART approach (more than 70% accuracy). The resulting models highlight the importance of using safety belts, as well as psychophysical conditions (alcohol, drugs, or sleep deprivation) and injury localization for the two accident types.

This paper is focused on the effect of road geometry, and other accident causing conditions, on the binary response variable road accident severity. The data is collected from two interurban routes in Spain (Madrid-Irún and Barcelona-Almeria) and covers a 3 year period (2010-2012). Data mining techniques were applied for the treatment and combination of two databases for road accident associated factors and geometry standards respectively. The effect of the influential factors on road accident severity was estimated through a non-parametric statistical methodology, random forests. Several standards of the road geometry design were found to have a significant effect on the road accident severity

This paper illustrates a methodology developed to analyze the influence of traffic conditions, i.e. volume and composition on accidents on different types of interurban roads in Spain, by applying negative binomial models. The annual average daily traffic was identified as the most important variable, followed by the percentage of heavy goods vehicles, and different covariate patterns were found for each road type. The analysis of hypothetical scenarios of the reduction of heavy goods vehicles in two of the most representative freight transportation corridors, combined with hypotheses of total daily traffic mean intensity variation, produced by the existence or absence of induced traffic gives rise to several scenarios. In all cases a reduction in the total number of accidents would occur as a result of the drop in the number of heavy goods transport vehicles, However the higher traffic intensity, resulting of the induction of other vehicular traffic, reduces the effects on the number of accidents on single carriageway road segments compared with high capacity roads, due to the increase in exposure. This type of analysis provides objective elements for evaluating policies that encourage modal shifts and road safety enhancements.