Traffic accidents occur due to a combination of factors that lead to casualties and injuries. By identifying the most effective factors, it is possible for safety authorities to provide appropriate solutions for decreasing the accident severity and implementing preventive measures. The aim of this research was to present models to predict the accident severity on two-lane two-way (TLTW) rural highways in Iran over a one-year period from 2019 to 2020. Therefore, the occurrence probability of any type of accident was determined by artificial neural network (ANN)-based prediction models using nine independent variables affecting the accident severity. This study developed numerous ANN structures using back-propagation to model the potential nonlinear relationship between the accident severity and accident-related factors. Results indicated that among the models, the multilayer perceptron neural network (MLPNN) model with 6-2-2 partition had the best performance and prediction power. This model was developed using the standardized rescaling method for covariates and batch for training. Also, 9, 5, and 2 units were considered automatically for the input, hidden, and output layers, respectively, and the hyperbolic tangent and softmax were used as an activation function in the hidden and output layers, respectively. This model had the lowest cross-entropy error of 39.6 and the highest correct percentage of 82.5%, and the area under the receiver operating characteristic (ROC) curve was 0.852. Moreover, among all the effective variables, pavement condition index, roadside hazard, shoulder width, and passing zone ratio had the greatest impact on the accident severity. Finally, safety strategies were proposed to increase safety and reduce accidents along these roads.

The aim of the current research was to develop models to predict the severity of accidents on rural roads in Tehran province, Iran. In this regard, using accident data from 2017 to 2020, the machine learning algorithms, including multiple logistic regression, multilayer perceptron neural network (MLPNN), and radial basis function neural network (RBFNN) models, as well as statistical methods, including Kolmogorov–Smirnov test, Friedman test, and factor analysis, were implemented to determine the contributory factors in the severity of accidents. Thus, nine variables affecting the severity of accidents were considered in modeling, and then the effect of each variable was calculated. By comparing the results of artificial neural network (ANN) models and the Friedman test, it was indicated that the human factor had a remarkable effect on accident severity. In addition, both machine learning and statistical methods can be served as guidance for safety authorities to provide safety solutions, thereby leading to reducing accidents. Finally, the performances of ANN models were analyzed by other mathematical models built by MATLAB programming.