Intelligent cost-effective winter road maintenance by predicting road surface temperature using machine learning techniques

Since Winter Road Maintenance (WRM) is an important activity in Nordic countries, accurate intelligent cost-effective WRM can create precise advance plans for developing decision support systems to improve traffic safety on the roads, while reducing cost and negative environmental impacts. Lack of comprehensive knowledge inaccurate information would lead a certain loss budget, reduction, irreparable damage. This study proposes methodology that uses data envelopment analysis machine learning techniques. In proposed methodology, efficiency calculated by different decision-making units (roads), inefficient need be considered further assessments. Therefore, road surface temperature predicted means methods, order achieve efficient effective roads during winter cold regions. total, four methods have been used predict road. One these linear regression, which classical statistical regression technique (ordinary least square regression); other three are machine-learning techniques, including vector multilayer perceptron artificial neural network, random forest regression. Graphical numerical results indicate most method.