Interstate-80 Closures: A Support Vector Machine Model

Road closure due to adverse and severe weather is common in Wyoming even in summer due to its high elevation and mountain related ice and snow storms. One particular section of Interstate-80 will be investigated. In this initial data driven study we use machine learning techniques based on a support vector machine approach to establish a predictive model for road closures in this region using roadway sensor data and road closure data. As the results suggest, such a data driven model will be beneficial in both establishing legitimate road closures and improving general safety in this region during periods of adverse and severe weather. In particular, the new model is superior to the ad hoc procedures currently in place by the state transportation department.