Creating knowledge by transforming geotechnical data based on machine learning algorithms

Machine learning has become one of the fastest-growing industries of the 21st century due to its ability to process fuzzy, incomplete, distorted, and even incorrect data. This ability to handle uncertainty and complex input relationships makes it a powerful tool for addressing geotechnical transportation problems. Each machine learning technique has distinct characteristics, advantages, and limitations. This variation allows researchers to address the same problem using different techniques to determine the best technique for such a problem. Over the last decades, machine learning has been increasingly applied in the field of transportation geotechnics to improve the design, construction, and maintenance of transportation infrastructure such as roads, railways, and slopes, among others. This chapter summarizes recent implementations of different machine learning algorithms to address complex geotechnical problems, namely: Slope stability level classification by combining machine learning and evolutionary algorithms; machine learning for analysis of equipment sensor data for prediction of road surface condition.