Trend and dynamic analysis on temporal drilling data and their data-driven models

In recent years, digitalization and automation with using novel tools, like data analytics, artificial intelligence, and smart sensors have been adopted in the Oil and Gas industry as game-changer solutions to the most demanding problems, like downhole parameters' estimation, formation classification and incidents detection. Moreover, there are the increasing needs for better interpretation and understanding on data itself and, fur-thermore, on data-driven models/algorithms, especially to facilitate their applications from various engineering perspectives. Our work presents a novel and automatic way to extract trend information from temporal drilling data streams to assist drillers to easily detect drilling process's trend and dynamic changes. In addition, the proposed trend analysis method can be applied to machine learning models to evaluate models' applicability considering their 'black-box' properties.