A recent big wave in machine learning (ML) has led to massive successes by leveraging large amounts of data, advancing ML algorithms, and innovating computational hardware. Deep learning (DL) methods have been greatly advanced to efficiently extract information, discover knowledge, and identify correlations and patterns. Recent efforts to apply ML driven models for problems in flow, transport, and coupled thermal-chemical-mechanical processes in natural and engineered environments demonstrated promising outcomes. Numerical simulations, governing equations, physical constraints, laboratory observations, and field measurement data all can be utilized to develop data-driven models in the physics-informed ML framework. The purpose of this session is to bring the latest theoretical, algorithmic, and practical advancements of ML to flow, transport, and the coupled processes across spatial and/or temporal scales in order to advance various ML/DL methods with our domain knowledge in terms of various data type and volume, modeling and simulations, and physical equations and constraints.