Engineering systems encounter numerous challenges related to energy losses, surface degradation, and increased maintenance costs caused by friction and wear. Traditionally, addressing these challenges has been both time-consuming and expensive, and conventional solutions often struggle to fully comprehend the intricate complexities of surface interactions. However, recent advancements in data-enabled engineering have revolutionized the field of tribology, empowering engineers with predictive models driven by data analysis. Data-enabled engineering approaches harness cutting-edge sensor technologies, data acquisition methods, and computational power to access vast amounts of tribological data, encompassing experimental measurements, simulations, and historical records. By tapping into this wealth of data, engineers can gain profound insights into tribological phenomena and devise more efficient and effective solutions. The integration of experimental measurements with data-driven techniques paves the way for the creation of highly accurate and reliable predictive models. These models not only optimize tribological designs but also facilitate the prediction of system behavior, empowering engineers to make well-informed decisions. Thanks to their ability to capture intricate interactions, dependencies, and trends, predictive models offer numerous advantages, including design optimization, reduced experimental costs, and enhanced system performance and reliability. In essence, data-enabled engineering methodologies are set to transform tribology by providing a new frontier of predictive models that deliver significant insights and solutions for enhancing the efficiency, dependability, and longevity of mechanical systems across various industrial applications.