Emerging AI Technologies and Future Trends in Sports Sciences
Abstract
This chapter examines emerging Artificial Intelligence technologies and future trends shaping the evolution of Sports Science, emphasizing the transition from retrospective data analysis toward real-time, adaptive, and autonomous systems. It highlights the convergence of Artificial Intelligence with edge computing, wearable technologies, and advanced sensor networks, enabling low-latency data processing and personalized performance monitoring directly within training environments. The chapter introduces agentic Artificial Intelligence systems capable of semi-autonomous decision-making through closed-loop architectures, such as the MAPE-K cycle, and discusses their potential role in optimizing training load, injury prevention, and performance management. It further explores the concept of digital twins, which integrate multimodal physiological and behavioral data into dynamic virtual representations of athletes, supporting predictive modeling and individualized intervention strategies. In addition, the chapter outlines key interdisciplinary and institutional challenges, including the need for data sharing, methodological transparency, curriculum development, and collaboration between sport scientists and technical experts. Finally, it addresses long-term disruptive innovations such as Quantum Artificial Intelligence, positioning them as a transformative horizon for complex pattern recognition and optimization in sports contexts. The chapter contributes to a forward-looking understanding of Artificial Intelligence in Sports Science by integrating technological, methodological, and systemic perspectives.
