A Digital Twin is a virtual representation of a real-world object or process, leveraging powerful computational architectures available both on-premises and in the cloud. By harnessing the increased availability of real-time data and advancements in machine learning predictive algorithms, Digital Twins find applications across various domains such as Earth Science, Oil and Gas, and Healthcare. However, realizing their full potential demands addressing the technical complexities of integrating numerous components during development and operational phases of the system. This paper describes an ongoing effort to build a comprehensive platform that supports the entire lifecycle of a Digital Twin, from continuous specialized model training to online prediction and event detection, by capturing and processing live data. This approach enables timely updates to the virtual representations of physical elements within the twin application as they change. We detail each component of the Digital Twin solution and demonstrate its applicability through a real use case implemented in the Oil and Gas industry. Specifically, we focus on monitoring the motion of oil platforms to ensure the integrity of the mooring systems and respond to adverse conditions through an alert system powered by our platform.