The acquisition of labeled, unbiased, high quality remote sensing information for training AI systems is expensive, error prone, and sometimes impossible or dangerous. The efficacy of Remote Sensing and Imagery Analysis tools that use AI depends directly on the data used for training and validation, meaning that the cost and availability of data limits the application of AI for imagery exploitation. Synthetic Computer Vision (CV) data has become a strategy to reduce the cost and limitations of using real-world data in detection problems in data sparse domains. Focusing on remote sensing data including visible and invisible electromagnetic spectra, attendees will learn about the expanding options for generating synthetic data that are being used in commercial and academic domains, the technology options available for users who want to create CV content of a variety of types, and patterns of creating synthetic data to support Learning Objectives - Describe synthetic data including different types such as Generative AI and physics-based data - Identify the opportunities for applying synthetic data in place of real sensor data Will be able to describe the steps required to generate synthetic data for computer vision workflows from concept to production for training and validating AI. - The intent of this class is to introduce the concepts and mechanisms behind the creation of synthetic data and to expose students to approaches for generating synthetic data using tools currently on the market. - Familiarity with concepts around AI training and validation using remotely sensed data will be helpful for attendees.