In this project, students will explore the fundamentals of machine learning applied to a space weather example through a hands-on activity. By using the space weather domain, this lesson can also be applied to general science standards. Using Google’s Teachable Machine, students create an image classification model that can recognize and differentiate between key space weather phenomena such as auroras, solar flares, and sunspots. This accessible approach introduces real-world applications of AI in science while helping students build practical skills in data analysis and pattern recognition. Students then deploy their models using a simple web application built with HTML and JavaScript. This combined assignment allows students to gain firsthand experience with advanced machine learning concepts, including model inference, confidence scores, and integrating models into digital tools. Designed for high school and introductory computer science courses, the project requires minimal technical setup and is adaptable to various levels. Students not only learn the basics of machine learning, such as how training data works, why class balance matters, and how to test with new examples, but also strengthen their coding skills by customizing and debugging their own web apps. For more advanced students, optional extension activities introduce topics such as user interface design, artificial intelligence ethics, and the impact of space weather on the technology we rely on every day.