Design and Practice of “Lightweight Simulation Experiments” for Geography Data Science Courses in the Digital Intelligence Era

In the digital intelligence era, the rapid development of earth observation technology and the continuous growth of geospatial big data have driven theoretical innovation and industrial upgrading in geography. Geographic data science courses are core curricula for cultivating computational thinking and practical abilities of geography majors. With the deep integration of big data and artificial intelligence, the shortcomings of traditional experimental teaching have become increasingly prominent, manifesting as single data dimensions, incomplete skill training systems, and weak interdisciplinary integration. To address these issues, this paper constructs a lightweight simulation experiment model based on an Internet of Things sensor matrix, establishes a real-time multi-factor geographic environment acquisition system covering illumination, temperature, humidity and wind speed, and completes the full-process practical teaching training from sensor acquisition to cloud storage to algorithm analysis via the Arduino development platform. This experiment model provides a feasible solution for practical teaching in geographic data science courses, strengthens the digital teaching technology foundation of geography, offers a reference for optimizing the teaching reform of geography-related courses in universities, and enhances the quality of interdisciplinary innovative geography talent cultivation.