Developing a weather prediction project-based machine learning course in facilitating AI learning among high school students

Abstract

The rapid growth of artificial intelligence (AI) technology has changed lifestyles, work patterns, and educational approaches. However, courses that can guide students through the practical applications of AI technology are still scarce in K-12 education. This study aimed to develop a project-based machine learning (ML) course for the implementation of AI technology. The core idea of this course, which focused on the supervised learning of AI ML technology, was designed based on the project of weather prediction. Furthermore, data collection and status display were realized using various hardware devices such as Arduino and sensors, whereas ML algorithms were implemented in Python programming language. A total of 68 eleventh-grade senior high school students from a public school in Southern Taiwan participated in this study. The main variables included understanding AI concepts, computational thinking (CT), and learning attitude. Data were analyzed using quantitative statistics, including descriptive statistics, t-test, and analysis of covariance, supplemented with qualitative data. Based on the findings, the following conclusions were drawn: (1) the proposed course on the implementation of ML helps students understand the basic concepts of AI; (2) students demonstrate a significant improvement in CT skills after attending this course; (3) although the students’ attitude toward learning AI shows no significant change after attending this course, their overall view for it is positive; (4) contrary to their learning attitude, the CT skills among the students with different capabilities of learning AI are significantly dissimilar. Overall, the machine-learning implementation course developed in this study can serve as a reference for promoting AI education in the future. However, considering learners’ prior knowledge in programming, setting up appropriate learning scaffolding for them, and providing them with more examples of the applications of AI in real-life scenarios is still necessary when conducting the course for improving the students’ attitude toward AI.