This study introduces an innovative interdisciplinary teaching model that integrates Geoscience, Business, and Data Science through AI-driven research and application development. Unlike traditional lecture-based courses, which follow a bottom-up knowledge acquisition approach and assess students through midterms and final exams, this model adopts a top-down inquiry-based approach, emphasizing real-world application development. It cultivates essential skills such as self-regulated learning, collaborative problem-solving, research inquiry, and effective communication.
The model's innovation is structured around three key themes:

Interdisciplinary Student Collaboration: The course unites students from two complementary backgrounds—those with strong coding and analytical skills but limited domain knowledge, and those with a deep understanding of scientific methodologies but minimal programming experience. Through team-based learning and faculty mentorship, coders gain exposure to hypothesis testing, experimental design, and environmental applications, while science students develop computational proficiency in R and Python for data-driven research.

Real-World Application and Communication Training: Each student team engages in a different domain-specific real-world project and presents their research progress periodically to the entire class. This serves two main objectives:
(a) enhancing their ability to communicate effectively with both domain experts and individuals from other disciplines, and
(b) fostering an awareness of shared STEM competencies—such as statistics, programming, data structures, optimization, and data visualization—regardless of the specific problem domain.

Dual Pathways for Knowledge Dissemination: The course framework supports two distinct yet equally valuable avenues for sharing knowledge. Students interested in academic research focus on scientific writing and conference presentations, while those oriented toward industry develop live online tools, such as mobile applications or interactive websites, to showcase AI-driven solutions.

Project topics span a diverse range of applications, including geohazards, environmental risk assessment, sustainability planning, the impact of ESG (Environmental, Social, Governance) violations on company value, and financial market stability—demonstrating AI’s relevance in both physical and financial systems. By fostering innovation and interdisciplinary collaboration, this teaching model equips students with cross-disciplinary research skills while bridging the gap between academia and industry. As a result, research outcomes become more accessible and impactful for a broader audience.

This paper outlines the course structure, learning objectives, and case studies of student projects, showcasing how interdisciplinary education can drive both academic research and real-world AI applications.

Keywords: Interdisciplinary education, AI-driven research, geoscience, data science, business analytics, sustainability.