Abstract

Scientific and technological convergence--the integration of knowledge, methods, and technologies from diverse domains--is a critical driver of innovation in the modern era. This study examines how scientific convergence drives technological innovation, with a particular emphasis on Artificial Intelligence (AI) as a meta-technology that accelerates interdisciplinary integration. Using 41,556 Canadian AI publications from 2000 to 2023 indexed in Scopus, we map patterns of knowledge convergence through citation networks. Fast-Newman clustering was applied to identify thematic communities via modularity optimization, while BERTopic was used to extract semantic topics within each community. Pathway analysis quantified the temporal evolution of these communities using overlap metrics to capture the dynamics of convergence over time. Our analysis shows that scientific convergence is a structured yet non-linear process driven by meta-technologies such as AI, which serve as cross-disciplinary catalysts. We identified three key patterns that shape new fields, and we observed that four analyzed communities embody a common growth pattern in which interaction with real-world problems enriches methodological knowledge, in tune with the paradigm of ``use-inspired'' basic research. These results highlight artificial intelligence’s central role in bridging distinct domains, fostering the emergence of new scientific disciplines, and enabling transformative technological developments. The proposed framework offers a data-driven approach for anticipating high-potential interdisciplinary fields, guiding strategic investments, and informing innovation policy in an increasingly interconnected research landscape.