Importance of artificial intelligence in Computational Fluid Dynamics Vision 2030—editor’s perspective

The vision for computational fluid dynamics (CFD) in 2030, now less than a decade away, has been an ambitious and inspiring goal for researchers dedicated to advancing the field and its applications. Originally released by NASA in 2014 the initiative aimed to drive CFD development, particularly in aerospace applications. The 2030 roadmap is structured around six key technical domains: physical modeling, algorithms, geometry and grid generation, knowledge extraction, and multidisciplinary analysis and optimization, each encompassing multiple subtopics. These domains were strategically selected to leverage the capabilities of massively parallel systems, such as high-performance computing, and to integrate emerging technologies, including quantum computing, as the field transitions from petascale to exascale computing. The complexity of CFD applications in aerospace has been systematically addressed from 2015 to the 2030 deadline. Since its inception in 2014, significant progress has been made, including the formulation of grand challenge problems to quantify advancements. When the roadmap was developed, artificial intelligence (AI) was still in its early stages. While machine learning has since been integrated into complex flow modeling as part of physical modeling, AI tools also hold great potential for other subfields, such as meshing, optimization, and visualization. This chapter provides a comprehensive overview of AI’s role in CFD Vision 2030, highlighting its current applications, significance, and future direction. However, this perspective may evolve with the commercialization and advancement of quantum computing may help in future roadmaps.