With the advent of powerful heterogeneous computers, scientists and engineers face unprecedented challenges in adapting their workflows to the demands of scientific machine learning and developing efficient surrogate models, typically through reduced order models. This mini-symposium, designed to be highly practical, provides a platform for attendees to exchange information, share best practices, and, most importantly, stay current on the rapidly evolving information technologies that are reshaping the convergence of simulation tools, scientific machine learning, and reduced order modeling. The Mini-Symposium topics cover (but are not limited to):

Computational environments for advanced scientific machine learning and engineering computation Digital prototyping techniques

Enabling software technologies

Data science in computational science applications

Software libraries and applications for model reduction and scientific machine learning

Supporting tools in performance evaluation, visualization, verification, and validation

Scientific workflows, theoretical frameworks, methodology, and algorithms