How to Run Design of Experiments on Rescale Using Rescale Edison and Workflows
Blog post from Rescale
Rescale has introduced two Design of Experiments approaches powered by Rescale Edison and Workflows, expanding beyond its traditional DOE job type for simple parameter sweeps. Edison can recommend and generate DOE matrices using methods such as full or fractional factorial designs, Latin hypercube sampling, Box-Behnken, central composite, and Monte Carlo sampling, then submit them through either independent Workflow Runs or a centralized Workflow Template. Workflow Runs create a separate, fully independent workflow for each design point, supporting custom fields, automations, pre- and post-processing, parallel execution, and isolated reruns of failed cases. Workflow Templates instead place all design points on one canvas, enabling engineers to review configurations and dependencies before submission, centrally monitor status, control concurrency, and retain a single record of the study. Both options work with any solver on Rescale and can make DOE results available for analysis and AI Physics model training, with the preferred method depending on whether per-run flexibility or centralized oversight is more important.
No tracked trend matches for this post yet.
Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.