cancel
Showing results for 
Show  only  | Search instead for 
Did you mean: 
Try the Materials Informatics Toolkit, which is designed to easily handle SMILES data. This and other helpful add-ins are available in the JMP® Marketplace
Choose Language Hide Translation Bar
View Original Published Thread

Using Design of Experiments Methods for Efficient Modeling & Simulation

Published on ‎11-07-2024 03:30 PM by Community Manager Community Manager | Updated on ‎11-07-2024 05:40 PM

 

Using DOE for Efficient Modeling and Simulation
Video Player is loading.
Current Time 0:00
Duration 54:49
Loaded: 0%
Stream Type LIVE
Remaining Time 54:49
 
1x
    • Chapters
    • descriptions off, selected
    • captions off, selected
    • en (Main), selected
    (view in My Videos)

     

    By sequentially running High Performance Computer (HPC) simulations in Design of Experiments (DOE) blocks, one can quickly increase the accuracy of fast surrogate models. When sufficiently precise surrogates have been obtained, HPC resources can sooner be made available to other Modeling & Simulation (M&S) projects.  

     

    See how to:

    • Understand why to create a designed experiment before attempting modeling and simulation
    • Compare and contract traditional DOE vs. Space-Filling DOE
    • Decide which types of design to use – Latin Hypercube or Space-Filling
    • Create a Space-Filling design, explore it visually, apply regression and machine learning models, create and honest assessment that includes training/test/validation data

    NOTE: Q&A is interspersed throughout the video.

     

    Resources:

    Efficient DOE.JPG



    Attachments
    0 Kudos
    0 Comments