University and Academia

Webinars

Teach students modern tools

Engineering education must evolve to match the rapid adoption of artificial intelligence (AI), machine learning (ML), and uncertainty quantification (UQ) in industry. Tools like SmartUQ expose students to the cutting-edge techniques that are transforming simulation-based design, optimization, and validation across sectors such as aerospace, automotive, and energy.

By integrating SmartUQ into the curriculum, educators can teach students how to:

  • Design and analyze experiments using modern methods (e.g., Latin Hypercube and sliced designs, adaptive design, Bayesian sampling).
  • Build fast, accurate surrogate models of complex simulations using Gaussian Processes and other ML techniques.
  • Perform uncertainty propagation, sensitivity analysis, and statistical calibration—key skills for robust engineering decision-making.

Teaching these skills ensures that students graduate with hands-on experience in tools that go beyond traditional solvers and optimization methods. This prepares them to contribute immediately in professional environments that increasingly demand data-driven engineering, robust design under uncertainty, and cross-functional collaboration between simulation, testing, and AI.

Bring Industrial AI, ML, and UQ tools to Research

Modern engineering research increasingly relies on the fusion of physics-based models and data-driven methods. SmartUQ enables academic researchers to tackle real-world problems using industrial-grade tools designed for flexibility, scalability, and insight

With SmartUQ, researchers can:

  • Develop high-dimensional surrogate models that accurately emulate expensive simulations.
  • Fuse test and simulation data through statistical calibration to improve model fidelity and reliability.
  • Explore novel domains such as multi-fidelity modeling, dynamic emulation, inverse analysis, and optimization under uncertainty.

SmartUQ supports a wide range of applications including CFD, structural mechanics, materials research, and manufacturing process optimization. Its flexible APIs and export formats (e.g., FMU for FMI-compliant tools) allow seamless integration into experimental workflows, digital twin frameworks, and control systems research.

By incorporating SmartUQ into research workflows, academic institutions can better align with industry priorities, accelerate discovery, and generate publishable results that are more directly translatable to engineering practice.

Adopted at Leading Universities Around the World:

  • University of Wisconsin-Madison, USA
  • Texas A&M University, USA
  • Nagoya Institute of Technology, Japan
  • Osaka University, Japan
  • Gakushuin University, Japan
  • Kyushu University, Japan
  • University of Occupational and Environmental Health, Japan
  • Keio University, Japan
  • Kanazawa University, Japan
  • Tohoku University, Japan
  • National Chung Hsing University, Taiwan
  • National Sun Yat-sen University, Taiwan
  • National Defense University, Taiwan
  • National Cheng Kung University, Taiwan
  • National Formosa University, Taiwan
  • National Chin-Yi University of Technology,Taiwan
  • National Taiwan Ocean University,Taiwan
  • Feng Chia University,Taiwan
  • Sejong University, Korea

Contact us for information about academic licensing for Research, Classes, and Students. [email protected]