User guide

• Make GEMSEO easy to use
  • High-level functions to use GEMSEO
  • Interface a software
  • Define an MDO problem
  • Cheat sheets
  • Extend GEMSEO features
• Main concepts
  • Design space
  • Discipline
  • Scenario
  • Data persistence
• Optimization and DOE
  • The GEMSEO concepts
  • Optimization and DOE framework
  • Optimization algorithms
  • DOE algorithms
• Design of experiments
  • API
  • Algorithms
  • Advanced use
• Multidisciplinary design optimization
  • Coupling visualization
  • MDO formulations
  • Multi Disciplinary Analyses
  • How to deal with post-processing
• Machine learning
  • Introduction
  • API
  • Unsupervised learning for unlabeled data
  • Supervised learning for input-output data
  • Measure the quality of a machine learning algorithm
  • Calibrate or select a machine learning algorithm
  • Transform data to improve the ML algorithm quality
• Surrogate models
  • Create a surrogate discipline
• Uncertainty quantification
  • Introduction
  • Probability distribution
  • Parameter space
  • Statistics
  • Sensitivity analysis
• Scalable models
  • Scalable models
  • The scalable problem
• Algorithms
  • DOE algorithms
  • Linear solvers
  • Algorithms of machine learning
  • MDA algorithms
  • MDO formulations
  • Ordinary differential equations solvers
  • Optimization algorithms
  • Post-processing algorithms
  • Surrogate disciplines
  • Uncertainty algorithms
• Benchmark problems
  • Sellar’s problem
  • Aerostructure problem
  • Sobieski’s SSBJ test case
  • The Propane combustion problem