globalMOO Documentation
  • globalMOO API Documentation
  • core
    • Authentication
    • Core Concepts
    • Getting Started with globalMOO
    • Error Handling
    • Event Handling
    • SDK Initialization
    • Debugging & Logging
  • schemas
    • Account Schema
    • Model Schema
    • Project Schema
    • Trial Schema
    • Objective Schema
    • Result Schema
    • Inverse Schema
  • quickstart
    • Your First Optimization with globalMOO
  • endpoints
    • accounts
      • Account Endpoints
      • Register Account
    • inverse
      • Inverse Optimization Endpoints
      • Initialize Inverse Optimization
      • Load Inverse Output
      • Suggest Inverse Step
    • models
      • Create Model
      • Model Endpoints
      • List Models
    • objectives
      • Objective Endpoints
      • Load Objectives
    • outputs
      • Output Endpoints
      • Load Output Cases
      • Load Developed Outputs
    • projects
      • Create Project
      • Project Endpoints
    • trials
      • Trial Endpoints
      • Read Trial
Powered by GitBook
On this page
  • Available Endpoints
  • Output Types
  • Common Use Cases
  • Best Practices
  1. endpoints
  2. outputs

Output Endpoints

PreviousoutputsNextLoad Output Cases

Last updated 2 months ago

Output endpoints in globalMOO handle the loading and management of output data for models and trials.

Available Endpoints

  • - Load outputs into a trial

  • - Load output cases into a project

Output Types

  1. Developed Outputs

    • Generated during trial execution

    • Associated with specific trials

    • Used for optimization feedback

  2. Output Cases

    • Reference data for projects

    • Used for model validation

    • Can serve as training data

Common Use Cases

  1. Loading simulation results for optimization

  2. Providing training data for model development

  3. Recording experimental data for comparison

  4. Validating model performance against known cases

Best Practices

  1. Validate output formats before sending

  2. Ensure consistent dimensionality across cases

  3. Use appropriate precision for numeric values

  4. Consider batching large datasets

  5. Handle missing or invalid data appropriately

Load Developed Outputs
Load Output Cases