PhytoOracle: A scalable, modular data pipeline

PhytoOracle is a scalable, modular data pipeline for phenomics research. It uses CCTools’ Makeflow and WorkQueue distributed task management frameworks. As a result, PhytoOracle significantly reduces data processing times. The pipeline also enables researchers to swap between supported extractors or to easily integrate new extractors. PhytoOracle is, therefore, able to handle the increasing rate of data collection while making it accessible to a wide range of users.

Home

• Welcome to PhytoOracle!
  • Supported Sensors & Pipelines
  • Pipeline Structure
  • Acknowledgements
  • Issues and Questions

Requirements & Set Ups

• Using PhytoOracle on the HPC
  • Overview
  • Software Requirements
  • Launching Interactive Node
  • Launching Workers
• Obtaining Pipeline Related Containers
  • Full list of containers
    • StereoTopRGB
    • FlirIr
    • PSII
    • Scanner3DTop

User Guides

• Running the StereoTopRGB Pipeline for Detecting Plant Area Data
  • Pipeline Overview
  • Running the Pipeline
    • Retrieve data
    • Retrieve vector and ML model files
    • Edit scripts
    • Run pipeline
    • Troubleshooting and Issues
• Running the FlirIr Pipeline for Infrared Data
  • Pipeline Overview
  • Running the Pipeline
    • Retrieve data
    • Edit scripts
    • Run pipeline
• Running the PSII Pipeline for Photosynthetic Potential Data
  • Pipeline Overview
  • Running the Pipeline
    • Retrieve data
    • Edit scripts
    • Run pipeline
• Running the Scanner3DTop Pipeline for Generating 3D Point Clouds
  • Pipeline Overview
  • Running the Pipeline
    • Retrieve data
    • Edit scripts
    • Run pipeline