Classification model training data for LabelChecker pipeline

These datasets were used to train two separate classification models as a demonstration of machine learning applications in the manuscript "Pipeline for FlowCam data processing with modular open-source software and optional machine learning classification" (under review). Folder and file names in both datasets denote <enclosure number>_<date>_<magnification>_<techinal replicate> SYKE dataset Integrated plankton samples collected from indoor experimental enclosures. Water in the enclosures was collected from the Bay of Finland. FlowCam runs collected with a FlowCam VS and VisualSpreadsheet v4.19.3. The instrument was equipped with a 100 µm flow cell and a 10x objective lens. Samples were run for 10 minutes in the AutoImage mode. LakeLab dataset Integrated epilimlion plankton samples collected from in situ experimental enclosures in Lake Stechlin, Germany. FlowCam runs collected with a FlowCam CYANO 8000 series and VisualSpreadsheet v4.15.1. The instrument was equipped with a 300 µm flow cell and a 4x objective lens. Samples were run for 5 minutes in the AutoImage mode.