This workflow aims to automate the counting of pollen grains in microscopy images. It involves two main components: extracting purple-colored pollen grains from large microscopy images and using artificial intelligence to count the grains. The processed data is then stored in CSV and JSON formats. This workflow enhances the efficiency and accuracy of pollen grain counting, providing valuable data for aerobiological studies. Key questions addressed include the precision of color extraction, the accuracy of AI-based counting, and the efficiency of data storage. Background Microscopy images of pollen samples collected from pollen traps provide valuable insights into airborne pollen concentration. This workflow, consisting of two components, focuses on processing large microscopy images. The images, featuring purple-colored pollen grains, undergo an initial phase of color extraction. The second component employs artificial intelligence techniques to count and record the total number of pollen grains present in the sample. The workflow then stores this information in both CSV and JSON formats. Introduction Microscopy analysis of pollen samples is a fundamental aspect of aerobiological studies. This workflow addresses the processing of large microscopy images derived from pollen traps. The images contain pollen grains colored in purple, and the workflow employs artificial intelligence techniques for precise pollen grain counting. The final output includes comprehensive CSV and JSON files, providing a detailed record of the total pollen count in the sample. Aims The primary aim of this workflow is to automate the pollen grain counting process in microscopy images, enhancing efficiency and accuracy. The workflow includes the following key components: - Color Extraction and Image Preprocessing: Extracts purple-colored pollen grains from microscopy images, preparing the data for subsequent counting. - Pollen Grain Counting and Data Storage: Utilizes artificial intelligence techniques to count the total number of pollen grains in the sample and stores this information in both CSV and JSON formats. Scientific Questions - Color Extraction Precision: How precise is the color extraction component in isolating purple-colored pollen grains from the microscopy images? - Pollen Grain Counting Accuracy: How accurate is the artificial intelligence-based pollen grain counting component in determining the total pollen count in the sample? - CSV and JSON Storage Efficiency: How efficiently does the workflow store pollen count information in both CSV and JSON formats, ensuring accessibility and data integrity? - Workflow Automation Impact: To what extent does the workflow automation enhance the efficiency and reliability of pollen grain counting compared to manual methods?

Sierra Nevada Global Change Observatory is an ambitious project promoted by the Environmental and Regional Planning Council of the Regional Government of Andalusia and the University of Granada, in order to develop a monitoring and information management programme. Our programme is intended to diagnose the degree of ecosystem sensitivity to changes, and their adaptation capacity, fostering resistance and resilience of the ecosystems through suitable management actions.