MYCOLab Ai Logo - gold and army green

Advancing automated identification of airborne fungal spores: guidelines for cultivation and reference dataset creation

Summary

Researchers developed standardized procedures to grow fungal spores in laboratories and prepare them for testing with automated detection devices. They tested 17 different fungal species commonly found in the air and created reference datasets to train computer algorithms to identify these spores. Two different detection technologies were evaluated, showing promising accuracies (55-95%) for identifying various fungal spores. This work provides a blueprint for other scientists to create reliable training data for automated air quality monitoring systems that track allergens and disease-causing fungi.

Background

Airborne fungal spores are important bioaerosols affecting human and plant health. While manual volumetric monitoring methods exist, there is growing demand for automated real-time identification systems. However, automated methods rely on machine learning algorithms that require large, clean reference datasets, which are currently limited for fungal spores.

Objective

This study aimed to establish best practices for cultivating fungal reference material, harvesting clean spores, and creating tailored datasets to train machine learning algorithms for automated identification of airborne fungal spores using airflow cytometry.

Results

Sporulation was successful for all 17 strains. The SwisensPoleno Jupiter achieved macro average F1-scores of 0.77-0.83 with accuracies ranging from 55-95%, showing better performance for Alternaria spp. and Curvularia caricae-papayae. The Plair Rapid-E+ demonstrated accuracies of 83.4-95.1% with macro average F1-score of 0.61, with optimal recognition for Cladosporium spp. and C. caricae-papayae.

Conclusion

The study provides standardized guidelines for fungal spore cultivation, harvesting, and aerosolization suitable for training automated identification algorithms. The protocol demonstrates feasibility of species-level differentiation for certain fungi and paves the way for more efficient and accurate automated identification of airborne fungal spores in monitoring networks.
  • Published in:Aerobiologia,
  • Study Type:Methods Development Study,
  • Source: 10.1007/s10453-025-09864-y, PMID: 40547190, PMCID: PMC12176942
Scroll to Top