Back to papers
0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Environmental Sources Human Health Effects Policy & Risk Sign in to save

Toxicity data for: COLLEMBOT: AI-based counting of Collembola for OECD 232 Tests

Zenodo (CERN European Organization for Nuclear Research) 2026
Micha Wehrli, Adrian Meyer, Éverton Souza da Silva, Sam van Loon, Bart G van Hall, Kees van Gestel, Tiago Natal da Luz, Döring Max, Heike Feldhaar, Heike Feldhaar, Magdalena M. Mair, Denis Jordan, Miriam Langer

Summary

This dataset accompanies research comparing traditional manual counting with an AI-based automated system (COLLEMBOT) for counting springtails in standardized soil toxicity tests. The experiments included exposure to various contaminants including polystyrene microplastics across different soil types. The data provide a resource for validating automated approaches to ecotoxicological testing that could improve the efficiency and reproducibility of microplastic toxicity assessments.

Polymers
PS
Body Systems
Reproductive

This dataset is part of a scientific article in preparation. Currently submitted to Environmental Toxicology & Chemistry. This dataset contains raw and processed data from laboratory toxicity tests on Folsomia candida (Collembola) exposed to various soil contaminants under controlled conditions. The study compares traditional manual counting of juveniles and adults with automated image-based counting using the COLLEMBOT system. Data were collected across multiple soils (LUFA 2.2, OECD variants) and exposure scenarios, including different concentrations of pesticides (e.g., imidacloprid, chlorpyrifos, lindane), fungicides (fluazinam, cyproconazole), microplastics (polystyrene), and reference substances (boric acid). The dataset includes: Raw observations: survival and reproduction endpoints per replicate. Manual vs automated counts: paired measurements for validation of automated image analysis. Metadata: compound identity, soil type, concentration (nominal and adjusted), replicate information. Dose-response modeling script: ECx values (ED10–ED90), NOEC/LOEC estimates, and statistical comparisons between counting methods. This resource supports ecotoxicological research, automation in soil toxicity testing, and reproducibility in environmental risk assessment workflows. This repository also contains the model weights for COLLEMBOT under a AGPL 3.0 license with the code being available at GitHub under a MIT license: https://github.com/waldstrom/collembot

Read via DOI Download PDF

Share this paper

Post Share Share Pin Email