Accelerating the pace of ecotoxicological assessment using artificial intelligence.
Source check: Source checked. Not independent scientific confirmation.
Finding: Held-out test R² ranged from 0.54 to 0.75 across species; predictive SSDs were generated for 8,424 chemicals, with selected experimental comparisons. Predictions are screening-level estimates, not experimental toxicity measurements; performance varies by species.
Technology: Eight species-specific artificial neural networks learned chemical-structure descriptors to predict LC50 toxicity values; predicted values were used to fit species-sensitivity distributions.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- Eight species-specific artificial neural networks learned chemical-structure descriptors to predict LC50 toxicity values; predicted values were used to fit species-sensitivity distributions.
- Test and result
- Held-out test R² ranged from 0.54 to 0.75 across species; predictive SSDs were generated for 8,424 chemicals, with selected experimental comparisons.
- Limitation / still unknown
- Predictions are screening-level estimates, not experimental toxicity measurements; performance varies by species.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://link.springer.com/article/10.1007/s13280-021-01598-8
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..
No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.
Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.