Automated software for counting and measuring Hyalella genus using artificial intelligence.

Amphipods belonging to the Hyalella genus are macroinvertebrates that inhabit aquatic environments. They are of particular interest in areas such as limnology and ecotoxicology, where data on the number of Hyalella individuals and their allometric measurements are used to assess the environmental dynamics of aquatic ecosystems. In this study, we introduce HyACS, a software tool that uses a model developed with the YOLOv3's architecture to detect individuals, and digital image processing techniques to extract morphological metrics of the Hyalella genus. The software detects body metrics of length, arc length, maximum width, eccentricity, perimeter, and area of Hyalella individuals, using basic imaging capture equipment. The performance metrics indicate that the model developed can achieve high prediction levels, with an accuracy above 90% for the correct identification of individuals. It can perform up to four times faster than traditional visual counting methods and provide precise morphological measurements of Hyalella individuals, which may improve further studies of the species populations and enhance their use as bioindicators of water quality.

Toxicity of methylparaben to green microalgae species and derivation of a predicted no effect concentration (PNEC) in freshwater ecosystems.

Methylparaben (MeP) is one of the most used preservatives in the industry; however, the toxic effects on aquatic ecosystems are still poorly understood. Therefore, this study was conducted (1) to identify and compare the toxic effects of MeP on physiological parameters of different green microalgae species, using suitable mathematical models; and (2) to estimate a PNEC value for MeP in freshwater ecosystems, adopting either the deterministic or the probabilistic approaches. Toxicity tests were carried out with three green microalgae (Pseudopediastrum boryanum, Desmodesmus communis, Raphidocelis subcapitata), in which different endpoints such as growth rate, chlorophyll-a, and cell viability were measured and compared through the effective concentration which caused a response in x% of test organisms (ECx). ECx were obtained by adjusting different non-linear regression models for each microalgae dataset. Chlorophyll-a endpoint resulted in the lowest EC50 values, respectively 125, 81.2, 18.3 mg L-1 for D. communis, P. boryanum and R. subcapitata, showing R. subicapitata as the most sensitive, and D. communis as the most tolerant species to MeP (P < 0.05). PNEC was estimated from the present study and previous reports resulting in 5.7 and 65 µg L-1, respectively for the deterministic (PNECd) and the probabilistic (PNECp) approach. The development of chronic assays using test organisms from different ecological groups is encouraged to provide robust PNECp. In this meantime, we recommend the use of the estimated PNECd to support MeP risk assessments and policy formulation.