Automated identification of aquatic insects: A case study using deep learning and computer vision techniques.

Deep learning techniques have recently found application in biodiversity research. Mayflies (Ephemeroptera), stoneflies (Plecoptera) and caddisflies (Trichoptera), often abbreviated as EPT, are frequently used for freshwater biomonitoring due to their large numbers and sensitivity to environmental changes. However, the morphological identification of EPT species is a challenging but fundamental task. Morphological identification of these freshwater insects is therefore not only extremely time-consuming and costly, but also often leads to misjudgments or generates datasets with low taxonomic resolution. Here, we investigated the application of deep learning to increase the efficiency and taxonomic resolution of biomonitoring programs. Our database contains 90 EPT taxa (genus or species level), with the number of images per category ranging from 21 to 300 (16,650 in total). Upon completion of training, a CNN (Convolutional Neural Network) model was created, capable of automatically classifying these taxa into their appropriate taxonomic categories with an accuracy of 98.7 %. Our model achieved a perfect classification rate of 100 % for 68 of the taxa in our dataset. We achieved noteworthy classification accuracy with morphologically closely related taxa within the training data (e.g., species of the genus Baetis, Hydropsyche, Perla). Gradient-weighted Class Activation Mapping (Grad-CAM) visualized the morphological features responsible for the classification of the treated species in the CNN models. Within Ephemeroptera, the head was the most important feature, while the thorax and abdomen were equally important for the classification of Plecoptera taxa. For the order Trichoptera, the head and thorax were almost equally important. Our database is recognized as the most extensive aquatic insect database, notably distinguished by its wealth of included categories (taxa). Our approach can help solve long-standing challenges in biodiversity research and address pressing issues in monitoring programs by saving time in sample identification.

Histopathology of chironomids exposed to fly ash and microplastics as a new biomarker of ecotoxicological assessment.

In the last few decades, industrial pollution has gained extensive attention in terms of its effect on the aquatic environment. This imposes the need to develop sensitive biomarkers for early detection of pollutant toxicity in ecotoxicological assessment. The advantages of histopathological biomarkers are many, including quick reaction to the presence of contaminants, and the small number of individuals needed for efficient analysis. The present study analyzed the negative effect of lignite coal fly ash (LCFA) and microplastic particles (MPs) on Chironomus riparius, a suggested model organism by the Organization for Economic Cooperation and Development (OECD). This study aimed to perform histological analyses of larval tissues and target potential changes in treated groups that could serve as promising histopathological biomarkers of the contaminant's negative effects. Following that, other known sensitive sub-organismal biomarkers were analyzed and paired with the histopathological ones. Histological analysis of larvae showed a significantly decreased length of microvilli in midgut regions II and III in both treatments. Treatments with MPs affected oxidative stress parameters: thiobarbituric acid reactive substances (TBARS), advanced oxidation protein products (AOPP), superoxide dismutase (SOD), and hemoglobin levels, while LCFA significantly affected all tested sub-organismal biomarkers (DNA damage, levels of AOPP, SOD, and hemoglobin), except catalase (CAT) and TBARS. When observing histological slides, a significant shortage of brush border length in the posterior parts of the midgut was detected in all treatments. In the case of LCFA, the appearance of intensive vacuolization of digestive cells with inclusions resembling apoptotic bodies, in mentioned regions was also detected. This study demonstrated high sensitivity of brush border length to the MPs and LCFA exposure, complementary to other tested sub-organismal biomarkers. Revealing the great potential of this histopathological biomarker in ecotoxicological studies contributes to the international standard ecotoxicology assessment of emerging pollutants.

In Situ Effects of a Microplastic Mixture on the Community Structure of Benthic Macroinvertebrates in a Freshwater Pond.

Benthic communities contain some of the most threatened organisms in aquatic habitats due to different anthropogenic pressures. The high abundance of microplastics in sediments will continue to increase in the future, further increasing the probability of interactions between macroinvertebrates and microplastics. In the present study, a benthic community in a relatively pristine shallow pond was exposed either to an environmentally relevant high concentration of a microplastic mixture of 80 g m-2 in the sediment, or a control sediment, without the addition of microplastics. The mixture of microplastics contained irregularly shaped polyethylene, polyvinyl chloride, and polyamide in a ratio of 50:25:25%, respectively. The in situ experiment lasted for 100 d. The total number of taxa that colonized the microcosms was 22 (17 in the control and 18 in the microplastic treatment), and the colonization was not affected by the treatment. The most dominant group within the macroinvertebrate community was the dipteran family Chironomidae, in both the control and the microplastic treatment. No significant differences in the abundance and biomass at a community level were recorded between the groups by permutational multivariate analysis of variance (F = 0.993, p = 0.456 and F = 0.344, p = 0.797, respectively). The mixture of microplastics did not influence the abundance or biomass of the functional feeding groups (F = 1.810, p = 0.137 and F = 0.377, p = 0.736, respectively). The species richness, species abundance, species biomass, Shannon's diversity index, and Simpson's index of diversity showed no statistically significant differences between the control and treatment groups. Czekanowski's quantitative similarity index indicated that 84% of the community remained unaffected after microplastic exposure. Environ Toxicol Chem 2022;41:888-895. © 2021 SETAC.

Changes in the wing shape and size in Drosophila melanogaster treated with food grade titanium dioxide nanoparticles (E171) - A multigenerational study.

Drosophila is among the most commonly used models for toxicity assessment of different types of nanoparticles. This study aims to examine the effects of a constant exposure to the low concentration of human food grade titanium dioxide nanoparticles (TiO2 E171) on Drosophila melanogaster wing morphology over multiple generations. Subsequently, the Geometric Morphometrics Analysis was employed to examine possible changes in the wing shape and size of the treated flies. The treatment resulted in the diminishment but not a disruption in the sexual dimorphism in wings. Consequently, the female flies were clearly separated from the male flies by the differences in wing morphology as in the control group. A splitting by generations was overly similar within the control and the treatment, but it was slightly more pronounced in the treatment. However, the observed generational differences seemed mostly random between generations, irrespective of the treatment. Specifically, the treated groups displayed slightly higher splitting by generations in females than in males. Regardless of the generation, the results show a clear splitting by the differences in the wing shape between the treated flies and the flies from control. The mean value of centroid size, which refers to the wing size, of both female and male wings was smaller in the treatment when compared to the control. The overall effect of TiO2 was to induce significant difference in Drosophila wing morphology but it did not alter the general wing morphology pattern. Therefore, the change in the wings occurred only within the normally allowed wing variation.

Can phytoplankton blooming be harmful to benthic organisms? The toxic influence of Anabaena sp. and Chlorella sp. on Chironomus riparius larvae.

Cyanobacteria and microalgae are abundant biota groups in eutrophic freshwater ecosystems, serving as a food source for many aquatic organisms, including the larvae of non-biting midges (Chironomidae). Many species of cyanobacteria are toxin producers, which can act as stressors to other organisms. The present study aimed to analyze and compare the effects of dietary exposure to the common toxic cyanobacteria Anabaena sp. and non-toxic microalgae Chlorella sp. in Chironomus riparius larvae. Microcystin was detected and quantified in the methanolic extract of Anabaena sp. using the HPLC-DAD technique, and it was identified as microcystin-LR. Both Anabaena sp. and Chlorella sp. were suitable food sources to enable the survival of C. riparius larvae in laboratory conditions, causing negligible mortality and significant differences in the larval mass (ANOVA and Post hoc LSD test; p < 0.05) and hemoglobin concentration (Student's t-test; p < 0.05). Oxidative stress parameters such as advanced oxidation protein products (AOPP), thiobarbituric acid reactive substances (TBARS), catalase (CAT) and superoxide dismutase (SOD) activity, and DNA damage, were also investigated. One-way ANOVA, followed by the Post hoc LSD test, showed a significant increase in AOPP and CAT for the group of larvae fed with Chlorella sp. The same test showed moderate DNA damage in both groups of larvae, with greater damage in the group fed with Anabaena sp. Thus, Chlorella sp. and microcystin-LR producing Anabaena sp. are food sources that did not result in any drastic acute effect on the population level of C. riparius larvae. However, sub-individual-level endpoints revealed significant effects of the treatments, since they caused oxidative stress and DNA damage that may pose a danger to successive generations of test organisms.

Application of deep learning in aquatic bioassessment: Towards automated identification of non-biting midges.

Morphological species identification is often a difficult, expensive, and time-consuming process which hinders the ability for reliable biomonitoring of aquatic ecosystems. An alternative approach is to automate the whole process, accelerating the identification process. Here, we demonstrate an automatic machine-based identification approach for non-biting midges (Diptera: Chironomidae) using Convolutional Neural Networks (CNNs) as a means of increasing taxonomic resolution of biomonitoring data at a minimal cost. Chironomidae were used to build the automatic identifier, as a family of insects that are abundant and ecologically important, yet difficult and time-consuming to accurately identify. The approach was tested with 10 morphologically very similar species from the same genus or subfamilies, comprising 1846 specimens from the South Morava river basin, Serbia. Three CNN models were built utilizing either species, genus, or subfamily data. After training the artificial neural network, images that the network had not seen during the training phase achieved an accuracy of 99.5% for species-level identification, while at the genus and subfamily level all images were correctly assigned (100% accuracy). Gradient-weighted Class Activation Mapping (Grad-CAM) visualized the mentum, ventromental plates, mandibles, submentum, and postoccipital margin to be morphologically important features for CNN classification. Thus, the CNN approach was a highly accurate solution for chironomid identification of aquatic macroinvertebrates opening a new avenue for implementation of artificial intelligence and deep learning methodology in the biomonitoring world. This approach also provides a means to overcome the gap in bioassessment for developing countries where widespread use techniques for routine monitoring are currently limited.

A Multiparametric Approach to Cerium Oxide Nanoparticle Toxicity Assessment in Non-Biting Midges.

Cerium oxide nanoparticles (CeO2 NPs) are included in the Organisation for Economic Co-operation and Development (OECD) priority list of engineered nanomaterials for assessment of their environmental impact. The present study was carried out to assess the CeO2 NP toxicity to the freshwater midge Chironomus riparius larvae at concentrations of 2.5, 25, 250, and 2500 mg of CeO2 NP/kg of sediment. Experiments were designed to assess the prolonged exposure of midges to CeO2 NPs while adhering to OECD test guideline 218. The following parameters were investigated: CeO2 NP uptake by larvae, oxidative stress parameters, in vivo genotoxic effects, and life trait parameters. Inductively coupled plasma-mass spectrometry analysis showed a significant positive correlation between the concentration of CeO2 NPs in the sediment and its uptake by the larvae. No significant mortality was observed in C. riparius, and oxidative stress was not detected. The only significantly induced sublethal effect was genotoxicity, which began to manifest at a lowest-observed-effect concentration of 25 mg kg-1 of sediment and progressively increased at higher concentrations. Our results indicate that exposure to CeO2 NP-contaminated freshwater sediments does not pose a risk to chironomids at environmentally realistic concentrations. However, the significant accumulation of CeO2 NPs by chironomid larvae may pose a risk through trophic transfer to organisms further up the food chain. Environ Toxicol Chem 2019;39:131-140. © 2019 SETAC.

An environmentally relevant concentration of titanium dioxide (TiO2) nanoparticles induces morphological changes in the mouthparts of Chironomus tentans.

The present study was carried out in order to assess the influence of environmentally relevant concentrations of TiO2 nanoparticles (E171 human food grade) toxicity on the freshwater midge Chironomus tentans. Tested concentrations were 125, 250, 500, 1000, 2000 and 4000 mg of E171 TiO2 per 1 kg of sediment, for the experiment aiming at life trait toxicity observation; and 2.5, 25 and 250 mg of E171 TiO2 per 1 kg of sediment for the experiment aiming at mouthpart deformity observation. The experimental design was constructed for the sediment dwelling chironomid larvae according to OECD guidelines. For the first time, a geometric morphometric approach was used to assess the deformities in chironomid larvae as sublethal implications of nanoparticle exposure. The present study showed a concentration-response relationship between the TiO2 concentration in the substrate and the TiO2 intake. The mortality and emergence ratio was affected at concentrations >1000 mg/kg. Geometric Morphometrics revealed the tendency of the mentum teeth to narrow and elongate and the mandibles to widen, as well as the loss of the first inner tooth, with a TiO2 concentration rise. The variability of morphological changes observed in the mouthparts indicates that C. tentans could be used as a bioindicator in nano-TiO2 monitoring.