RESUMO
Background: Identifying species, particularly small metazoans, remains a daunting challenge and the phylum Nematoda is no exception. Typically, nematode species are differentiated based on morphometry and the presence or absence of certain characters. However, recent advances in artificial intelligence, particularly machine learning (ML) algorithms, offer promising solutions for automating species identification, mostly in taxonomically complex groups. By training ML models with extensive datasets of accurately identified specimens, the models can learn to recognize patterns in nematodes' morphological and morphometric features. This enables them to make precise identifications of newly encountered individuals. Implementing ML algorithms can improve the speed and accuracy of species identification and allow researchers to efficiently process vast amounts of data. Furthermore, it empowers non-taxonomists to make reliable identifications. The objective of this study is to evaluate the performance of ML algorithms in identifying species of free-living marine nematodes, focusing on two well-known genera: Acantholaimus Allgén, 1933 and Sabatieria Rouville, 1903. Methods: A total of 40 species of Acantholaimus and 60 species of Sabatieria were considered. The measurements and identifications were obtained from the original publications of species for both genera, this compilation included information regarding the presence or absence of specific characters, as well as morphometric data. To assess the performance of the species identification four ML algorithms were employed: Random Forest (RF), Stochastic Gradient Boosting (SGBoost), Support Vector Machine (SVM) with both linear and radial kernels, and K-nearest neighbor (KNN) algorithms. Results: For both genera, the random forest (RF) algorithm demonstrated the highest accuracy in correctly classifying specimens into their respective species, achieving an accuracy rate of 93% for Acantholaimus and 100% for Sabatieria, only a single individual from Acantholaimus of the test data was misclassified. Conclusion: These results highlight the overall effectiveness of ML algorithms in species identification. Moreover, it demonstrates that the identification of marine nematodes can be automated, optimizing biodiversity and ecological studies, as well as turning species identification more accessible, efficient, and scalable. Ultimately it will contribute to our understanding and conservation of biodiversity.
Assuntos
Inteligência Artificial , Nematoides , Humanos , Animais , Algoritmos , Aprendizado de Máquina , CromadoriaRESUMO
Interactive effects of trace metal contamination, ocean warming, and CO2-driven acidification on the structure of a meiofaunal benthic community was assessed. Meiofauna microcosm bioassays were carried out in controlled conditions in a full factorial experimental design which included three fixed factors: metal contamination in the sediment (3 levels of a mixture of Cu, Pb, Zn, and Hg), temperature (26 and 28 °C) and pH (7.6 and 8.1). Metal contamination caused a sharp decrease in the densities of the most abundant meiobenthic groups and interacted with temperature rise, exacerbating deleterious effects for Nematoda and Copepoda, but mitigating effects for Acoelomorpha. CO2-driven acidification resulted in increased acoelomorphs density, but only in sediments with lower levels of metals. Copepod densities, in turn, were lower in the CO2-driven acidification scenario regardless of contamination or temperature. The results obtained in the present study showed that temperature rise and CO2-driven acidification of coastal ocean waters, at environmentally relevant levels, interacts with trace metals in marine sediments, differently affecting the major groups of benthic biota.
Assuntos
Nematoides , Oligoelementos , Animais , Dióxido de Carbono , Concentração de Íons de Hidrogênio , Metais/toxicidade , Oceanos e Mares , Sedimentos Geológicos/químicaRESUMO
Natural pH values in coastal waters vary largely among locations, ecosystems, and time periods; still, there is an ongoing acidification trend. In this scenario, more acidic pH values can alter bioavailability of organic contaminants, to organisms. Despite this, interactive effects between pH and chemical substances are not usually considered in Ecological Risk Assessment protocols. This study investigated the effects of pH on the toxicity of a hydrophobic organic compound on a benthic community using a microcosm experiment setup to assess the response of nematode assemblages exposed to environmentally relevant concentrations of Irgarol at two natural pH conditions. Estuarine nematode assemblages were exposed to two concentrations of Irgarol at pH 7.0 and 8.0 for periods of 7 and 35 days. Lower diversity of nematode genera was observed at the highest tested Irgarol concentration (1281 ± 65 ng.g-1). The results showed that the effects of Irgarol contamination were independent of pH variation, indicating no influence of acidification within this range on the toxicity of Irgarol to benthic meiofauna. However, the results showed that estuarine nematode assemblages are impacted by long-term exposure to low (but naturally occurring) pHs. This indicates that estuarine organisms may be under naturally high physiological pressure and that permanent changes in the ecosystem's environmental factors, such as future coastal ocean acidification, may drive organisms closer to the edges of their tolerance windows.
Assuntos
Nematoides , Poluentes Químicos da Água , Animais , Ecossistema , Monitoramento Ambiental , Concentração de Íons de Hidrogênio , Água do Mar , Triazinas/análise , Poluentes Químicos da Água/análise , Poluentes Químicos da Água/toxicidadeRESUMO
The usual approaches used in ecological risk assessment have been based on individual and population level standard procedures. Although these have been important tools to assess adverse effects on ecosystems, they are generally simplified and therefore lack ecological realism. Microcosm studies using meiobenthic communities offer a good compromise between the complexity of the ecosystem and the often highly artificial settings of laboratory experiments. An experiment was designed to investigate the potential of the microcosm approach using meiofauna as a tool for ecotoxicological studies. The experiment tested the ecological effects of exposure to sewage-impacted pore water simultaneously at the community level using meiofauna microcosms and at the individual level using laboratory fecundity tests with the copepod Nitokra sp. Specifically, the experiment tested the toxicity of pore water from three sites according to a contamination gradient. Both approaches were efficient in detecting differences in toxicity between the less and more contaminated sites. However, only multivariate data from community analysis detected differences in the gradient of contamination. In addition to information about toxicity, the community level microcosm experiment gave indications about sensitive and tolerant species, indirect ecological effects, as well as raised hypothesis about contamination routes and bioavailability to be tested. Considering the importance of meiofauna for benthic ecosystems, the microcosm approach using natural meiobenthic communities might be a valuable addition as a higher tier approach in ecological risk assessment, providing highly relevant ecological information on the toxicity of contaminated sediments.
Assuntos
Copépodes/efeitos dos fármacos , Ecotoxicologia/métodos , Monitoramento Ambiental/métodos , Sedimentos Geológicos/microbiologia , Poluentes Químicos da Água/toxicidade , Animais , Brasil , Ecologia , Ecossistema , Sedimentos Geológicos/análise , Medição de RiscoRESUMO
The present study investigates the effects of drill cutting discharges on the structure of meiofauna communities in an area of the shelf break at Campos Basin, Southeast Brazil. Drilling activities were operated, in a first phase, with water-based fluid and, in a second phase, with synthetic fluid paraffin-based (NAF-III). A total of 135 samples taken at a pre-drilling situation (MS1) and two post-drilling moments (MS2 and MS3-3 and 22 months post-drilling, respectively) were analyzed. Effects on meiofauna were dependent on two main factors: 1-the impact received during drilling operation, if water-based or synthetic/water-based drilling fluid and 2-the background state, if it already presented signs of previous drilling activities or not. Based on univariate and multivariate analysis, there were evidences that the most affected area after drilling was those under the influence of synthetic-based fluid and that already had signs of previous drillings activities. The region impacted only by water-based fluid was less affected and the only one that completely recovered after 22 months. Nematodes and copepods had different responses to the impact. While copepods flourish in the impacted area and recovered 22 months after drilling, nematodes were adversely affected shortly after drilling and the community structure only recovered where hydrocarbons had been depleted.