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
The Antarctic environment has special characteristics that influence the local marine life. The benthic organisms, adapted to these extreme conditions of life, are subject nowadays to effects of climate change. Recently, the consequences of glacier retreat on these assemblages have been observed in many West Antarctic Peninsula (WAP) regions, including King George Island (KGI). This study described the spatial variation of the benthic macrofauna in different areas of the Martel Inlet (Admiralty Bay - KGI), at depths around 25-30 m. Sampling was done in January 2001 at ten stations classified in localities according to their proximity to ice-margin/coastline in marine-terminating glacier (MTG), terrestrial-terminating glacier (TTG) and ice-free area (IFA). The total density and the abundance of annelids, nematodes, peracarid crustaceans and bivalves were higher at IFA stations. The locality discrimination by taxa and species was independent of available environmental/sedimentary conditions or was the result of unmeasured variables or species life history processes not assessed herein. Considering that our findings were obtained 21 years ago, they will be especially useful for comparing future studies of benthic assemblage responses to the influence of climate change and continuous glacier retreats in the WAP region.
Assuntos
Ecossistema , Nematoides , Animais , Baías , Regiões Antárticas , Camada de GeloRESUMO
Activities at the Brazilian Antarctic Station (EACF) may cause damage to surrounding environment. Meiofauna was used to evaluate this impact. One area possibly impacted by the stations' presence (CF) and a reference area (BP) were compared. Sediment samples for meiofauna and environmental variables were obtained in two periods, at two sites and depths in each area. Densities were higher at 20-30m and nematodes were the dominant taxa (90%). Nematode densities ranged from 1,278±599 (BP1 50-60m) to 16,021±12,298 ind.10 cm-² (BP2 20-30m). A total of 68 genera were found. Sample richness ranged from 8 to 26 and diversity from 1.4 to 3.6 bits/ind, both being higher at BP 50-60m, where dominance of epistrate feeders was lower. Selective and non-selective deposit feeders were codominant with similar proportions. Maturity index was high and constant between samples. Aponema, Sabatieria, Daptonema, Dichromadora and Halalaimus were dominant, with higher densities at 20-30m. In contrast, Actinonema, Molgolaimus, Oxystomina and Marylynnia were more abundant at 50-60m. Differences in meiofauna community were found mainly between depths, but not between sites or periods, suggesting no anthropogenic impact. Nevertheless, lower Nematoda diversities and maturity index at 50-60m in CF when compared to BP may indicate a possible anthropogenic effect near EACF.