RESUMO
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.
Assuntos
Anfípodes , Inteligência Artificial , Humanos , Animais , Ecossistema , Software , Qualidade da ÁguaRESUMO
RESUMEN Los lagos altoandinos son ecosistemas afectados por múltiples presiones antrópicas que alteran la calidad del agua y las comunidades bióticas, siendo los macroinvertebrados acuáticos excelentes bioindicadores para estos ecosistemas. El presente trabajo analiza la dinámica de la comunidad de macroinvertebrados asociada a Egeria densa, la relación con las variables fisicoquímicas, los índices bióticos y la interacción predador-presa en el litoral del Lago de Tota. Este trabajo se desarrolló en tres campañas sobre nueve estaciones de muestreo en el perímetro del lago. Dentro de los hallazgos, Hyallela sp. (30 %) y Dicrotendipes sp.(27 %) son los taxones más abundantes y dominantes del estudio, siendo bioindicadores de presencia de materia orgánica en descomposición y disminución en la calidad del agua. El análisis ANOVA de las variables fisicoquímicas del agua y los nutrientes de Egeria densa mostró diferencias significativas a nivel temporal. Los índices bióticos mostraron diferencias en la calidad del agua, determinando una posible zonificación de este parámetro en el litoral. Finalmente, para identificar las relaciones de la comunidad, se presenta un modelo predador-presa, con Hyalella sp. como presa e Ischnura sp. como predador a través de las ecuaciones Lotka-Volterra, encontrando que hay concordancia entre el comportamiento de las abundancias medidas y las simuladas. De esta forma, la dinámica trófica contribuye a entender las comunidades y su proyección en el tiempo con relación a las condiciones ambientales de la zona litoral.
ABSTRACT High Andean lakes are ecosystems affected by multiple anthropogenic pressures that alter water quality and biotic communities, and aquatic macroinvertebrates are excellent bioindicators for these ecosystems. The present work analyzes the dynamics of the macroinvertebrate community associated with Egeria densa, the relationship with physicochemical variables, biotic indices, and predator-prey interaction in the littoral of Lake Tota. This work was developed in three campaigns on nine sampling stations on the perimeter of the lake. Among the findings, Hyallela sp. (30 %) and Dicrotendipes sp. (27 %) are the most abundant and dominant taxa of the study, being bioindicators of the presence of decomposing organic matter and decrease in water quality. ANOVA analysis of the physicochemical variables of water and nutrients of Egeria densa showed significant differences at the temporal level. The biotic indices showed differences in water quality, determining a possible zoning of this parameter along the coast. Finally, to identify community relationships, a predator-prey model is presented, with Hyalella sp. as prey and Ischnura sp. as predator through the Lotka-Volterra equations, finding that there is agreement between the behavior of measured and simulated abundances. In this way, the trophic dynamics contribute to understand the communities and their projection in time in relation to the environmental conditions of the littoral zone.