RESUMO
BACKGROUND: Identifying mosquito vectors is crucial for controlling diseases. Automated identification studies using the convolutional neural network (CNN) have been conducted for some urban mosquito vectors but not yet for sylvatic mosquito vectors that transmit the yellow fever. We evaluated the ability of the AlexNet CNN to identify four mosquito species: Aedes serratus, Aedes scapularis, Haemagogus leucocelaenus and Sabethes albiprivus and whether there is variation in AlexNet's ability to classify mosquitoes based on pictures of four different body regions. METHODS: The specimens were photographed using a cell phone connected to a stereoscope. Photographs were taken of the full-body, pronotum and lateral view of the thorax, which were pre-processed to train the AlexNet algorithm. The evaluation was based on the confusion matrix, the accuracy (ten pseudo-replicates) and the confidence interval for each experiment. RESULTS: Our study found that the AlexNet can accurately identify mosquito pictures of the genus Aedes, Sabethes and Haemagogus with over 90% accuracy. Furthermore, the algorithm performance did not change according to the body regions submitted. It is worth noting that the state of preservation of the mosquitoes, which were often damaged, may have affected the network's ability to differentiate between these species and thus accuracy rates could have been even higher. CONCLUSIONS: Our results support the idea of applying CNNs for artificial intelligence (AI)-driven identification of mosquito vectors of tropical diseases. This approach can potentially be used in the surveillance of yellow fever vectors by health services and the population as well.
Assuntos
Aedes , Mosquitos Vetores , Redes Neurais de Computação , Febre Amarela , Animais , Mosquitos Vetores/classificação , Febre Amarela/transmissão , Aedes/classificação , Aedes/fisiologia , Algoritmos , Processamento de Imagem Assistida por Computador/métodos , Culicidae/classificação , Inteligência ArtificialRESUMO
Litterfall is the main source of dry deposition of mercury (Hg) into the soil in forest ecosystems. The accumulation of Hg in soil and litter suggests the possibility of transfer to terrestrial invertebrates through environmental exposure or ingestion of plant tissues. We quantified total mercury (THg) concentrations in two soil layers (organic: 0-0.2 m; mineral: 0.8-1 m), litter, fresh leaves, and terrestrial invertebrates of the Araguaia River floodplain, aiming to evaluate the THg distribution among terrestrial compartments, bioaccumulation in invertebrates, and the factors influencing THg concentrations in soil and invertebrates. The mean THg concentrations were significantly different between the compartments evaluated, being higher in organic soil compared to mineral soil, and higher in litter compared to mineral soil and fresh leaves. Soil organic matter content was positively related to THg concentration in this compartment. The order Araneae showed significantly higher Hg concentrations among the most abundant invertebrate taxa. The higher Hg concentrations in Araneae were positively influenced by the concentrations determined in litter and individuals of the order Hymenoptera, confirming the process of biomagnification in the terrestrial trophic chain. In contrast, the THg concentrations in Coleoptera, Orthoptera and Hymenoptera were not significantly related to the concentrations determined in the soil, litter and fresh leaves. Our results showed the importance of organic matter for the immobilization of THg in the soil and indicated the process of biomagnification in the terrestrial food web, providing insights for future studies on the environmental distribution of Hg in floodplains.
Assuntos
Bioacumulação , Monitoramento Ambiental , Invertebrados , Mercúrio , Rios , Mercúrio/análise , Mercúrio/metabolismo , Brasil , Animais , Rios/química , Invertebrados/metabolismo , Poluentes do Solo/análise , Poluentes do Solo/metabolismo , Pradaria , Cadeia Alimentar , Ecossistema , Solo/químicaRESUMO
Mercury (Hg) is a chemical element that, depending on its concentration, may become toxic to living organisms due to the ability of Hg to bioaccumulate in food chains. In this study, we collected samples of soil, litter, and organisms in the Middle Araguaia floodplain, Brazil. Total mercury (THg) concentrations in litter were significantly higher (p < 0.0001) than that in soil, ranging from 10.68 ± 0.55 to 48.94 ± 0.13 and 20.80 ± 1.07 to 55 .19 ± 1.59 ng g-1, respectively. Total mercury concentration levels in soil showed a linear, inversely proportional relationship with soil organic matter (SOM) contents and soil pH, consistent with the geochemical behavior of chemical elements in flooded environments. Ten orders of organisms were identified, and the average THg concentrations determined in their bodies were up to 20 times higher than those in soil and litter. We found a significant linear relationship between the levels of THg in litter and those found in soil organisms, thereby allowing the prediction of THg concentration levels in soil organisms through the analysis of litter at the sample units. The different dynamics and feeding habits of soil organisms and the concentration of THg in these organisms may be influenced by the river's course. This study provides evidence of the bioaccumulation of THg in soil organisms in the floodplain of the Middle Araguaia River, an important river basin in the Brazilian savanna.