RESUMEN
Varroa mites, scientifically identified as Varroa destructor, pose a significant threat to beekeeping and cause one of the most destructive diseases affecting honey bee populations. These parasites attach to bees, feeding on their fat tissue, weakening their immune systems, reducing their lifespans, and even causing colony collapse. They also feed during the pre-imaginal stages of the honey bee in brood cells. Given the critical role of honey bees in pollination and the global food supply, controlling Varroa mites is imperative. One of the most common methods used to evaluate the level of Varroa mite infestation in a bee colony is to count all the mites that fall onto sticky boards placed at the bottom of a colony. However, this is usually a manual process that takes a considerable amount of time. This work proposes a deep learning approach for locating and counting Varroa mites using images of the sticky boards taken by smartphone cameras. To this end, a new realistic dataset has been built: it includes images containing numerous artifacts and blurred parts, which makes the task challenging. After testing various architectures (mainly based on two-stage detectors with feature pyramid networks), combination of hyperparameters and some image enhancement techniques, we have obtained a system that achieves a mean average precision (mAP) metric of 0.9073 on the validation set.
Asunto(s)
Aprendizaje Profundo , Programas Informáticos , Varroidae , Animales , Varroidae/patogenicidad , Varroidae/fisiología , Abejas/parasitología , Abejas/fisiología , Infestaciones por Ácaros/parasitología , Apicultura/métodos , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
Different types of measuring errors can increase the uncertainty of solar radiation measurements, but most common quality control (QC) methods do not detect frequent defects such as shading or calibration errors due to their low magnitude. We recently presented a new procedure, the Bias-based Quality Control (BQC), that detects low-magnitude defects by analyzing the stability of the deviations between several independent radiation databases and measurements. In this study, we extend the validation of the BQC by analyzing the quality of all publicly available Spanish radiometric networks measuring global horizontal irradiance (9 networks, 732 stations). Similarly to our previous validation, the BQC found many defects such as shading, soiling, or calibration issues not detected by classical QC methods. The results questioned the quality of SIAR, Euskalmet, MeteoGalica, and SOS Rioja, as all of them presented defects in more than 40% of their stations. Those studies based on these networks should be interpreted cautiously. In contrast, the number of defects was below a 5% in BSRN, AEMET, MeteoNavarra, Meteocat, and SIAR Rioja, though the presence of defects in networks such as AEMET highlights the importance of QC even when using a priori reliable stations.