Search for: All records

Abstract Pollen identification is necessary for several subfields of geology, ecology, and evolutionary biology. However, the existing methods for pollen identification are laborious, time-consuming, and require highly skilled scientists. Therefore, there is a pressing need for an automated and accurate system for pollen identification, which can be beneficial for both basic research and applied issues such as identifying airborne allergens. In this study, we propose a deep learning (DL) approach to classify pollen grains in the Great Basin Desert, Nevada, USA. Our dataset consisted of 10,000 images of 40 pollen species. To mitigate the limitations imposed by the small volume of our training dataset, we conducted an in-depth comparative analysis of numerous pre-trained Convolutional Neural Network (CNN) architectures utilizing transfer learning methodologies. Simultaneously, we developed and incorporated an innovative CNN model, serving to augment our exploration and optimization of data modeling strategies. We applied different architectures of well-known pre-trained deep CNN models, including AlexNet, VGG-16, MobileNet-V2, ResNet (18, 34, and 50, 101), ResNeSt (50, 101), SE-ResNeXt, and Vision Transformer (ViT), to uncover the most promising modeling approach for the classification of pollen grains in the Great Basin. To evaluate the performance of the pre-trained deep CNN models, we measured accuracy, precision, F1-Score, and recall. Our results showed that the ResNeSt-110 model achieved the best performance, with an accuracy of 97.24%, precision of 97.89%, F1-Score of 96.86%, and recall of 97.13%. Our results also revealed that transfer learning models can deliver better and faster image classification results compared to traditional CNN models built from scratch. The proposed method can potentially benefit various fields that rely on efficient pollen identification. This study demonstrates that DL approaches can improve the accuracy and efficiency of pollen identification, and it provides a foundation for further research in the field. 

Abstract Many species distribution maps indicate the ranges of Aedes aegypti (Linnaeus) and Aedes albopictus (Skuse) overlap in Florida despite the well-documented range reduction of Ae. aegypti. Within the last 30 yr, competitive displacement of Ae. aegypti by Ae. albopictus has resulted in partial spatial segregation of the two species, with Ae. aegypti persisting primarily in urban refugia. We modeled fine-scale distributions of both species, with the goal of capturing the outcome of interspecific competition across space by building habitat suitability maps. We empirically parameterized models by sampling 59 sites in south and central Florida over time and incorporated climatic, landscape, and human population data to identify predictors of habitat suitability for both species. Our results show human density, precipitation, and urban land cover drive Ae. aegypti habitat suitability, compared with exclusively climatic variables driving Ae. albopictus habitat suitability. Remotely sensed variables (macrohabitat) were more predictive than locally collected metrics (microhabitat), although recorded minimum daily temperature showed significant, inverse relationships with both species. We detected minor Aedes habitat segregation; some periurban areas that were highly suitable for Ae. albopictus were unsuitable for Ae. aegypti. Fine-scale empirical models like those presented here have the potential for precise risk assessment and the improvement of operational applications to control container-breeding Aedes mosquitoes.