Browsing by Author "Allen, Julie M."

Now showing 1 - 2 of 2
  • Thumbnail Image
    Changes in parrot diversity after human arrival to the Caribbean
    Oswald, Jessica A.; Smith, Brian Tilston; Allen, Julie M.; Guralnick, Robert P.; Steadman, David W.; LeFebvre, Michelle J. (National Academy of Science, 2023-09-23)
    Humans did not arrive on most of the world’s islands until relatively recently, making islands favorable places for disentangling the timing and magnitude of natural and anthropogenic impacts on species diversity and distributions. Here, we focus on Amazona parrots in the Caribbean, which have close relationships with humans (e.g., as pets as well as sources of meat and colorful feathers). Caribbean parrots also have substantial fossil and archaeological records that span the Holocene. We leverage this exemplary record to showcase how combining ancient and modern DNA, along with radiometric dating, can shed light on diversification and extinction dynamics and answer long-standing questions about the magnitude of human impacts in the region. Our results reveal a striking loss of parrot diversity, much of which took place during human occupation of the islands. The most widespread species, the Cuban Parrot, exhibits interisland divergences throughout the Pleistocene. Within this radiation, we identified an extinct, genetically distinct lineage that survived on the Turks and Caicos until Indigenous human settlement of the islands. We also found that the narrowly distributed Hispaniolan Parrot had a natural range that once included The Bahamas; it thus became “endemic” to Hispaniola during the late Holocene. The Hispaniolan Parrot also likely was introduced by Indigenous people to Grand Turk and Montserrat, two islands where it is now also extirpated. Our research demonstrates that genetic information spanning paleontological, archaeological, and modern contexts is essential to understand the role of humans in altering the diversity and distribution of biota.
  • Thumbnail Image
    Efficient pollen grain classification using pre-trained Convolutional Neural Networks: a comprehensive study
    Rostami, Masoud A.; Balmaki, Behnaz; Dyer, Lee A.; Allen, Julie M.; Sallam, Mohamed F.; Frontalini, Fabrizio (2023-10-01)
    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.