Utilizing CNNs for classification and uncertainty quantification for 15 families of European fly pollinators

Abstract

Pollination is essential for maintaining biodiversity and ensuring food security, and in Europe it is primarily mediated by four insect orders (Coleoptera, Diptera, Hymenoptera, Lepidoptera). However, traditional monitoring methods are costly and time consuming. Although recent automation efforts have focused on butterflies and bees, flies, a diverse and ecologically important group of pollinators, have received comparatively little attention, likely due to the challenges posed by their subtle morphological differences. In this study, we investigate the application of Convolutional Neural Networks (CNNs) for classifying 15 European pollinating fly families and quantifying the associated classification uncertainty. Our dataset comprises a wide range of morphological and phylogenetic features, such as wing venation patterns and wing shapes. We evaluated the performance of three state-of-the-art CNN architectures, ResNet18, MobileNetV3, and EfficientNetB4, and demonstrate their effectiveness in accurately distinguishing fly families. In particular, EfficientNetB4 achieved an overall accuracy of up to 95.61%. Furthermore, cropping images to the bounding boxes of the Diptera not only improved classification accuracy but also increased prediction confidence, reducing misclassifications among families. This approach represents a significant advance in automated pollinator monitoring and has promising implications for both scientific research and practical applications.