Automatic acoustic recognition of pollinating bee species can be highly improved by Deep Learning models accompanied by pre-training and strong data augmentation

Abstract

IntroductionBees capable of performing floral sonication (or buzz-pollination) are among the most effective pollinators of blueberries. However, the quality of pollination provided varies greatly among species visiting the flowers. Consequently, the correct identification of flower visitors becomes indispensable to distinguishing the most efficient pollinators of blueberry. However, taxonomic identification normally depends on microscopic characteristics and the active participation of experts in the decision-making process. Moreover, the many species of bees (20,507 worldwide) and other insects are a challenge for a decreasing number of insect taxonomists. To overcome the limitations of traditional taxonomy, automatic classification systems of insects based on Machine-Learning (ML) have been raised for detecting and distinguishing a wide variety of bioacoustic signals, including bee buzzing sounds. Despite that, classical ML algorithms fed by spectrogram-type data only reached marginal performance for bee ID recognition. On the other hand, emerging systems from Deep Learning (DL), especially Convolutional Neural Networks (CNNs), have provided a substantial boost to classification performance in other audio domains, but have yet to be tested for acoustic bee species recognition tasks. Therefore, we aimed to automatically identify blueberry pollinating bee species based on characteristics of their buzzing sounds using DL algorithms.MethodsWe designed CNN models combined with Log Mel-Spectrogram representations and strong data augmentation and compared their performance at recognizing blueberry pollinating bee species with the current state-of-the-art models for automatic recognition of bee species.Results and DiscussionWe found that CNN models performed better at assigning bee buzzing sounds to their respective taxa than expected by chance. However, CNN models were highly dependent on acoustic data pre-training and data augmentation to outperform classical ML classifiers in recognizing bee buzzing sounds. Under these conditions, the CNN models could lead to automating the taxonomic recognition of flower-visiting bees of blueberry crops. However, there is still room to improve the performance of CNN models by focusing on recording samples for poorly represented bee species. Automatic acoustic recognition associated with the degree of efficiency of a bee species to pollinate a particular crop would result in a comprehensive and powerful tool for recognizing those that best pollinate and increase fruit yields.

Towards acoustic monitoring of bees: wingbeat sounds are related to species and individual traits

“…It is also important to highlight that our study, which aimed to distinguish Apis mellifera from other wild bee species, employed handcrafted features owing to the availability of samples. While our Random Forestbased models demonstrated commendable classification performance, we acknowledge the existence of more advanced methods, particularly the use of deep learning models for classifying bee species based on wingbeat sounds [45,71]. These advanced methods have demonstrated highly accurate classification results, especially when provided with a larger dataset.…”

Artificial neuronal networks are revolutionizing entomological research

“…By analysing the unique sounds made by different species (Ferreira et al., 2023), AI algorithms can accurately identify and classify most of them even in the presence of moderate background noise (Ashurov et al., 2022; Høye et al., 2021). For example, Santiago et al.…”

“…This is useful in identifying and classifying species that are difficult to observe visually, such as nocturnal insects or those that are too small to be easily seen. By analysing the unique sounds made by different species (Ferreira et al, 2023), AI algorithms can accurately identify and classify most of them even in the presence of moderate background noise (Ashurov et al, 2022;Høye et al, 2021). For example, Santiago et al ( 2017) described the sound-based detection of pests in stored grains using an ANN that analyses the MFCCs for sound classification.…”

Extensive data engineering to the rescue: building a multi-species katydid detector from unbalanced, atypical training datasets

“…Though often not as pronounced, domain mismatch problems are commonly encountered in bioacoustic ML, across various taxa including insects (e.g. [ 34 , 35 ]), birds (e.g. [ 36 , 37 ]) and marine fauna (e.g.…”