Next generation insect taxonomic classification by comparing different deep learning algorithms.

Insect taxonomy lies at the heart of many aspects of ecology, and identification tasks are challenging due to the enormous inter- and intraspecies variation of insects. Conventional methods used to study insect taxonomy are often tedious, time-consuming, labor intensive, and expensive, and recently, computer vision with deep learning algorithms has offered an alternative way to identify and classify insect images into their taxonomic levels. We designed the classification task according to the taxonomic ranks of insects-order, family, and genus-and compared the generalization of four state-of-the-art deep convolutional neural network (DCNN) architectures. The results show that different taxonomic ranks require different deep learning (DL) algorithms to generate high-performance models, which indicates that the design of an automated systematic classification pipeline requires the integration of different algorithms. The InceptionV3 model has advantages over other models due to its high performance in distinguishing insect order and family, which is having F1-score of 0.75 and 0.79, respectively. Referring to the performance per class, Hemiptera (order), Rhiniidae (family), and Lucilia (genus) had the lowest performance, and we discuss the possible rationale and suggest future works to improve the generalization of a DL model for taxonomic rank classification.

Life History of Thalerosphyrus (Ephemeroptera: Heptageniidae) in Tropical Rivers with Reference to the Varying Altitude.

The life history and the influence of environmental parameters on Thalerosphyrus were investigated in two first-order rivers-the Batu Hampar River and the Teroi River of Gunung Jerai, Kedah-in northern peninsular Malaysia. Based on nymphal body length, Thalerosphyrus was found to be trivoltine in both rivers, regardless of the altitudinal difference, but its population abundance was four times higher in the Teroi River, presumably related to its better survival in the lower water temperature. At least nine instars of Thalerosphyrus were detected in the field-collected nymphs. Its life cycle was completed within 2.5-3.0 months, with overlapping cohorts and continual emergence of up to 3 months. The main driving factors of the high abundance of Thalerosphyrus were the water temperature and habitat quality.

Ecology of ephemeroptera, plecoptera and trichoptera (insecta) in rivers of the gunung jerai forest reserve: diversity and distribution of functional feeding groups.

A field study was performed to describe the functional feeding groups (FFGs) of Ephemeroptera, Plecoptera and Trichoptera (EPT) in the Tupah, Batu Hampar and Teroi Rivers in the Gunung Jerai Forest Reserve (GJFR), Kedah, Malaysia. Twenty-nine genera belonging to 19 families were identified. The EPTs were classified into five FFGs: collector-gatherers (CG), collector-filterers (CF), shredders (SH), scrapers (SC) and predators (P). In this study, CG and CF were the dominant groups inhabiting all three rivers. Ephemeroptera dominated these rivers due to their high abundance, and they were also the CG (90.6%). SC were the lowest in abundance among all groups. Based on the FFGs, the Teroi River was suitable for CG, whereas the Tupah and Batu Hampar Rivers were suitable for CG and CF. The distribution of FFGs differed among the rivers (CG, χ(2) = 23.6, p = 0.00; SH, χ(2) = 10.02, p = 0.007; P, χ(2) = 25.54, p = 0.00; CF, χ(2) = 21.95, p = 0.00; SC, χ(2) = 9.31, p = 0.01). These findings indicated that the FFGs found in rivers of the GJFR represent high river quality.