International Journal of Molecular Evolution and Biodiversity 2024, Vol.14, No.5, 208-218 http://ecoevopublisher.com/index.php/ijmeb 213 Additionally, the phylogenomic study of Aphididae subfamilies highlights the impact of gene tree discordance and introgression events on aphid classification (Owen and Miller, 2022). The research suggests that environmental factors, such as geographical barriers and ecological niches, have influenced the genetic makeup and evolutionary history of aphids. These factors must be considered when developing taxonomic frameworks to ensure they accurately reflect the evolutionary relationships and ecological adaptations of aphids. 6 Advances in Digital Taxonomy and Image-Based Tools 6.1 Use of artificial intelligence in aphid identification The integration of artificial intelligence (AI) into aphid identification has revolutionized the field of entomology, particularly in the monitoring and management of aphid populations. AI techniques, such as machine learning and image recognition, have been employed to address the challenges associated with manual identification, which is often time-consuming and requires a high level of taxonomic expertise. For instance, the use of convolutional neural networks (CNNs) has shown significant promise in automating the identification process, thereby reducing the bottleneck in specimen processing (Júnior and Rieder, 2020). These AI-driven methods not only enhance the accuracy of identification but also allow for the processing of large datasets, which is crucial for long-term monitoring and forecasting of aphid populations (Batz et al., 2023). Moreover, AI applications extend beyond mere identification. They are instrumental in developing predictive models that can forecast aphid abundance and the associated risks of plant virus transmission. This is particularly important in the context of climate change, which influences aphid population dynamics and peak occurrences. The potential of AI in aphid identification and monitoring underscores the need for continued research and development in this area, as it offers a scalable and efficient solution to the challenges posed by traditional taxonomic methods. 6.2 Development of digital databases and keys The creation of digital databases and identification keys represents a significant advancement in the field of aphid taxonomy. These tools facilitate the accurate and efficient identification of aphid species, which is essential for effective pest management and biodiversity studies. One notable example is the development of a web-based digital key for the identification of Neuroptera in West Bengal, India. This digital key, accessible via the platform www.lacewingsofwestbengal.in, exemplifies how region-specific databases can be utilized to create user-friendly identification tools (Dutta et al., 2023). Digital databases also play a crucial role in the global taxonomic community by providing centralized repositories of taxonomic information. The PhylAphidB@se website, for instance, offers a comprehensive database of DNA barcodes for European aphids, enabling researchers to identify species based on genetic data (D’acier et al., 2014). Such databases not only streamline the identification process but also support large-scale taxonomic projects by providing access to a wealth of information that can be used for comparative studies and biodiversity assessments. 6.3 Remote sensing and automated classification systems Remote sensing and automated classification systems have emerged as powerful tools in the field of aphid taxonomy. These technologies enable the monitoring of aphid populations over large geographic areas and extended periods, providing valuable data for ecological and agricultural studies. Automated classification systems, which utilize computer vision and machine learning algorithms, have been developed to count and classify aphids from digital images. These systems offer a reliable and efficient alternative to manual counting, which is often labor-intensive and prone to errors (Lins et al., 2020). The use of remote sensing technologies, such as suction traps combined with automated image analysis, allows for the continuous monitoring of aphid populations without the need for constant human intervention. This approach not only improves the accuracy of population estimates but also provides real-time data that can be used to inform pest management strategies (Batz et al., 2023). The integration of remote sensing and automated classification systems represents a significant advancement in the field, offering new opportunities for large-scale and long-term monitoring of aphid populations.
RkJQdWJsaXNoZXIy MjQ4ODYzNA==