Dailinfei Xia

MSc Student (2025)

Project Title: AI-driven identification of beetle collections, combining machine learning tools with morphological analysis to accelerate identification and curation

Research Focus: Dailinfei’s MSc research focuses on developing artificial intelligence approaches for the identification of beetle specimens in museum collections. The project combines cutting-edge machine learning techniques with traditional morphological analysis to create tools that can accelerate specimen identification and improve curation workflows in natural history museums.

Key Research Areas:

• Machine learning for taxonomic identification
• Beetle (Coleoptera) systematics
• Computer vision applications
• Museum collection management
• Morphological analysis automation
• Digital curation workflows

Research Significance: Beetles represent the most diverse group of animals on Earth, comprising approximately 25% of all known species. Their identification often requires significant taxonomic expertise, making them an ideal test case for AI-assisted identification systems. This research aims to address the taxonomic impediment by providing tools that can support both expert taxonomists and non-specialists.

Methodological Approach: The project combines multiple approaches including image-based machine learning, morphometric analysis, and integration with existing taxonomic databases to create robust identification systems that can handle the vast morphological diversity within Coleoptera.