# AntID_APP: Empowering Citizen Scientists with YOLO Models for Ant Identification in Taiwan

## TL;DR

AntID_APP is a web app that uses AI to help citizen scientists in Taiwan quickly identify native ant species from photos, improving biodiversity monitoring.

## Contribution

The novel contribution is a web application using fine-tuned YOLO models for real-time, genus-level ant identification in user-submitted images.

## Key findings

- The AntID_APP achieved high detection accuracy (mAP50: 0.935–0.948) using fine-tuned YOLO models trained on 60,429 open-access ant images.
- The app enables efficient genus-level ant identification with an intuitive interface and lightweight server architecture.
- Blurred images and busy backgrounds can reduce accuracy, highlighting the need for careful model adjustments and interdisciplinary collaboration.

## Abstract

Identifying ants is crucial for tracking environmental health, but traditional identification methods require specialized experts and significant time. This makes it difficult for the public to gather ecological data. To address this, we developed a web application to help citizen scientists in Taiwan to instantly identify native ant groups using their photographs. Here, we trained advanced artificial intelligence computer programs on over sixty thousand public images, and our results show that the system can highly accurately locate and identify ants in everyday pictures. However, we also discovered that blurry photos, busy backgrounds, and natural physical differences among ants of the same group can sometimes confuse the program. Regardless, building this tool demonstrated that artificial intelligence is a powerful aid for identifying species, but it still requires careful adjustments for different types of animals and close teamwork between computer scientists and biologists. This accessible tool empowers anyone to participate in scientific research, making large-scale environmental monitoring faster and easier. Ultimately, combining modern technology with public participation will improve how society tracks biodiversity and protects natural ecosystems.

Ants are vital bioindicators that contribute to soil health and food webs, making accurate identification essential for biodiversity monitoring and conservation. However, traditional taxonomic methods are time-consuming and require specialized expertise, limiting large-scale data collection and public participation. This paper presents AntID_APP, a web-based application designed to support citizen scientists in Taiwan by enabling real-time, image-based detection and the identification of native ant genera. Fine-tuned YOLO models first detect ants in user-uploaded images and then classify them at the genus level. The models were trained on a curated dataset of 60,429 open-access images from iNaturalist, covering 54 native ant species. To ensure robustness in real-world conditions, we applied targeted data augmentation and evaluated multiple YOLO versions (v9–v12). The best-performing model achieved a mean Average Precision (mAP50: 0.935–0.948, mAP50-95: 0.777–0.807) for the detection task, followed by accurate genus-level identification. The application features an intuitive interface and a lightweight asynchronous server architecture, allowing users to upload images and receive both visual detection results (bounding boxes) and genus predictions efficiently. By combining high accuracy with accessibility, AntID_APP offers a scalable solution for biodiversity monitoring and public engagement in ecological research.