AI-Powered Automation of Tick Species Classification: A Synergy of Citizen Science and Deep Learning

NAISS 2024/5-63


NAISS Medium Compute

Principal Investigator:

Najmeh Abiri


Högskolan i Halmstad

Start Date:


End Date:


Primary Classification:

10207: Computer Vision and Robotics (Autonomous Systems)

Secondary Classification:

10202: Information Systems (Social aspects to be 50804)

Tertiary Classification:

10501: Climate Research




This research article introduces a pioneering methodology that effectively integrates Artificial Intelligence (AI) and citizen science, focusing on tackling the complexities inherent in tick surveillance and enhancing public health measures. The core of this project lies in its utilization of state-of-the-art deep learning algorithms used for the automated and accurate classification of various tick species. This initiative was launched as a direct response to the discovery of an exotic tick species in Sweden in 2018. The project collected substantial public engagement following a citizen science campaign spearheaded by Sweden's National Veterinary Institute (SVA). Implementing advanced AI strategies, including image analysis, object detection, and the application of transfer learning, plays a crucial role in this project. These advanced methodologies significantly optimize the process of identifying and classifying tick species. By doing so, they substantially augment the efficacy and dependability of the data obtained through citizen-driven scientific endeavors. In its initial stages, the system has exhibited encouraging outcomes, underlining its capability to transform the landscape of tick surveillance. This transformation is pivotal, particularly in public and veterinary health realms, where accurate and timely data is crucial. Furthermore, this article underscores the significant role of AI in redefining the scope and impact of citizen science, especially in the domain of public health surveillance. The study demonstrates the practical applications of AI in environmental and health sciences and sets a precedent for future research in AI-assisted citizen science projects. The findings and methodologies presented in this article are relevant to the specific case of tick surveillance in Sweden and provide valuable insights and frameworks that can be adapted and applied globally in similar public health challenges.