AI ‐assisted identification of stromatoporoids

Abstract

Stromatoporoid sponge fossils were major diverse reef‐builders in the Palaeozoic Era; their taxonomic identification relies on thin sections examined under transmitted light microscopy, where vertical and transverse skeletal elements reveal diagnostic architectural features that vary with taxa. These elements typically appear darker than the cement‐filled internal spaces, allowing stromatoporoid taxa to be distinguished. However, stromatoporoid architecture is variable so that judgement of identification is not always unequivocal. Therefore, this study investigates the application of artificial intelligence (AI) to automate stromatoporoid identification, introducing a novel approach to streamline and standardise palaeontological taxonomy. For the first time, both vertical and transverse sections have been simultaneously analysed and integrated into an automated framework. High‐resolution images of thin sections from four well‐established Silurian genera, collected from the West Midlands and Shropshire counties, UK, were used to train supervised machine learning models. The images, captured using plane‐polarised transmitted light microscopy on thin sections, were digitally enhanced to increase contrast and eliminate background noise, ensuring that only skeletal features were used to inform the models. Despite variations in fossil preservation, section orientation and image quality, the AI models achieved classification accuracies of up to 96%. This demonstrates that stromatoporoid skeletal architecture is highly amenable to automated analysis, even under suboptimal conditions. The results represent a significant step forward in the application of AI to palaeontology, reducing reliance on manual identification and accelerating the classification process. Ultimately, this approach provides a new quantitative framework for evaluating stromatoporoid skeletal architecture, strengthening the scientific basis of their taxonomic interpretation and opening new avenues for analysing morphological diversity in hypercalcified sponges.