Twenty thousand leagues under plant biominerals: a deep learning implementation for automatic phytolith classification

• Published in: Earth science informatics 2023-06, Vol.16 (2), p.1551-1562
• Main Authors: Andriopoulou, Nafsika C., Petrakis, Georgios, Partsinevelos, Panagiotis
• Format: Article
• Language: English
• Subjects: Artificial neural networks; Classification; Coders; Datasets; Deep learning; Earth and Environmental Science; Earth Sciences; Earth System Sciences; Encoders-Decoders; Homogeneity; Image segmentation; Information Systems Applications (incl.Internet); Machine learning; Neural networks; Ontology; Parameterization; Photomicrographs; Sediments; Silicon dioxide; Simulation and Modeling; Space Exploration and Astronautics; Space Sciences (including Extraterrestrial Physics; Training
• ISSN: 1865-0473; 1865-0481
• DOI: 10.1007/s12145-023-00975-z

Phytoliths constitute microscopic SiO 2 -rich biominerals formed in the cellular system of many living plants and are often preserved in soils, sediments and artefacts. Their analysis contributes significantly to the identification and study of botanical remains in (paleo)ecological and archaeological contexts. Traditional identification and classification of phytoliths rely on human experience, and as such, an emerging challenge is to automatically classify them to enhance data homogeneity among researchers worldwide and facilitate reliable comparisons. In the present study, a deep artificial neural network (NN) is implemented under the objective to detect and classify phytoliths, extracted from modern wheat ( Triticum spp.). The proposed methodology is able to recognise four phytolith morphotypes: (a) Stoma, (b) Rondel, (c) Papillate, and (d) Elongate dendritic. For the learning process, a dataset of phytolith photomicrographs was created and allocated to training, validation and testing data groups. Due to the limited size and low diversity of the dataset, an end-to-end encoder-decoder NN architecture is proposed, based on a pre-trained MobileNetV2, utilised for the encoder part and U-net, used for the segmentation stage. After the parameterisation, training and fine-tuning of the proposed architecture, it is capable to classify and localise the four classes of phytoliths in unknown images with high unbiased accuracy, exceeding 90%. The proposed methodology and corresponding dataset are quite promising for building up the capacity of phytolith classification within unfamiliar (geo)archaeological datasets, demonstrating remarkable potential towards automatic phytolith analysis.