Paper List

期刊: ArXiv Preprint
发布日期: 2026-03-12
BioinformaticsArchaeology

Leveraging Phytolith Research using Artificial Intelligence

Institut de Ciència i Tecnologia Ambientals, Universitat Autònoma de Barcelona | Smithsonian National Museum of Natural History | University of Duisburg-Essen | Università di Trento | Herbario Nacional de Bolivia | The Pennsylvania State University

Andrés G. Mejía Ramón, Kate Dudgeon, Nina Witteveen, Dolores Piperno, Michael Kloster, Luigi Palopoli, Mónica Moraes R., José M. Capriles, Umberto Lombardo
Figure
Figure
Figure
Figure

30秒速读

IN SHORT: This paper addresses the critical bottleneck in phytolith research by automating the labor-intensive manual microscopy process through a multimodal AI pipeline that enables high-throughput analysis of archaeological samples.

核心创新

  • Methodology First multimodal fusion model combining ConvNeXt (2D images) and PointNet++ (3D point clouds) for phytolith classification, achieving 77.9% global accuracy across 24 morphotypes.
  • Methodology Complete end-to-end pipeline from z-stack microscopy to Bayesian mixture modeling, processing 3.81 million segmented objects from 712 slide sectors.
  • Biology Demonstrates that 3D data is essential for distinguishing complex morphotypes like grass silica short cells, where diagnostic features are often obscured in 2D projections.

主要结论

  • The multimodal fusion model achieved 77.9% global classification accuracy (71.4% class-adjusted) and 84.5% segmentation quality accuracy, with 3D data proving critical for distinguishing orientation-dependent morphotypes.
  • Bayesian finite mixture modeling successfully identified specific plant contributions (maize and palms) in complex mixed samples, enabling assemblage-level analysis beyond individual object classification.
  • The pipeline processed 3.81 million objects from 123 slides, demonstrating scalability orders of magnitude beyond traditional methods while maintaining systematic error patterns usable for compositional analysis.
研究空白： Traditional phytolith analysis relies on labor-intensive manual microscopy limited to 200-400 morphotypes per sample, while previous AI approaches focused on limited morphotype sets using only 2D data, lacking scalability for complex archaeological assemblages.

摘要: Phytolith analysis is a crucial tool for reconstructing past vegetation and human activities, but traditional methods are severely limited by labour-intensive, time-consuming manual microscopy. To address this bottleneck, we present Sorometry: a comprehensive end-to-end artificial intelligence pipeline for the high-throughput digitisation, inference, and interpretation of phytoliths. Our workflow processes z-stacked optical microscope scans to automatically generate synchronised 2D orthoimages and 3D point clouds of individual microscopic particles. We developed a multimodal fusion model that combines ConvNeXt for 2D image analysis and PointNet++ for 3D point cloud analysis, supported by a graphical user interface for expert annotation and review. Tested on reference collections and archaeological samples from the Bolivian Amazon, our fusion model achieved a global classification accuracy of 77.9% across 24 diagnostic morphotypes and 84.5% for segmentation quality. Crucially, the integration of 3D data proved essential for distinguishing complex morphotypes (such as grass silica short cell phytoliths) whose diagnostic features are often obscured by their orientation in 2D projections. Beyond individual object classification, Sorometry incorporates Bayesian finite mixture modelling to predict overall plant source contributions at the assemblage level, successfully identifying specific plants like maize and palms in complex mixed samples. This integrated platform transforms phytolith research into an “omics”-scale discipline, dramatically expanding analytical capacity, standardising expert judgements, and enabling reproducible, population-level characterisations of archaeological and paleoecological assemblages.