Paper List
-
Autonomous Agents Coordinating Distributed Discovery Through Emergent Artifact Exchange
This paper addresses the fundamental limitation of current AI-assisted scientific research by enabling truly autonomous, decentralized investigation w...
-
D-MEM: Dopamine-Gated Agentic Memory via Reward Prediction Error Routing
This paper addresses the fundamental scalability bottleneck in LLM agentic memory systems: the O(N²) computational complexity and unbounded API token ...
-
Countershading coloration in blue shark skin emerges from hierarchically organized and spatially tuned photonic architectures inside skin denticles
This paper solves the core problem of how blue sharks achieve their striking dorsoventral countershading camouflage, revealing that coloration origina...
-
Human-like Object Grouping in Self-supervised Vision Transformers
This paper addresses the core challenge of quantifying how well self-supervised vision models capture human-like object grouping in natural scenes, br...
-
Hierarchical pp-Adic Framework for Gene Regulatory Networks: Theory and Stability Analysis
This paper addresses the core challenge of mathematically capturing the inherent hierarchical organization and multi-scale stability of gene regulator...
-
Towards unified brain-to-text decoding across speech production and perception
This paper addresses the core challenge of developing a unified brain-to-text decoding framework that works across both speech production and percepti...
-
Dual-Laws Model for a theory of artificial consciousness
This paper addresses the core challenge of developing a comprehensive, testable theory of consciousness that bridges biological and artificial systems...
-
Pulse desynchronization of neural populations by targeting the centroid of the limit cycle in phase space
This work addresses the core challenge of determining optimal pulse timing and intensity for desynchronizing pathological neural oscillations when the...
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
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.
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.