Gramian Angular Fields for leveraging pretrained computer vision models with anomalous diffusion trajectories

TL;DR

This paper introduces a novel approach using Gramian Angular Fields to encode diffusion trajectories as images, enabling the use of pre-trained computer vision models to classify diffusive regimes and estimate the anomalous diffusion exponent with high accuracy.

Contribution

The study presents a new data-driven method that transforms 1D diffusion trajectories into images, allowing the application of pre-trained vision models for improved analysis of diffusive behaviors.

Findings

GAF encoding improves classification accuracy of diffusive regimes.

Pre-trained models outperform existing methods on short trajectories.

Method enhances accessibility of machine learning in diffusion analysis.

Abstract

Anomalous diffusion is present at all scales, from atomic to large scales. Some exemplary systems are; ultra-cold atoms, telomeres in the nucleus of cells, moisture transport in cement-based materials, the free movement of arthropods, and the migration patterns of birds. The characterization of the diffusion gives critical information about the dynamics of these systems and provides an interdisciplinary framework with which to study diffusive transport. Thus, the problem of identifying underlying diffusive regimes and inferring the anomalous diffusion exponent {$\alpha$} with high confidence is critical to physics, chemistry, biology, and ecology. Classification and analysis of raw trajectories combining machine learning techniques with statistics extracted from them have widely been studied in the Anomalous Diffusion Challenge ge (Munoz-Gil et al., 2021). Here we present a new data-driven method for working with diffusive trajectories. This method utilizes Gramian Angular Fields (GAF) to encode one-dimensional trajectories as images (Gramian Matrices), while preserving their spatiotemporal structure for input to computer-vision models. This allows us to leverage two well-established pre-trained computer-vision models, ResNet and MobileNet, to characterize the underlying diffusive regime, and infer the anomalous diffusion exponent {$\alpha$}. Short raw trajectories, of lengths between 10 and 50, are commonly encountered in single-particle tracking experiments and are the most difficult to characterize. We show that by using GAF images, we can outperform the current state-of-the-art while increasing accessibility to machine learning methods in an applied setting.