Measurement of Anomalous Diffusion Using Recurrent Neural Networks

Abstract

Anomalous diffusion occurs in many physical and biological phenomena, when the growth of the mean squared displacement (MSD) with time has an exponent different from one. We show that recurrent neural networks (RNN) can efficiently characterize anomalous diffusion by determining the exponent from a single short trajectory, outperforming the standard estimation based on the MSD when the available data points are limited, as is often the case in experiments. Furthermore, the RNN can handle more complex tasks where there are no standard approaches, such as determining the anomalous diffusion exponent from a trajectory sampled at irregular times, and estimating the switching time and anomalous diffusion exponents of an intermittent system that switches between different kinds of anomalous diffusion. We validate our method on experimental data obtained from sub-diffusive colloids trapped in speckle light fields and super-diffusive microswimmers.

arXiv comment6 pages, 4 figures. Supplemental material available as separate file in the Ancillary Files section

References in corpus (16)

• TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
• Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation
• A Critical Review of Recurrent Neural Networks for Sequence Learning
• Anomalous transport in the crowded world of biological cells
• Don't Decay the Learning Rate, Increase the Batch Size
• Active Brownian Motion Tunable by Light
• Quantitative analysis of single particle trajectories: mean maximal excursion method
• Spectral content of a single non-Brownian trajectory
• Improved estimation of anomalous diffusion exponents in single particle tracking experiments
• Light-controlled Assembly of Active Colloidal Molecules
• Brownian Motion in a Speckle Light Field: Tunable Anomalous Diffusion and Deterministic Optical Manipulation
• Speckle Optical Tweezers: Micromanipulation with Random Light Fields
• Microscopic Engine Powered by Critical Demixing
• Single-Molecule Imaging of Nav1.6 on the Surface of Hippocampal Neurons Reveals Somatic Nanoclusters
• Elucidating distinct ion channel populations on the surface of hippocampal neurons via single-particle tracking recurrence analysis
• Optimal parameters for anomalous diffusion exponent estimation from noisy data

Cited by in corpus (38)

• Misalignment Resilient Diffractive Optical Networks
• Machine learning method for single trajectory characterization
• Quantitative Digital Microscopy with Deep Learning
• Zermelo's problem: Optimal point-to-point navigation in 2D turbulent flows using Reinforcement Learning
• Bayesian deep learning for error estimation in the analysis of anomalous diffusion
• Classification of particle trajectories in living cells: machine learning versus statistical testing hypothesis for fractional anomalous diffusion
• Classification, inference and segmentation of anomalous diffusion with recurrent neural networks
• Machine-Learning Solutions for the Analysis of Single-Particle Diffusion Trajectories
• Characterization of anomalous diffusion classical statistics powered by deep learning (CONDOR)
• Drawing Phase Diagrams of Random Quantum Systems by Deep Learning the Wave Functions
• Learning physical properties of anomalous random walks using graph neural networks
• Universal spectral features of different classes of random diffusivity processes
• Boosting the performance of anomalous diffusion classifiers with the proper choice of features
• Inferring pointwise diffusion properties of single trajectories with deep learning
• Quantitative evaluation of methods to analyze motion changes in single-particle experiments
• Moses, Noah and Joseph Effects in Coupled Lévy Processes
• Characterization of anomalous diffusion through convolutional transformers
• Leveraging large-deviation statistics to decipher the stochastic properties of measured trajectories
• Predicting Critical Transitions in Multiscale Dynamical Systems Using Reservoir Computing
• Extreme Learning Machine for the Characterization of Anomalous Diffusion from Single Trajectories (AnDi-ELM)
• Different anomalous diffusion regimes measured in the dynamics of tracer particles in actin networks
• WaveNet-Based Deep Neural Networks for the Characterization of Anomalous Diffusion (WADNet)
• Semantic Segmentation of Anomalous Diffusion Using Deep Convolutional Networks
• Gramian Angular Fields for leveraging pretrained computer vision models with anomalous diffusion trajectories
• Variational inference of fractional Brownian motion with linear computational complexity
• Anomalous Diffusion: Fractional Brownian Motion vs. Fractional Ito Motion
• Anomalous diffusion, non-Gaussianity, and nonergodicity for subordinated fractional Brownian motion with a drift
• Machine Learning Analysis of Anomalous Diffusion
• Objective comparison of methods to decode anomalous diffusion
• Dead or alive: Distinguishing active from passive particles using supervised learning
• Preface: Characterisation of Physical Processes from Anomalous Diffusion Data
• Change-point detection in anomalous-diffusion trajectories utilising machine-learning-based uncertainty estimates
• Efficient recurrent neural network methods for anomalously diffusing single particle short and noisy trajectories
• Persistence of temperature and precipitation: from local to global anomalies
• Inferring nonlinear fractional diffusion processes from single trajectories
• Shape matters: Inferring the motility of confluent cells from static images
• Recurrent neural network analysis of single trajectories switching between anomalous diffusion states
• Holographic characterisation of subwavelength particles enhanced by deep learning