WaveNet-Based Deep Neural Networks for the Characterization of Anomalous Diffusion (WADNet)

TL;DR

This paper introduces WADNet, a WaveNet-based deep neural network that effectively characterizes anomalous diffusion from short trajectories, outperforming existing methods in the AnDi Challenge across multiple tasks and dimensions.

Contribution

The paper presents a novel WaveNet-based neural network that improves inference and classification of anomalous diffusion without prior knowledge, setting a new benchmark in the field.

Findings

WADNet outperforms current top methods in the AnDi Challenge.

The model achieves high accuracy across all dimensions and tasks.

It provides a versatile tool for characterizing anomalous diffusion.

Abstract

Anomalous diffusion, which shows a deviation of transport dynamics from the framework of standard Brownian motion, is involved in the evolution of various physical, chemical, biological, and economic systems. The study of such random processes is of fundamental importance in unveiling the physical properties of random walkers and complex systems. However, classical methods to characterize anomalous diffusion are often disqualified for individual short trajectories, leading to the launch of the Anomalous Diffusion (AnDi) Challenge. This challenge aims at objectively assessing and comparing new approaches for single trajectory characterization, with respect to three different aspects: the inference of the anomalous diffusion exponent; the classification of the diffusion model; and the segmentation of trajectories. In this article, to address the inference and classification tasks in the challenge, we develop a WaveNet-based deep neural network (WADNet) by combining a modified WaveNet encoder with long short-term memory networks, without any prior knowledge of anomalous diffusion. As the performance of our model has surpassed the current 1st places in the challenge leaderboard on both two tasks for all dimensions (6 subtasks), WADNet could be the part of state-of-the-art techniques to decode the AnDi database. Our method presents a benchmark for future research, and could accelerate the development of a versatile tool for the characterization of anomalous diffusion.