Machine learning method for single trajectory characterization
This method enables precise analysis of transport in complex environments for researchers, though it is incremental as it applies an existing random forest architecture to a specific data challenge.
The paper tackles the problem of characterizing diffusion mechanisms from short, noisy single trajectories, achieving high accuracy in classifying normal vs. anomalous diffusion and determining anomalous exponents with small errors.
In order to study transport in complex environments, it is extremely important to determine the physical mechanism underlying diffusion, and precisely characterize its nature and parameters. Often, this task is strongly impacted by data consisting of trajectories with short length and limited localization precision. In this paper, we propose a machine learning method based on a random forest architecture, which is able to associate even very short trajectories to the underlying diffusion mechanism with a high accuracy. In addition, the method is able to classify the motion according to normal or anomalous diffusion, and determine its anomalous exponent with a small error. The method provides highly accurate outputs even when working with very short trajectories and in the presence of experimental noise. We further demonstrate the application of transfer learning to experimental and simulated data not included in the training/testing dataset. This allows for a full, high-accuracy characterization of experimental trajectories without the need of any prior information.