# Particle streak velocimetry using Ensemble Convolutional Neural Networks

## TL;DR

This paper introduces a CNN-based method for analyzing streak images in flow experiments, enabling quantitative flow characterization with uncertainty estimation, validated on simulations and real experiments.

## Contribution

It presents an open-source ensemble CNN approach for streak velocimetry, including a rapid data generation method and uncertainty quantification, advancing flow measurement techniques.

## Key findings

- Accurate flow velocity and directionality retrieval from streak images.
- Effective uncertainty estimation using ensemble CNNs.
- Validated approach on simulated and experimental flow data.

## Abstract

This study reports an approach and presents its open-source implementation for quantitative analysis of experimental flows using streak images and Convolutional Neural Networks (CNN). The latter are applied to retrieve a length and an angle from streaks, which can be used to deduce kinetic energy and directionality (up to 180$^{\circ}$ ambiguity) of an imaged flow. We developed a quick method for generating essentially unlimited number of training and validation images, which enabled efficient training. Additionally, we show how to apply an ensemble of CNNs to derive a formal uncertainty on the estimated quantities. The approach is validated on the numerical simulation of a convenctive turbulent flow and applied to a longitutidal libration flow experiment.