Microparticle cloud imaging and tracking for data-driven plasma science
arXiv:1911.01000 · doi:10.1063/1.5134787
Abstract
Large data sets give rise to the `fourth paradigm' of scientific discovery and technology development, extending other approaches based on human intuition, fundamental laws of physics, statistics and intense computation. Both experimental and simulation data are growing explosively in plasma science and technology, motivating data-driven discoveries and inventions, which are currently in infancy. Here we describe recent progress in microparticle cloud imaging and tracking (mCIT, CIT) for laboratory plasma experiments. Three types of microparticle clouds are described: from exploding wires, in dusty plasmas and in atmospheric plasmas. The experimental data sets are obtained with one or more imaging cameras at a rate up to 100k frames per second (fps). A physics-constrained motion tracker, a Kohonen neural network (KNN) or self-organizing map (SOM), the feature tracking kit (FTK), and U-Net are described and compared with each other for particle tracking using the datasets. Particle density and signal-to-noise ratio have been identified as two important factors that affect the tracking accuracy. Fast Fourier transform (FFT) is used to reveal how U-Net, a deep convolutional neural network (CNN) developed for non-plasma applications, achieves the improvements for noisy scenes. The fitting parameters for a simple polynomial track model are found to group into clusters that reveal the geometry information about the camera setup. The mCIT or CIT techniques, when enhanced with data models, can be used to study the microparticle- or Debye-length scale plasma physics. The datasets are also available for ML code development and comparisons of algorithms.
arXiv comment14 pages, 15 figures, invited talk to the 2nd international conference on data-driven plasma science, Marseille, France, May 13-17, 2019
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Fully Convolutional Networks for Semantic Segmentation
- Fully Convolutional Networks for Semantic Segmentation
- Star-galaxy Classification Using Deep Convolutional Neural Networks
- The Power of Depth for Feedforward Neural Networks
- Convolutional neural networks automate detection for tracking of submicron scale particles in 2D and 3D
- A deep convolutional neural network approach to single-particle recognition in cryo-electron microscopy
- Errors in particle tracking velocimetry with high-speed cameras
- SO-Net: Self-Organizing Network for Point Cloud Analysis
- Machine-learning techniques for fast and accurate feature localization in holograms of colloidal particles
- Dust density waves in a dc flowing complex plasma with discharge polarity reversal
- End-to-end people detection in crowded scenes
- Tracking shocked dust: state estimation for a complex plasma during a shock wave
- Measurement of high-temperature microparticle acceleration through imaging
Cited by in corpus (5)
- 2022 Review of Data-Driven Plasma Science
- Extracting Forces from Noisy Dynamics in Dusty Plasmas
- Asynchronous and Load-Balanced Union-Find for Distributed and Parallel Scientific Data Visualization and Analysis
- 3D tracking of particles in a dusty plasma by laser sheet tomography
- Sparse identification of effective microparticle interaction potential in dusty plasma from simulation data