Machine Learning in Plasma Physics, Chemistry, and Processing

Plasma research has expanded and continues to expand in novel multi-disciplinary areas such as plasma conversion and catalysis, materials processing, nanotechnology, space science, ion thrusters, agriculture, food processing, astronomy, biotechnology, medicine, and many more. In these applications, the dynamics of plasmas is highly complex, making modeling and characterization of these plasmas challenging. Further, real-time data analysis, to extract key information and optimize plasma processing in a given application, requires advanced modeling techniques. In this regard, data-driven approaches, such as machine learning, offer unprecedented potential to advance plasma characterization, modeling, simulation, and their application. However, in most cases, the amount of data collected is not adequate, which introduces an ambiguity that requires attention regarding trustworthiness and physical explainability. At the same time, recent developments in measurement techniques and computational ability are leading to the generation of larger and larger amounts of data, which may promote a paradigm shift toward novel applications of machine learning methods in plasma science. Additional advanced in machine learning algorithms are also expected to foster data-driven model interpretability.

This Research Topic aims to collect, highlight, and disseminate the latest developments in machine learning methods in plasma physics, chemistry and processing. It will also provide useful literature to the researchers working in associated research areas.

Topics to be covered in this thematic collection of papers include the following subjects and related topics:

● Integration of ML mentioned in plasma modeling and simulation
● Integration of ML mentioned in plasma characterization
● Integration of ML mentioned in understanding plasma mediated physical and chemical processing
● ML in plasma physics
● ML in plasma chemistry
● Research data management
● Explainability / Trustworthiness.

We welcome submissions of the following article types: Brief Research Report, General Commentary, Mini Review, Original Research, Perspective, Review, Technology and Code.

Keywords: Low-temperature Plasmas, Machine Learning, Modeling, Diagnostics, Plasma-mediated processing

Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.