DustNET: Enabling machine learning and AI models of dusty plasmas
Physics of Plasmas · 01.10.2026 · 33 (10)
DOI: 10.1063/5.0337599 ↗Kurz gefasst
Fachartikel in der Zeitschrift Physics of Plasmas, online erschienen am 30.10.2026. Verfasst von Zhehui Wang und 32 weiteren Autor:innen. Die Arbeit nennt 514 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Science Foundation, Plasma Physics Program, U.S. Department of Energy, National Science Foundation.
Abstract (Originalsprache)
Dusty plasmas, ubiquitous throughout the universe, may be found in laboratory and industrial plasmas, nuclear fusion devices, Earth's atmosphere and ionosphere, the lunar surface, planetary rings, cometary tails, and the interstellar and intergalactic media. Despite decades of experimental, theoretical, and computational research, many aspects of dusty plasmas remain poorly understood within a unified predictive framework, i.e., the Standard Model for dusty plasmas. Existing first-principles models based on particle, kinetic, fluid, and compound descriptions have successfully explained numerous phenomena, including dust charging, transport, waves, and self-organization. However, predictions remain challenging because of the inherent multiscale and multiphysics nature of dusty plasmas; computational complexity and other computing limitations; and incomplete knowledge of material properties, transport coefficients, and boundary conditions. Recent advances in machine learning (ML) and artificial intelligence (AI) provide new opportunities to complement traditional physics and first-principles modeling through data-driven scientific inference. This paper surveys current ML and AI applications in dusty plasma research, including microparticle imaging and tracking, image analysis, surrogate modeling, physics-informed learning, geometric learning, uncertainty quantification, and multimodal data fusion. We then introduce Dust Neural nEtworks Technology (DustNET), a community-oriented data infrastructure and benchmark ecosystem designed to support curated dusty plasma datasets spanning laboratory experiments, industrial plasmas, planetary, space, and astrophysical observations, numerical simulations, and AI-driven methods. We further discuss the Dusty-plasma Unified Sensing, Testing and Multi-modal Analysis Platform (DUST-MAP), a proposed member of dusty plasma world models that learn unified representations from heterogeneous dusty plasma data. By integrating experiments, measurements, simulations, scientific data and metadata, physical constraints and other regularizations within a common representation-learning framework, DUST-MAP aims to support universal inference and predictions across heterogeneous instruments, experimental facilities, and natural dusty plasmas. Toward the end, we present a phased community roadmap for the co-evolution of DustNET and DUST-MAP, emphasizing reproducible benchmarking, AI agents, and edge intelligence toward an AI-enabled ecosystem for dusty plasma science, with scalable and data-driven scientific intelligence across laboratory, industrial, planetary, space, and astrophysical dusty plasma environments.
Förderung
- the National Science Foundation, Plasma Physics Program
- U.S. Department of Energy
- National Science Foundation
- Simons Foundation
- US DOE
- German Federal Ministry of Economic Affairs and Climate Action
- the National Natural Science Foundation of China
- the National Science Foundation ECLIPSE program
Zitieren
APA
Wang, Z., Burton, J. C., Dormagen, N., Du, C., Feng, Y., Foster, J. E., Glenn, S. S., Klein, M., Knapek, C. A., Matthews, L., Melzer, A., Thomas, E., Wang, C., Avritte, J., Chang, S., Chaubey, N., Ekanayaka, P., Goree, J. A., Hyde, T., …, & Zhang, X. (2026). DustNET: Enabling machine learning and AI models of dusty plasmas. Physics of Plasmas, 33(10). https://doi.org/10.1063/5.0337599
Vancouver
Wang Z, Burton JC, Dormagen N, Du C, Feng Y, Foster JE, et al. DustNET: Enabling machine learning and AI models of dusty plasmas. Physics of Plasmas. 2026;33(10). doi:10.1063/5.0337599
BibTeX
@article{Wang2026,
author = {Wang, Zhehui and Burton, Justin C. and Dormagen, Niklas and Du, Cheng-Ran and Feng, Yan and Foster, John E. and Glenn, Susan S. and Klein, Max and Knapek, Christina A. and Matthews, Lorin and Melzer, André and Thomas, Edward and Wang, Chuji and Avritte, Jalaan and Chang, Shan and Chaubey, Neeraj and Ekanayaka, Pubuduni and Goree, John A. and Hyde, Truell and Liang, Chen and Liu, Zhuang and Ma, Zhuang and Nemenman, Ilya and Price, Elon and Schmitz, A. S. and Schwarz, Mike and Thakur, Saikat C. and Thoma, M. H. and Thomas, Hubertus M. and Wimmer, L. and Yang, Wei and Yang, Zimu and Zhang, Xiaoman},
title = {DustNET: Enabling machine learning and AI models of dusty plasmas},
journal = {Physics of Plasmas},
year = {2026},
volume = {33},
number = {10},
doi = {10.1063/5.0337599}
}
EUVIMED