ORIGINAL RESEARCH article
Front. Astron. Space Sci.
Sec. Low-Temperature Plasma Physics
Volume 12 - 2025 | doi: 10.3389/fspas.2025.1614225
This article is part of the Research TopicMachine Learning in Plasma Physics, Chemistry, and ProcessingView all articles
Stacking data analysis method for Langmuir multi-probes payload
Provisionally accepted
- 1National Space Science Center, Chinese Academy of Sciences (CAS), Beijing, China
- 2Shandong University, Weihai, Weihai, Shandong, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
There are numerous small-scale electron density irregularities in the ionosphere. The coordination of multiple needle Langmuir probes (m-NLP) can achieve in-situ measurement of electron density with high spatial resolution. However, the theoretical analysis method based on Orbital Motion-Limited (OML) theory cannot estimate electron density accurately even at higher resolution due to the restriction in satellite measurements. In addition, due to the influence of satellite charging and flight wake, the current collected between multi-probes has low consistency, which introduces a large error in the measurement results. This study uses the Stacking algorithm to process the m-NLP data and cites the International Reference Ionosphere (IRI) Model to correct the Ne prediction results. The integrated characteristics of the Stacking model make full use of the advantages of models such as Multilayer Perceptron (MLP), Support Vector Regression (SVR), K-Nearest Neighbors (KNN) and Light Gradient Boosting Machine (LightGBM) theories. The combination of integrated machine learning methods and IRI models greatly improves the accuracy of the electron density obtained by m-NLP. The results indicate that even with poor consistency in the collected current between multi-probes, the R2 of the prediction results of this method can reach 0.9553, which is 0.5079 higher than the traditional diagnostic method.
Keywords: langmuir probe, stacking, machine learning, plasma diagnosis, Ionospheric irregularity
Received: 18 Apr 2025; Accepted: 16 Jul 2025.
Copyright: © 2025 Wang, Zhang, Zhang, Xie, Zou, Du, VARGHESE and Sun. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Jin Wang, National Space Science Center, Chinese Academy of Sciences (CAS), Beijing, China
Qinghe Zhang, National Space Science Center, Chinese Academy of Sciences (CAS), Beijing, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.