Plasma-Sheet Bubble Identification Using Multivariate Time Series Classification

Feng, Xuedong; Yang, Jian

2023-10-01

10.1029/2023JA031469

JOURNAL OF GEOPHYSICAL RESEARCH-SPACE PHYSICS   Impact Factor & Quartile

2169-9380

2169-9402

Plasma-sheet bubbles play a major role in the earthward transport of magnetotail particles. The most remarkable feature of bubbles is their fast bulk flow velocities, along with reduced plasma density and pressure accompanied by magnetic field dipolarization. These bubbles can be identified based on in situ observations, but subjective ambiguity necessitates human verification, due to confusion with other phenomena mostly associated with magnetic reconnection and plasma waves. In this study, we aim to employ machine learning (ML) techniques to detect bubbles automatically and to create a tool that can be utilized by individuals without specialized subject expertise. To identify bubbles, we combine three distinct techniques: MINImally RandOm Convolutional KErnel Transform (MINIROCKET), 1D convolution neural network, and Residual Network (ResNet). The imbalanced training data set consists of bubble and non-bubble events with a ratio of 1:40 from 2007 to 2020. The results indicate that the accuracy of all three models is approximately 99%, and their precision, recall, and F-2 score are all above 80% for both the validation and test datasets. The three methods are combined with the intersection set as the minimum set of predictions and the union set as the maximum set. The union set can accurately identify 66.7% of bubbles. The combined method reduces the number of false negatives significantly. In the prediction of bubbles in observations made in the year 2021 using a union set, the bubbles obtained by the model are comparable to those discovered using traditional criteria and manual inspections.

plasma-sheet bubble multivariate time series classification sample imbalanced image recognition

SCI

English

First ; Corresponding

This work was supported by Grants 41974187, 42174197, and 42204170 of the National Natural Science Foundation of China, the Stable Support Plan Program of Shenzhen Natural Science Fund (Grant 20200925153644003), Shenzhen Science and Technology Program (Gra["41974187","42174197","42204170"] ; National Natural Science Foundation of China[20200925153644003] ; Shenzhen Science and Technology Program["JCYJ20220530113402004","XDB41000000"] ; Chinese Academy of Sciences[NAS5-02099] ; German Ministry for Economy and Technology[50 OC 0302]

Astronomy & Astrophysics

Astronomy & Astrophysics

WOS:001086426100001

AMER GEOPHYSICAL UNION

SPACE SCIENCE

Web of Science

Southern Univ Sci & Technol, Dept Earth & Space Sci, Shenzhen, Peoples R China

Feng, Xuedong,Yang, Jian. Plasma-Sheet Bubble Identification Using Multivariate Time Series Classification[J]. JOURNAL OF GEOPHYSICAL RESEARCH-SPACE PHYSICS,2023,128(10).

Feng, Xuedong,&Yang, Jian.(2023).Plasma-Sheet Bubble Identification Using Multivariate Time Series Classification.JOURNAL OF GEOPHYSICAL RESEARCH-SPACE PHYSICS,128(10).

Feng, Xuedong,et al."Plasma-Sheet Bubble Identification Using Multivariate Time Series Classification".JOURNAL OF GEOPHYSICAL RESEARCH-SPACE PHYSICS 128.10(2023).