Two-Stage Solar Flare Forecasting Based on Convolutional Neural Networks

Chen, Jun; Li, Weifu; Li, Shuxin; Chen, Hong; Zhao, Xuebin; Peng, Jiangtao; Chen, Yanhong; Deng, Hao

doi:10.34133/2022/9761567

Cited by 10 publications

(4 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ANN technique has been widely applied to deal with classification, regression, and pattern recognition tasks in Earth science, such as by Chen et al [35]. A classic ANN consists of three components: an input layer, hidden layers, and an output layer.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Thermospheric Mass Density Modelling during Geomagnetic Quiet and Weakly Disturbed Time

He,

Li,

et al. 2024

Atmosphere

View full text Add to dashboard Cite

Atmospheric drag stands out as the predominant non-gravitational force acting on satellites in Low Earth Orbit (LEO), with altitudes below 2000 km. This drag exhibits a strong dependence on the thermospheric mass density (TMD), a parameter of vital significance in the realms of orbit determination, prediction, collision avoidance, and re-entry forecasting. A multitude of empirical TMD models have been developed, incorporating contemporary data sources, including TMD measurements obtained through onboard accelerometers on LEO satellites. This paper delves into three different TMD modelling techniques, specifically, Fourier series, spherical harmonics, and artificial neural networks (ANNs), during periods of geomagnetic quiescence. The TMD data utilised for modelling and evaluation are derived from three distinct LEO satellites: GOCE (at an altitude of approximately 250 km), CHAMP (around 400 km), and GRACE (around 500 km), spanning the years 2002 to 2013. The consistent utilisation of these TMD data sets allows for a clear performance assessment of the different modelling approaches. Subsequent research will shift its focus to TMD modelling during geomagnetic disturbances, while the present work can serve as a foundation for disentangling TMD variations stemming from geomagnetic activity. Furthermore, this study undertakes precise TMD modelling during geomagnetic quiescence using data obtained from the GRACE (at an altitude of approximately 500 km), CHAMP (around 400 km), and GOCE (roughly 250 km) satellites, covering the period from 2002 to 2013. It employs three distinct methods, namely Fourier analysis, spherical harmonics (SH) analysis, and the artificial neural network (ANN) technique, which are subsequently compared to identify the most suitable methodology for TMD modelling. Additionally, various combinations of time and coordinate representations are scrutinised within the context of TMD modelling. Our results show that the precision of low-order Fourier-based models can be enhanced by up to 10 % through the utilisation of geocentric solar magnetic coordinates. Both the Fourier- and SH-based models exhibit limitations in approximating the vertical gradient of TMD. Conversely, the ANN-based model possesses the capacity to capture vertical TMD variability without manifesting sensitivity to variations in time and coordinate inputs.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Thermospheric Mass Density Modelling during Geomagnetic Quiet and Weakly Disturbed Time

He,

Li,

et al. 2024

Atmosphere

View full text Add to dashboard Cite

show abstract

“…This destructive eruption with the Volcanic Explosivity Index of ∼6 emitted total eject mass of 6.5 × 10 12 kg, and generated the strongest atmospheric wave in the 21st century, larger than any volcanic event or nuclear test (Poli & Shapiro, 2022). This interesting event has attracted the focus of many scientists on volcanic‐ionospheric coupling (J. Chen et al., 2022; Matoza et al., 2022; Wright et al., 2022). This explosion produced huge amounts of atmospheric waves across a range of lengths, including external Lamb wave, acoustic wave and internal gravity wave, and the waves propagated individually in different atmospheric layers (C.‐H.…”

Section: Introductionmentioning

confidence: 99%

Asymmetric Ionospheric Fluctuations Over the Circum‐Pacific Regions Following the January 2022 Tonga Volcanic Eruption

Li,

Zhu,

Feng

et al. 2023

Space Weather

View full text Add to dashboard Cite

The Hunga Tonga‐Hunga Ha'apai volcanic eruption on 15 January 2022 had a significant impact on the ionosphere‐thermosphere system, resulting in large‐scale ionospheric irregularities with longitudinal and latitudinal asymmetries. Multiple instruments recorded these irregularities, indicating the propagation of a westward wave at an average velocity of 354 ± 8 m/s, which led to plasma irregularities of 0.2 TECu/min. Conversely, an eastward‐propagating wave was detected on the Pacific's east coast, traveling at a speed of 348 ± 6 m/s, with a corresponding decrease in plasma fluctuations to 0.1 TECu/min. In Asia, noticeable plasma irregularities appeared within a few hours after the eruption, and the maximum speed exceeded 1,100 m/s, which cannot be explained by the acoustic wave model. There was also a significant latitudinal asymmetry of ionospheric disturbances in the Asian‐Oceania sector, with the plasma density around Oceania depleted by 2–3 orders of magnitude within the altitudes of ∼150–575 km, while the ion density over Asia was enhanced by 1–2 orders of magnitude, and was uplifted ∼50 km. The plasma temperature was proportional to ion density, indicating the ion temperature reduced ∼500 K and increased 100–200 K around Oceania and Asia, respectively. The equatorial electric field, vertical E × B drifts and thermospheric O/N2 density ratio also fluctuated significantly following the eruption, indicating the redistribution of charged particles due to the magnetic field mapping effect, which was the main contributor to the asymmetries observed.

show abstract

“…In recent years, machine learning algorithms have been applied to solar physics and have made progress in flare prediction, especially in extracting new predictors and developing effective models (Liu et al, 2017;Wang et al, 2020;Chen et al, 2022;Sun et al, 2022;Wang et al, 2022;Li et al, 2022;Nishizuka et al, 2021;Sun et al, 2021). Liu et al (2017) adopted the random forest method for the multiclass classification of flares.…”

Section: Introductionmentioning

confidence: 99%

A selective up-sampling method applied upon unbalanced data for flare prediction: potential to improve model performance

Liu

Wang

et al. 2023

Front. Astron. Space Sci.

View full text Add to dashboard Cite

The Spaceweather HMI Active Region Patch (SHARP) parameters have been widely used to develop flare prediction models. The relatively small number of strong-flare events leads to an unbalanced dataset that prediction models can be sensitive to the unbalanced data and might lead to bias and limited performance. In this study, we adopted the logistic regression algorithm to develop a flare prediction model for the next 48 h based on the SHARP parameters. The model was trained with five different inputs. The first input was the original unbalanced dataset; the second and third inputs were obtained by using two widely used sampling methods from the original dataset, while the fourth input was the original dataset but accompanied by a weighted classifier. Based on the distribution properties of strong-flare occurrences related to SHARP parameters, we established a new selective up-sampling method and applied it to the mixed-up region (referred to as the confusing distribution areas consisting of both the strong-flare events and non-strong-flare events) to pick up the flare-related samples and add small random values to them and finally create a large number of flare-related samples that are very close to the ground truth. Thus, we obtained the fifth balanced dataset aiming to 1) promote the forecast capability in the mixed-up region and 2) increase the robustness of the model. We compared the model performance and found that the selective up-sampling method has potential to improve the model performance in strong-flare prediction with its F1 score reaching 0.5501 ± 0.1200, which is approximately 22% − 33% higher than other imbalance mitigation schemes.

show abstract

Two-Stage Solar Flare Forecasting Based on Convolutional Neural Networks

Cited by 10 publications

References 44 publications

Thermospheric Mass Density Modelling during Geomagnetic Quiet and Weakly Disturbed Time

Thermospheric Mass Density Modelling during Geomagnetic Quiet and Weakly Disturbed Time

Asymmetric Ionospheric Fluctuations Over the Circum‐Pacific Regions Following the January 2022 Tonga Volcanic Eruption

A selective up-sampling method applied upon unbalanced data for flare prediction: potential to improve model performance

Contact Info

Product

Resources

About