Assessing the Predictability of Solar Energetic Particles with the Use of Machine Learning Techniques

Lavasa, Eleni; Giannopoulos, Giorgos; Papaioannou, Athanasios; Anastasiadis, A.; Daglis, Ioannis A.; Aran, A.; Pacheco, Daniel

doi:10.1007/s11207-021-01837-x

Cited by 24 publications

(35 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, independently, different authors (i.e., Lavasa et al. (2021), and the authors of the current manuscript) have shown the usage and extent of ML methods to the imbalanced problem of SPE forecasting with results in very good agreement and pointing to the same direction.…”

Section: Discussionmentioning

confidence: 58%

“…We point out that this is a critical issue of any statistical approach, and thus the model validation must be done by preserving the class distributions within the training and test datasets. Very recently, Lavasa et al (2021), also treated the inherently imbalanced problem of SPE binary prediction. Thus, independently, different authors (i.e., Lavasa et al (2021), and the authors of the current manuscript) have shown the usage and extent of ML methods to the imbalanced problem of SPE forecasting with results in very good agreement and pointing to the same direction.…”

Section: Discussionmentioning

confidence: 99%

“…Very recently, Lavasa et al. (2021), also treated the inherently imbalanced problem of SPE binary prediction. Thus, independently, different authors (i.e., Lavasa et al.…”

Section: Discussionmentioning

confidence: 99%

“…Very recently, Lavasa et al (2021), also treated the inherently imbalanced problem of SPE binary prediction. Thus, independently, different authors (i.e., Lavasa et al (2021), and the authors of the current manuscript) have shown the usage and extent of ML methods to the imbalanced problem of SPE forecasting with results in very good agreement and pointing to the same direction. obtained here through the cross-validated SMOTE MLE over the whole data set, we observe a quite better FAR despite the fact that we have a greater imbalance (1:9) with respect to Núñez and Paul-Pena (2020, 1.5:8.5).…”

Section: Discussionmentioning

confidence: 99%

See 3 more Smart Citations

Open Issues in Statistical Forecasting of Solar Proton Events: A Machine Learning Perspective

et al. 2021

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 58%

Section: Discussionmentioning

confidence: 99%

“…Very recently, Lavasa et al. (2021), also treated the inherently imbalanced problem of SPE binary prediction. Thus, independently, different authors (i.e., Lavasa et al.…”

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

See 2 more Smart Citations

Open Issues in Statistical Forecasting of Solar Proton Events: A Machine Learning Perspective

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Predictions of SEPs have also been explored with a number of physics-based (e.g., Marsh et al, 2015;Schwadron et al, 2010;Zhang and Zhao, 2017), empirical (e.g., Anastasiadis et al, 2017;Bruno and Richardson, 2021;Posner , 2007;Richardson et al, 2018), and machine learning (e.g., Kasapis et al, 2022;Lavasa et al, 2021;Stumpo et al, 2021) models, some of which can additionally be coupled with coronal and/or heliospheric MHD simulations to investigate time-dependent particle acceleration (e.g., Wijsen et al, 2021;Young et al, 2021). International efforts (see, e.g., the SEP Validation Team: https://ccmc.gsfc.nasa.gov/assessment/topics/helio-sep.php) are underway to assess the current status of SEP forecasting and to establish community-wide metrics.…”

Section: Introductionmentioning

confidence: 99%

CMEs and SEPs During November-December 2020: A Challenge for Real-Time Space Weather Forecasting

Palmerio,

Lee,

Mays

et al. 2022

Preprint

View full text Add to dashboard Cite

Predictions of coronal mass ejections (CMEs) and solar energetic particles (SEPs) are a central issue in space weather forecasting. In recent years, interest in space weather predictions has expanded to include impacts at other planets beyond Earth as well as spacecraft scattered throughout the heliosphere. In this sense, the scope of space weather science now encompasses the whole heliospheric system, and multi-point measurements of solar transients can provide useful insights and validations for prediction models. In this work, we aim to analyse the whole inner heliospheric context between two eruptive flares that took place in late 2020, i.e. the M4.4 flare of November 29 and the C7.4 flare of December 7. This period is especially interesting because the STEREO-A spacecraft was located ∼60 • east of the Sun-Earth line, giving us the opportunity to test the capabilities of "predictions at 360 • " using remote-sensing observations from the Lagrange L1 and L5 points as input. We simulate the CMEs that were ejected during our period of interest and the SEPs accelerated by their shocks using the WSA-Enlil-SEPMOD modelling chain and four sets of input parameters, forming a "mini-ensemble". We validate our results using in-situ observations at six locations, including Earth and Mars. We find that, despite some limitations arising from the models' architecture and assumptions, CMEs and shock-accelerated SEPs can be reasonably studied and forecast in real time at least out to several tens of degrees away from the eruption site using the prediction tools employed here. Plain Language SummaryCoronal mass ejections (CMEs) and solar energetic particles (SEPs) are phenomena from the Sun that are able to cause significant disturbances at Earth and other planets. Reliable predictions of these events and their effects are amongst the major goals of space weather forecasts, which aim to tackle all processes related to solar activity that can endanger human technology and society. In recent years, the breadth of space weather science has started to encompass other locations than Earth, ranging from all solar system planets to spacecraft scattered throughout space. In this work, we test our current capabilities in predicting space weather events in the inner solar system (i.e., within the orbit of Mars) for a period in late 2020. We use a chain of models that are able to simulate the background solar wind as well as transient phenomena such as CMEs and SEPs, and compare our results with spacecraft measurements from six well-separated locations, including Earth and Mars. We find that our current forecasting tools, despite their limitations, can successfully provide reasonable predictions of both CMEs and SEPs, especially out to several tens of degrees around the corresponding eruption source region on the Sun.

show abstract

Machine learning in solar physics

Ramos

Cheung

Chifu

et al. 2023

Living Rev Sol Phys

View full text Add to dashboard Cite

The application of machine learning in solar physics has the potential to greatly enhance our understanding of the complex processes that take place in the atmosphere of the Sun. By using techniques such as deep learning, we are now in the position to analyze large amounts of data from solar observations and identify patterns and trends that may not have been apparent using traditional methods. This can help us improve our understanding of explosive events like solar flares, which can have a strong effect on the Earth environment. Predicting hazardous events on Earth becomes crucial for our technological society. Machine learning can also improve our understanding of the inner workings of the sun itself by allowing us to go deeper into the data and to propose more complex models to explain them. Additionally, the use of machine learning can help to automate the analysis of solar data, reducing the need for manual labor and increasing the efficiency of research in this field.

show abstract

Assessing the Predictability of Solar Energetic Particles with the Use of Machine Learning Techniques

Cited by 24 publications

References 54 publications

Open Issues in Statistical Forecasting of Solar Proton Events: A Machine Learning Perspective

Open Issues in Statistical Forecasting of Solar Proton Events: A Machine Learning Perspective

CMEs and SEPs During November-December 2020: A Challenge for Real-Time Space Weather Forecasting

Machine learning in solar physics

Contact Info

Product

Resources

About