A New Tool for CME Arrival Time Prediction using Machine Learning Algorithms: CAT-PUMA

Liu, Jiajia; Ye, Yudong; Shen, Chenglong; Wang, Yuming; Erdélyi, R.

doi:10.3847/1538-4357/aaae69

Cited by 69 publications

(74 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Notable examples include the Effective Acceleration Model (Paouris & Mavromichalaki, 2017) and the Empirical Shock Arrival or Empirical CME Arrival (Gopalswamy et al, 2001). In a similar manner, machine learning techniques can be used to generate simple arrival time models (Liu et al, 2018).…”

Section: 1029/2019sw002382mentioning

confidence: 99%

Identifying Critical Input Parameters for Improving Drag‐Based CME Arrival Time Predictions

2020

View full text Add to dashboard Cite

Coronal mass ejections (CMEs) typically cause the strongest geomagnetic storms, so a major focus of space weather research has been predicting the arrival time of CMEs. Most arrival time models fall into two categories: (1) drag-based models that integrate the drag force between a simplified CME structure and the background solar wind and (2) full magnetohydrodynamic models. Drag-based models typically are much more computationally efficient than magnetohydrodynamic models, allowing for ensemble modeling. While arrival time predictions have improved since the earliest attempts, both types of models currently have difficulty achieving mean absolute errors below 10 hr. Here we use a drag-based model ANTEATR (Another Type of Ensemble Arrival Time Results) to explore the sensitivity of arrival times to various input parameters. We consider CMEs of different strengths from average to extreme size, speed, and mass (kinetic energies between 9 × 10 29 and 6 × 10 32 erg). For each scale CME, we vary the input parameters to reflect the current observational uncertainty in each and determine how accurately each must be known to achieve predictions that are accurate within 5 hr. We find that different scale CMEs are the most sensitive to different parameters. The transit time of average strength CMEs depends most strongly on the CME speed, whereas an extreme strength CME is the most sensitive to the angular width. A precise CME direction is critical for impacts near the flanks but not near the CME nose. We also show that the Drag-Based Model has similar sensitivities, suggesting that these results are representative for all drag-based models.Plain Language Summary Large explosions of plasma and magnetic field known as coronal mass ejections (CMEs) frequently erupt from the solar atmosphere. When CMEs head toward Earth, they interact with the near-Earth plasma and magnetic field, affecting the "space weather." CMEs typically cause the strongest space weather effects, so a major focus has been predicting the time it takes for a CME to propagate from the Sun to the Earth. Many models have been developed over the past decades to predict the arrival time of CMEs, but all have difficulty achieving absolute errors less than 10 hr. Here we use a simple model that integrates the drag force between a CME and the background solar wind. Due to the model's simplicity, we can run a large number of simulations, allowing us to explore how the arrival time changes as the various model inputs are changed. We consider CMEs of different strengths and find that the behavior differs between average and extreme CMEs. We determine the precision needed for each input parameter to achieve predictions that are accurate within 5 hr. We compare our results with those from a similar model. Both models exhibit the same sensitivity to the input parameters, suggesting that these results are representative for most drag-based models.Coronal mass ejections (CMEs) are large explosions of plasma and structured magnetic field that routinely erupt from the solar ...

show abstract

Section: 1029/2019sw002382mentioning

confidence: 99%

Identifying Critical Input Parameters for Improving Drag‐Based CME Arrival Time Predictions

2020

View full text Add to dashboard Cite

show abstract

“…Forecasting outcomes were mostly confined to images (e.g., Mukkavilli, Meger, & Dudek, with Mars images; Liu, Deng, Wang, & Wang, , Nishizuka et al, , Inceoglu et al, , and Florios et al, using Solar magnetograms), photometric measurements (French & Zabludoff, predicted likely tidal disruption events in post‐starburst galaxies using a RF algorithm) and catalogue data (forecasts of coronal mass ejections from the Sun based on ∼180 similar events using a SVM Liu, Ye, Shen, Wang, & Erdélyi, ). Generation methods, in particular generative adversarial network (GANs), have been used with images from observations (Vavilova, Elyiv, & Vasylenko, ), and to simplify or remove the need for expensive numerical simulation (e.g., Diakogiannis et al, ; Fussell & Moews, ; Rodríguez et al, ).…”

Section: Machine Learning and Artificial Intelligence In Astronomymentioning

confidence: 99%

Surveying the reach and maturity of machine learning and artificial intelligence in astronomy

Fluke

Jacobs

2019

WIREs Data Min & Knowl

113

View full text Add to dashboard Cite

Machine learning (automated processes that learn by example in order to classify, predict, discover, or generate new data) and artificial intelligence (methods by which a computer makes decisions or discoveries that would usually require human intelligence) are now firmly established in astronomy. Every week, new applications of machine learning and artificial intelligence are added to a growing corpus of work. Random forests, support vector machines, and neural networks are now having a genuine impact for applications as diverse as discovering extrasolar planets, transient objects, quasars, and gravitationally lensed systems, forecasting solar activity, and distinguishing between signals and instrumental effects in gravitational wave astronomy. This review surveys contemporary, published literature on machine learning and artificial intelligence in astronomy and astrophysics. Applications span seven main categories of activity: classification, regression, clustering, forecasting, generation, discovery, and the development of new scientific insights. These categories form the basis of a hierarchy of maturity, as the use of machine learning and artificial intelligence emerges, progresses, or becomes established. This article is categorized under: Application Areas > Science and Technology Fundamental Concepts of Data and Knowledge > Motivation and Emergence of Data Mining Technologies > Machine Learning

show abstract

“…[51] 、Zernike矩 [52] 、灰度共生矩阵 [69] 、复小波变换 [69] 、数学形态学 [73] 等图像分析和模式识别技术, 被 [74] 和SHARP(Space-Weather HMI Active Region Patches)数据集 [75] , 以及从 [42] 2018 CME到达时间估计 SOHO LASCO C2之前观测到的182个部分或全晕CME事件 SVM 预测误差约为5.9 h Inceoglu等人 [43] 2018 CME关联事件分析 2010-2018年的DONKI数据 SVM, MLP 基于18个活动区物理参数, 分析CME和SEPs的关联性, TSS约为0.91.…”

Section: 函数unclassified

The application of machine learning in solar physics

Liu

Jin

2019

Sci. Sin.-Phys. Mech. Astron.

View full text Add to dashboard Cite

A New Tool for CME Arrival Time Prediction using Machine Learning Algorithms: CAT-PUMA

Cited by 69 publications

References 80 publications

Identifying Critical Input Parameters for Improving Drag‐Based CME Arrival Time Predictions

Identifying Critical Input Parameters for Improving Drag‐Based CME Arrival Time Predictions

Surveying the reach and maturity of machine learning and artificial intelligence in astronomy

The application of machine learning in solar physics

Contact Info

Product

Resources

About