A5004506519- Solar and Space Plasma Dynamics
- Global Energy and Sustainability Research
- Ionosphere and magnetosphere dynamics
- Solar Radiation and Photovoltaics
- Image Processing Techniques and Applications
- Geomagnetism and Paleomagnetism Studies
- Astro and Planetary Science
- Market Dynamics and Volatility
- Domain Adaptation and Few-Shot Learning
- Forecasting Techniques and Applications
- Robotic Path Planning Algorithms
- Bayesian Methods and Mixture Models
- Image Retrieval and Classification Techniques
- COVID-19 diagnosis using AI
- Machine Learning and Data Classification
- Spectroscopy Techniques in Biomedical and Chemical Research
- Machine Learning and Algorithms
- Atmospheric Ozone and Climate
- Photovoltaic System Optimization Techniques
- Stellar, planetary, and galactic studies
- Energy Load and Power Forecasting
- Industrial Vision Systems and Defect Detection
- Advanced Clustering Algorithms Research
Ames Research Center
2023-2024
University of Michigan
2020-2023
Goddard Space Flight Center
2023
KBR (United States)
2022
Solar Energetic Particle (SEP) events are interesting from a scientific perspective as they the product of broad set physical processes corona out through extent heliosphere, and provide insight into particle acceleration transport that widely applicable in astrophysics. From operations perspective, SEP pose radiation hazard for aviation, electronics space, human space exploration, particular missions outside Earth's protective magnetosphere including to Moon Mars. Thus, it is critical...
Abstract We use machine learning methods to predict whether an active region (AR) which produces flares will lead a solar energetic particle (SEP) event using Space‐Weather Michelson Doppler Imager (MDI) Active Region Patches (SMARPs). This new data product is derived from maps of the surface magnetic field taken by MDI aboard Solar and Heliospheric Observatory. survey SMARP regions associated with that appear on disk between 5 June 1996 14 August 2010, label those produced SEPs as positive...
Abstract Solar flare prediction studies have been recently conducted with the use of Space-Weather MDI (Michelson Doppler Imager on board and Heliospheric Observatory) Active Region Patches (SMARPs) HMI (Helioseismic Magnetic Dynamics (SHARPs), which are two currently available data products containing magnetic field characteristics solar active regions (ARs). The present work is an effort to combine them into one product, perform some initial statistical analyses in order further expand...
Abstract The prediction of solar energetic particle (SEP) events garners increasing interest as space missions extend beyond Earth’s protective magnetosphere. These events, which are, in most cases, products magnetic-reconnection-driven processes during flares or fast coronal-mass-ejection-driven shock waves, pose significant radiation hazards to aviation, space-based electronics, and particularly exploration. In this work, we utilize the recently developed data set that combines Solar...
Abstract To create early warning capabilities for upcoming Space Weather disturbances, we have selected a dataset of 61 emerging active regions, which allows us to identify characteristic features in the evolution acoustic power density predict continuum intensity emergence. For our study, utilized Doppler shift and observations from Helioseismic Magnetic Imager (HMI) onboard Solar Dynamics Observatory (SDO). The local tracking 30.66 × 30.66-degree patches vicinity regions allowed trace...
Solar flare prediction studies have been recently conducted with the use of Space-Weather MDI (Michelson Doppler Imager onboard and Heliospheric Observatory) Active Region Patches (SMARP) HMI (Helioseismic Magnetic Dynamics (SHARP), which are two currently available data products containing magnetic field characteristics solar active regions. The present work is an effort to combine them into one product, perform some initial statistical analyses in order further expand their application...
To create early warning capabilities for upcoming Space Weather disturbances, we have selected a dataset of 61 emerging active regions, which allows us to identify characteristic features in the evolution acoustic power density predict continuum intensity emergence. For our study, utilized Doppler shift and observations from Helioseismic Magnetic Imager (HMI) onboard Solar Dynamics Observatory (SDO). The local tracking 30.66 x 30.66-degree patches vicinity regions allowed trace starting...
Prediction of the Solar Energetic Particle (SEP) events garner increasing interest as space missions extend beyond Earth's protective magnetosphere. These events, which are, in most cases, products magnetic reconnection-driven processes during solar flares or fast coronal-mass-ejection-driven shock waves, pose significant radiation hazards to aviation, space-based electronics, and particularly, exploration. In this work, we utilize recently developed dataset that combines Dynamics...
We developed Long Short-Term Memory (LSTM) models to predict the formation of active regions (ARs) on solar surface. Using Doppler shift velocity, continuum intensity, and magnetic field observations from Solar Dynamics Observatory (SDO) Helioseismic Magnetic Imager (HMI), we have created time-series datasets acoustic power flux, which are used train LSTM predicting 12 hours in advance. These novel machine learning (ML) able capture variations density associated with upcoming flux emergence...
Abstract The Solar Dynamics Observatory (SDO) is a solar mission in an inclined geosynchronous orbit. Since commissioning, images acquired by Atmospheric Imaging Assembly (AIA) instrument on‐board the SDO have frequently displayed “spikes,” pixel regions yielding extreme number of digital counts. These are theorized to occur from energetic electron collisions with detector system. spikes regularly removed AIA Level 1.0 produce clean and reliable data. A study historical data has found over...
The exponential growth of digital image data has given rise to the need efficient content management and retrieval tools. Currently, there is a lack tools for processing collected unlabeled in schematic manner. K-means one most widely used clustering methods been applied variety fields, them being sorting. Although useful tool management, method heavily influenced by initializations, important know number clusters priori. A different have proposed identifying correct K-means, variance ratio...
In search, exploration, and reconnaissance tasks performed with autonomous ground vehicles, an image classification capability is needed for specifically identifying targeted objects (relevant classes) at the same time recognize when a candidate does not belong to anyone of relevant classes (irrelevant images). this paper, we present open-set low-shot classifier that uses, during its training, modest number (less than 40) labeled images each class, unlabeled irrelevant are randomly selected...
In search, exploration, and reconnaissance operations of autonomous ground vehicles, an image recognition capability is needed for specifically classifying targeted objects (relevant classes) at the same time identifying as unknown (irrelevant unseen) that do not belong to any known classes, opposed falsely them in one relevant classes. This paper integrates unsupervised learning feature extraction framework based on Instance Discrimination method with Open-Set Low-Shot (IDLS) classifier...
The Solar Dynamics Observatory (SDO) is a solar mission in an inclined geosynchronous orbit. Since commissioning, images acquired by Atmospheric Imaging Assembly (AIA) instrument on-board the SDO have frequently displayed “spikes”, pixel regions yielding extreme number of digital counts. These are theorized to occur from energetic electron collisions with detector system. spikes regularly removed AIA Level 1.0 produce clean and reliable data. A study historical data has found over 100...
Earth and Space Science Open Archive This work has been accepted for publication in Weather. Version of RecordESSOAr is a venue early communication or feedback before peer review. Data may be preliminary. Learn more about preprints. preprintOpen AccessYou are viewing the latest version by default [v1]Interpretable Machine Learning to Forecast SEP Events Solar Cycle 23AuthorsSpiridonKasapisiDLuluZhaoYangCheniDXiantongWangiDMonicaBobraiDTamas I. I.GombosiiDSee all authors Spiridon...