Berkay Aydin

Georgia State University | GSU · Department of Computer Science

Accurate and reliable predictions of solar flares are essential due to their potentially significant impact on Earth and space-based infrastructure. Although deep learning models have shown notable predictive capabilities in this domain, current evaluations often focus on accuracy while neglecting interpretability and reliability--factors that are...

Solar energetic particle (SEP) events are one of the most crucial aspects of space weather that require continuous monitoring and forecasting using robust methods. We demonstrate a proof of concept of using a data-driven supervised classification framework on a multivariate time-series data set covering solar cycles 22, 23, and 24. We implement ens...

Deep learning-based methods have been widely researched in the areas of language and vision, demonstrating their capacity to understand long sequences of data and their usefulness in numerous helio-physics applications. Foundation models (FMs), which are pre-trained on a large-scale datasets, form the basis for a variety of downstream tasks. These...

Traditional solar flare forecasting approaches have mostly relied on physics-based or data-driven models using solar magnetograms, treating flare predictions as a point-in-time classification problem. This approach has limitations, particularly in capturing the evolving nature of solar activity. Recognizing the limitations of traditional flare fore...

In this paper, we propose a novel loss function aimed at optimizing the binary flare prediction problem by embedding the intrinsic ordinal flare characteristics into the binary cross-entropy (BCE) loss function. This modification is intended to provide the model with better guidance based on the ordinal characteristics of the data and improve the o...

Solar energetic particle (SEP) events are one of the most crucial aspects of space weather that require continuous monitoring and forecasting using robust methods. We demonstrate a proof of concept of using a data-driven supervised classification framework on a multivariate time series data set covering solar cycles 22, 23, and 24. We implement ens...

In this paper, we introduce a novel methodology for leveraging shape-based characteristics of magnetograms of active region (AR) patches and provide a novel capability for predicting solar flares covering the entirety of the solar disk (AR patches spanning from -90$^{\circ}$ to +90$^{\circ}$ of solar longitude). We create three deep learning models...

Solar energetic particle (SEP) events are one of the most crucial aspects of space weather that require continuous monitoring and forecasting. Their prediction depends on various factors, including source eruptions. In the present work, we use the Geostationary Solar Energetic Particle data set covering solar cycles 22, 23, and 24. We develop a fra...

Aiming to assess the progress and current challenges on the formidable problem of the prediction of solar energetic events since the COSPAR/ International Living With a Star (ILWS) Roadmap paper of Schrijver et al. (2015), we attempt an overview of the current status of global research efforts. By solar energetic events we refer to flares, coronal...

Aiming to assess the progress and current challenges on the formidable problem of the prediction of solar energetic events since the COSPAR / International Living With a Star (ILWS) Roadmap paper of Schrijver et al. (2015), we attempt an overview of the current status of global research efforts. By solar energetic events we refer to flares, coronal...

Space weather events can have a significant impact on electric systems and health, with solar flares being one of the central events in space weather forecasting. However, existing solar flare prediction tools heavily rely on the Geostationary Operational Environmental Satellites (GOES) classification system , using maximum X-ray flux measurements...

Solar Energetic Particles (SEP) events are interesting from a scientific perspective as they are the product of a broad set of physical processes from the corona out through the extent of the heliosphere, and provide insight into processes of particle acceleration and transport that are widely applicable in astrophysics. From the operations perspec...

This paper presents a post hoc analysis of a deep learning-based full-disk solar flare prediction model. We used hourly full-disk line-of-sight magnetogram images and selected binary prediction mode to predict the occurrence of \(\ge \)M1.0-class flares within 24 h. We leveraged custom data augmentation and sample weighting to counter the inherent...

This study aims to evaluate the performance of deep learning models in predicting ≥M-class solar flares with a prediction window of 24 hours, using hourly sampled full-disk line-of-sight (LoS) magnetogram images, particularly focusing on the often overlooked flare events corresponding to the near-limb regions (beyond ±70 • of the solar disk). We tr...

Solar flares are transient space weather events that pose a significant threat to space and ground-based technological systems, making their precise and reliable prediction crucial for mitigating potential impacts. This paper contributes to the growing body of research on deep learning methods for solar flare prediction, primarily focusing on highl...

Solar flare prediction is a central problem in space weather forecasting and recent developments in machine learning and deep learning accelerated the adoption of complex models for data-driven solar flare forecasting. In this work, we developed an attention-based deep learning model as an improvement over the standard convolutional neural network...

This study progresses solar flare prediction research by presenting a full-disk deep-learning model to forecast $\geq$M-class solar flares and evaluating its efficacy on both central (within $\pm$70$^\circ$) and near-limb (beyond $\pm$70$^\circ$) events, showcasing qualitative assessment of post hoc explanations for the model's predictions, and pro...

Solar flare prediction is a central problem in space weather forecasting. Existing solar flare prediction tools are mainly dependent on the GOES classification system, and models commonly use a proxy of maximum (peak) X-ray flux measurement over a particular prediction window to label instances. However, the background X-ray flux dramatically fluct...

This paper presents a post hoc analysis of a deep learning-based full-disk solar flare prediction model. We used hourly full-disk line-of-sight magnetogram images and selected binary prediction mode to predict the occurrence of $\geq$M1.0-class flares within 24 hours. We leveraged custom data augmentation and sample weighting to counter the inheren...

This paper contributes to the growing body of research on deep learning methods for solar flare prediction, primarily focusing on highly overlooked near-limb flares and utilizing the attribution methods to provide a post hoc qualitative explanation of the model's predictions. We present a solar flare prediction model, which is trained using hourly...

Explaining and Evaluating the Deep Learning Model for Full-disk Solar Flare Prediction.

Magnetic polarity inversion lines (PILs) detected in solar active regions have long been recognized as arguably the most essential feature for triggering instabilities such as flares and eruptive events (i.e., eruptive flares and coronal mass ejections). In recent years, efforts have been focused on using features engineered from PILs for solar eru...

Solar flare prediction presents a significant challenge in space weather forecasting. Currently, existing solar flare prediction tools heavily rely on the GOES classification system. These tools commonly use the maximum X-ray flux measurement within a specific prediction window, often set at 24 hours, as a basis for labeling instances. However, the...

We present a catalog of solar energetic particle (SEP) events covering solar cycles 22, 23 and 24. We correlate and integrate three existing catalogs based on Geostationary Operational Environmental Satellite integral proton flux data. We visually verified and labeled each event in the catalog to provide a homogenized data set. We have identified a...

Solar flare prediction is a central problem in space weather forecasting and has captivated the attention of a wide spectrum of researchers due to recent advances in both remote sensing as well as machine learning and deep learning approaches. The experimental findings based on both machine and deep learning models reveal significant performance im...

Solar flare prediction is a central problem in space weather forecasting and has captivated the attention of a wide spectrum of researchers due to recent advances in both remote sensing as well as machine learning and deep learning approaches. The experimental findings based on both machine and deep learning models reveal significant performance im...

This poster presents methodologies on training deep learning architectures to predict occurrences of Solar Flares(M1.0+) for the next 24 hours. We use magnetogram active region patches, automatically detected and provided by Joint Science Operations Center (JSOC), as inputs to our models.

We present a catalog of solar energetic particle (SEP) events covering solar cycles 22, 23 and 24. We correlate and integrate three existing catalogs based on Geostationary Operational Environmental Satellite (GOES) integral proton flux data. We visually verified and labeled each event in the catalog to provide a homogenized data set. We have ident...

The efforts in solar flare prediction have been engendered by the advancements in machine learning and deep learning methods. We present a new approach to flare prediction using full-disk compressed magnetogram images with Convolutional Neural Networks. We selected three prediction modes, among which two are binary for predicting the occurrence of...

Solar energetic particle (SEP) events, as one of the most dangerous manifestations of solar activity, can generate severe hazardous radiation when accelerated by solar flares or shock waves formed aside coronal mass ejections (CMEs). Unlike common predictions that focus on the occurrence of an event, an All-Clear forecast puts more emphasis on pred...

We present a case study of solar flare forecasting by means of metadata feature time series, by treating it as a prominent class-imbalance and temporally coherent problem. Taking full advantage of pre-flare time series in solar active regions is made possible via the Space Weather Analytics for Solar Flares (SWAN-SF) benchmark data set, a partition...

An all-clear flare prediction is a type of solar flare forecasting that puts more emphasis on predicting non-flaring instances (often relatively small flares and flare quiet regions) with high precision while still maintaining valuable predictive results. While many flare prediction studies do not address this problem directly, all-clear prediction...

We present a case study of solar flare forecasting by means of metadata feature time series, by treating it as a prominent class-imbalance and temporally coherent problem. Taking full advantage of pre-flare time series in solar active regions is made possible via the Space Weather Analytics for Solar Flares (SWAN-SF) benchmark dataset; a partitione...

Spatiotemporal event sequences (STESs) are the ordered series of event types whose instances frequently follow each other in time and are located close-by. An STES is a spatiotemporal frequent pattern type, which is discovered from moving region objects whose polygon-based locations continiously evolve over time. Previous studies on STES mining req...

We have compiled a catalog of solar flares (SFs) as observed by the Extreme ultraviolet Imaging Telescope (EIT) on board the Solar and Heliospheric Observatory (SOHO) spacecraft and the Geostationary Operational Environmental Satellites (GOES) spacecraft over a span from 1997 to 2010. During mid-1998, the cadence of EIT images was revised from two...

We introduce and make openly accessible a comprehensive, multivariate time series (MVTS) dataset extracted from solar photospheric vector magnetograms in Spaceweather HMI Active Region Patch (SHARP) series. Our dataset also includes a cross-checked NOAA solar flare catalog that immediately facilitates solar flare prediction efforts. We discuss meth...

We have compiled a catalog of solar flares as observed by the Extreme ultraviolet Imaging Telescope (EIT) aboard the Solar and Heliospheric Observatory (SOHO) spacecraft and the GOES spacecraft over a span from 1997 to 2010. During mid-1998, the cadence of EIT images was revised from two images per day to 12 minutes. However, the low temporal resol...

We developed a domain-independent Python package to facilitate the preprocessing routines required in preparation of any multi-class, multivariate time series data. It provides a comprehensive set of 48 statistical features for extracting the important characteristics of time series. The feature extraction process is automated in a sequential and p...

The authors of this white paper met on 16-17 January 2020 at the New Jersey Institute of Technology, Newark, NJ, for a 2-day workshop that brought together a group of heliophysicists, data providers, expert modelers, and computer/data scientists. Their objective was to discuss critical developments and prospects of the application of machine and/or...

We present a case study for time series prediction models in extreme class-imbalance problems. We have extracted multiple properties from the Space Weather ANalytics for Solar Flares (SWAN-SF) benchmark dataset which comprises of magnetic features from over 4075 active regions over a period of 9 years to create the forecasting dataset used in this...

Machine learning-based space weather analytics has attracted much attention due to the potential damages that can be caused by the extreme space weather events. Using a recently released data benchmark, named SWAN-SF, designed for solar flare forecasting based on the pre-flare time series of solar magnetic field parameters, we conduct a case study...

In analyses of rare-events, regardless of the domain of application, class-imbalance issue is intrinsic. Although the challenges are known to data experts, their explicit impact on the analytic and the decisions made based on the findings are often overlooked. This is in particular prevalent in interdisciplinary research where the theoretical aspec...

In analyses of rare-events, regardless of the domain of application, class-imbalance issue is intrinsic. Although the challenges are known to data experts, their explicit impact on the analytic and the decisions made based on the findings are often overlooked. This is in particular prevalent in interdisciplinary research where the theoretical aspec...

The authors of this report met on 28-30 March 2018 at the New Jersey Institute of Technology, Newark, New Jersey, for a 3-day workshop that brought together a group of data providers, expert modelers, and computer and data scientists, in the solar discipline. Their objective was to identify challenges in the path towards building an effective frame...

Spatiotemporal data mining refers to the extraction of knowledge, regularly repeating relationships, and interesting patterns from data with spatial and temporal aspects. In recent years, many spatiotemporal frequent pattern mining algorithms were developed for spatiotemporal event instances represented by a series of region objects that evolves ov...

The comprehensive set of neuronal connections of the human brain, which is known as the human connectomes, have been widely used in the research of neurological and neurodevelopmental disorders. Functional Magnetic Resonance Imaging (fMRI) has facilitated the research by capturing functional activities of the neurons. fMRI-based functional connec-t...

k Nearest Neighbor (kNN) is a widely used classifier in time series data analytics due to its interpretability. kNN is often referred to as a lazy learning algorithm as it does not learn any discriminative function nor does it generate any rules from the training data. Instead, kNN classifier requires a search over all the training data for classif...

This paper introduces four spatiotemporal interpolation methods that enrich complex, evolving region trajectories that are reported from a variety of ground-based and space-based solar observatories every day. Our interpolation module takes an existing solar event trajectory as its input and generates an enriched trajectory with any number of addit...

Spatiotemporal event sequences are the ordered series of event types. These event types represent the types of evolving region trajectory based instances that follow each other. The goal of spatiotemporal event sequence mining is finding frequently occurring sequences of event types from the follow relationships among all event instances. The key a...

Given a dataset of event instances which are represented as trajectories of evolving region trajectories, spatiotemporal co-occurrence patterns (STCOPs) can be defined as subsets of event types, whose instances frequently co-occur in both space and time. STCOPs are the first type of spatiotemporal frequent patterns, we will derive from the evolving...

In this chapter, we will explore the spatiotemporal relationships occurring among the spatiotemporal objects. These relationships have their roots in topological spatial and temporal relationships presented over many data mining studies. In essence, these relationships are the building blocks of the spatiotemporal frequent pattern mining from evolv...

An important aspect of data mining research is the determination of the interestingness of patterns. In classical frequent pattern mining tasks (e.g., shopping basket analysis), the main goal is to identify items (e.g., types of purchased goods) frequently appearing together in an itemset (e.g., shopping cart). Such analyses require an appropriate...

In this chapter, we will focus on the spatiotemporal object modeling and put special attention on the moving objects with extended geometric representations. Our spatiotemporal frequent pattern mining algorithms primarily make use of region trajectories whose polygon-based region representations continuously evolve over time. In the rest of this ch...

Solar energetic particles are a result of intense solar events such as solar flares and Coronal Mass Ejections (CMEs). These latter events all together can cause major disruptions to spacecraft that are in Earth's orbit and outside of the magnetosphere. In this work we are interested in establishing the necessary conditions for a major geo-effectiv...