{"id":{"repo_id":"utahstate","oai_identifier":"oai:digitalcommons.usu.edu:etd-9282"},"canonical_url":"https://search.ndltd.org/etd/utahstate/oai:digitalcommons.usu.edu:etd-9282","repository":{"repo_id":"utahstate","name":"Utah State University","base_url":"https://digitalcommons.usu.edu/do/oai/"},"display":{"title":"Comparative Study of Machine Learning Models on Solar Flare Prediction Problem","abstract":"Solar flare events are explosions of energy and radiation from the Sun’s surface. These events occur due to the tangling and twisting of magnetic fields associated with sunspots. When Coronal Mass ejections accompany solar flares, solar storms could travel towards earth at very high speeds, disrupting all earthly technologies and posing radiation hazards to astronauts. For this reason, the prediction of solar flares has become a crucial aspect of forecasting space weather. Our thesis utilized the time-series data consisting of active solar region magnetic field parameters acquired from SDO that span more than eight years. The classification models take AR data from an observation period of 12 hours as input to predict the occurrence of flare in next 24 hours. We performed preprocessing and feature selection to find optimal feature space consisting of 28 active region parameters that made our multivariate time series dataset (MVTS). For the first time, we modeled the flare prediction task as a 4-class problem and explored a comprehensive set of machine learning models to identify the most suitable model. This research achieved a state-of-the-art true skill statistic (TSS) of 0.92 with a 99.9% recall of X-/M- class flares on our time series forest model. This was accomplished with the augmented dataset in which the minority class is over-sampled using synthetic samples generated by SMOTE and the majority classes are randomly under-sampled. This work has established a robust dataset and baseline models for future studies in this task, including experiments on remedies to tackle the class imbalance problem such as weighted cost functions and data augmentation. Also the time series classifiers implemented will enable shapelets mining that can provide interpreting ability to domain experts.","abstract_html":"Solar flare events are explosions of energy and radiation from the Sun’s surface. These events occur due to the tangling and twisting of magnetic fields associated with sunspots. When Coronal Mass ejections accompany solar flares, solar storms could travel towards earth at very high speeds, disrupting all earthly technologies and posing radiation hazards to astronauts. For this reason, the prediction of solar flares has become a crucial aspect of forecasting space weather. Our thesis utilized the time-series data consisting of active solar region magnetic field parameters acquired from SDO that span more than eight years. The classification models take AR data from an observation period of 12 hours as input to predict the occurrence of flare in next 24 hours. We performed preprocessing and feature selection to find optimal feature space consisting of 28 active region parameters that made our multivariate time series dataset (MVTS). For the first time, we modeled the flare prediction task as a 4-class problem and explored a comprehensive set of machine learning models to identify the most suitable model. This research achieved a state-of-the-art true skill statistic (TSS) of 0.92 with a 99.9% recall of X-/M- class flares on our time series forest model. This was accomplished with the augmented dataset in which the minority class is over-sampled using synthetic samples generated by SMOTE and the majority classes are randomly under-sampled. This work has established a robust dataset and baseline models for future studies in this task, including experiments on remedies to tackle the class imbalance problem such as weighted cost functions and data augmentation. Also the time series classifiers implemented will enable shapelets mining that can provide interpreting ability to domain experts.","abstract_has_math":false,"creators":["Kurivella, Nikhil Sai"],"institution":"Hosted by Utah State University Libraries","degree_name":"Master of Science (MS)","degree_level":"Thesis","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":["Soukaina Filali Boubrahimi","Nicholas Flann","Curtis Dyreson"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T08:52:35Z","subjects":["Solar flare prediction","Synthetic samples","Comparative Analysis","Machine learning","Time series classifiers","Time series forest","space weather prediction","exploratory space weather data mining","feature selection","Computer Sciences","Physical Sciences and Mathematics"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/a10e-ca5b"],"render_values":[{"text":"https://doi.org/10.26076/a10e-ca5b","href":"https://doi.org/10.26076/a10e-ca5b","code":true}]}],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usu.edu/etd/8140","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usu.edu/etd/8140","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.usu.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usu.edu%3Aetd-9282","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Soukaina Filali Boubrahimi","Nicholas Flann","Curtis Dyreson"]},{"key":"dc:creator","label":"Author","values":["Kurivella, Nikhil Sai"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2010-01-01T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2021-08-01T07:00:00Z"]},{"key":"dc:publisher","label":"Institution","values":["Hosted by Utah State University Libraries"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science (MS)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Solar flare prediction","Synthetic samples","Comparative Analysis","Machine learning","Time series classifiers","Time series forest","space weather prediction","exploratory space weather data mining","feature selection","Computer Sciences","Physical Sciences and Mathematics"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usu.edu/etd/8140"]},{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.26076/a10e-ca5b"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Solar flare events are explosions of energy and radiation from the Sun’s surface. These events occur due to the tangling and twisting of magnetic fields associated with sunspots. When Coronal Mass ejections accompany solar flares, solar storms could travel towards earth at very high speeds, disrupting all earthly technologies and posing radiation hazards to astronauts. For this reason, the prediction of solar flares has become a crucial aspect of forecasting space weather. Our thesis utilized the time-series data consisting of active solar region magnetic field parameters acquired from SDO that span more than eight years. The classification models take AR data from an observation period of 12 hours as input to predict the occurrence of flare in next 24 hours. We performed preprocessing and feature selection to find optimal feature space consisting of 28 active region parameters that made our multivariate time series dataset (MVTS). For the first time, we modeled the flare prediction task as a 4-class problem and explored a comprehensive set of machine learning models to identify the most suitable model. This research achieved a state-of-the-art true skill statistic (TSS) of 0.92 with a 99.9% recall of X-/M- class flares on our time series forest model. This was accomplished with the augmented dataset in which the minority class is over-sampled using synthetic samples generated by SMOTE and the majority classes are randomly under-sampled. This work has established a robust dataset and baseline models for future studies in this task, including experiments on remedies to tackle the class imbalance problem such as weighted cost functions and data augmentation. Also the time series classifiers implemented will enable shapelets mining that can provide interpreting ability to domain experts."]},{"key":"dc:title","label":"Title","values":["Comparative Study of Machine Learning Models on Solar Flare Prediction Problem"]}]}],"canonical_facts":{"dc:contributor":["Soukaina Filali Boubrahimi","Nicholas Flann","Curtis Dyreson"],"dc:creator":["Kurivella, Nikhil Sai"],"dc:date.available":["2010-01-01T08:00:00Z"],"dc:date.created":["2021-08-01T07:00:00Z"],"dc:description.abstract":["Solar flare events are explosions of energy and radiation from the Sun’s surface. These events occur due to the tangling and twisting of magnetic fields associated with sunspots. When Coronal Mass ejections accompany solar flares, solar storms could travel towards earth at very high speeds, disrupting all earthly technologies and posing radiation hazards to astronauts. For this reason, the prediction of solar flares has become a crucial aspect of forecasting space weather. Our thesis utilized the time-series data consisting of active solar region magnetic field parameters acquired from SDO that span more than eight years. The classification models take AR data from an observation period of 12 hours as input to predict the occurrence of flare in next 24 hours. We performed preprocessing and feature selection to find optimal feature space consisting of 28 active region parameters that made our multivariate time series dataset (MVTS). For the first time, we modeled the flare prediction task as a 4-class problem and explored a comprehensive set of machine learning models to identify the most suitable model. This research achieved a state-of-the-art true skill statistic (TSS) of 0.92 with a 99.9% recall of X-/M- class flares on our time series forest model. This was accomplished with the augmented dataset in which the minority class is over-sampled using synthetic samples generated by SMOTE and the majority classes are randomly under-sampled. This work has established a robust dataset and baseline models for future studies in this task, including experiments on remedies to tackle the class imbalance problem such as weighted cost functions and data augmentation. Also the time series classifiers implemented will enable shapelets mining that can provide interpreting ability to domain experts."],"dc:identifier":["https://digitalcommons.usu.edu/etd/8140"],"dc:identifier.doi":["https://doi.org/10.26076/a10e-ca5b"],"dc:publisher":["Hosted by Utah State University Libraries"],"dc:subject":["Solar flare prediction","Synthetic samples","Comparative Analysis","Machine learning","Time series classifiers","Time series forest","space weather prediction","exploratory space weather data mining","feature selection","Computer Sciences","Physical Sciences and Mathematics"],"dc:title":["Comparative Study of Machine Learning Models on Solar Flare Prediction Problem"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["Master of Science (MS)"]},"updated_at":"2026-11-19T08:52:35Z"}