Fatemeh Fazel Hesar, Bernard Foing, Ana M. Heras, Mojtaba Raouf, Victoria Foing, Shima Javanmardi, Fons J. Verbeek
{"title":"推进恒星活动和系外行星周期旋转的机器学习","authors":"Fatemeh Fazel Hesar, Bernard Foing, Ana M. Heras, Mojtaba Raouf, Victoria Foing, Shima Javanmardi, Fons J. Verbeek","doi":"arxiv-2409.05482","DOIUrl":null,"url":null,"abstract":"This study applied machine learning models to estimate stellar rotation\nperiods from corrected light curve data obtained by the NASA Kepler mission.\nTraditional methods often struggle to estimate rotation periods accurately due\nto noise and variability in the light curve data. The workflow involved using\ninitial period estimates from the LS-Periodogram and Transit Least Squares\ntechniques, followed by splitting the data into training, validation, and\ntesting sets. We employed several machine learning algorithms, including\nDecision Tree, Random Forest, K-Nearest Neighbors, and Gradient Boosting, and\nalso utilized a Voting Ensemble approach to improve prediction accuracy and\nrobustness. The analysis included data from multiple Kepler IDs, providing detailed\nmetrics on orbital periods and planet radii. Performance evaluation showed that\nthe Voting Ensemble model yielded the most accurate results, with an RMSE\napproximately 50\\% lower than the Decision Tree model and 17\\% better than the\nK-Nearest Neighbors model. The Random Forest model performed comparably to the\nVoting Ensemble, indicating high accuracy. In contrast, the Gradient Boosting\nmodel exhibited a worse RMSE compared to the other approaches. Comparisons of\nthe predicted rotation periods to the photometric reference periods showed\nclose alignment, suggesting the machine learning models achieved high\nprediction accuracy. The results indicate that machine learning, particularly\nensemble methods, can effectively solve the problem of accurately estimating\nstellar rotation periods, with significant implications for advancing the study\nof exoplanets and stellar astrophysics.","PeriodicalId":501068,"journal":{"name":"arXiv - PHYS - Solar and Stellar Astrophysics","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Advancing Machine Learning for Stellar Activity and Exoplanet Period Rotation\",\"authors\":\"Fatemeh Fazel Hesar, Bernard Foing, Ana M. Heras, Mojtaba Raouf, Victoria Foing, Shima Javanmardi, Fons J. Verbeek\",\"doi\":\"arxiv-2409.05482\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This study applied machine learning models to estimate stellar rotation\\nperiods from corrected light curve data obtained by the NASA Kepler mission.\\nTraditional methods often struggle to estimate rotation periods accurately due\\nto noise and variability in the light curve data. The workflow involved using\\ninitial period estimates from the LS-Periodogram and Transit Least Squares\\ntechniques, followed by splitting the data into training, validation, and\\ntesting sets. We employed several machine learning algorithms, including\\nDecision Tree, Random Forest, K-Nearest Neighbors, and Gradient Boosting, and\\nalso utilized a Voting Ensemble approach to improve prediction accuracy and\\nrobustness. The analysis included data from multiple Kepler IDs, providing detailed\\nmetrics on orbital periods and planet radii. Performance evaluation showed that\\nthe Voting Ensemble model yielded the most accurate results, with an RMSE\\napproximately 50\\\\% lower than the Decision Tree model and 17\\\\% better than the\\nK-Nearest Neighbors model. The Random Forest model performed comparably to the\\nVoting Ensemble, indicating high accuracy. In contrast, the Gradient Boosting\\nmodel exhibited a worse RMSE compared to the other approaches. Comparisons of\\nthe predicted rotation periods to the photometric reference periods showed\\nclose alignment, suggesting the machine learning models achieved high\\nprediction accuracy. The results indicate that machine learning, particularly\\nensemble methods, can effectively solve the problem of accurately estimating\\nstellar rotation periods, with significant implications for advancing the study\\nof exoplanets and stellar astrophysics.\",\"PeriodicalId\":501068,\"journal\":{\"name\":\"arXiv - PHYS - Solar and Stellar Astrophysics\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - PHYS - Solar and Stellar Astrophysics\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.05482\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - PHYS - Solar and Stellar Astrophysics","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.05482","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
这项研究应用机器学习模型从美国宇航局开普勒任务获得的校正光曲线数据中估算恒星的自转周期。工作流程包括使用 LS-Periodogram 和 Transit Least Squarestechniques 得出的初始周期估计值,然后将数据分成训练集、验证集和测试集。我们使用了几种机器学习算法,包括决策树、随机森林、K-近邻和梯度提升,还使用了投票集合方法来提高预测准确性和稳健性。分析包括来自多个开普勒 ID 的数据,提供了轨道周期和行星半径的详细指标。性能评估结果表明,投票集合模型产生了最准确的结果,其均方误差比决策树模型低约50%,比K-近邻模型好17%。随机森林模型的表现与投票集合模型相当,显示出较高的准确性。相比之下,梯度提升模型的均方根误差比其他方法要小。预测的旋转周期与光度参考周期的比较显示两者接近,表明机器学习模型达到了较高的预测精度。结果表明,机器学习,尤其是集合方法,可以有效地解决准确估计恒星旋转周期的问题,对推动系外行星和恒星天体物理学的研究具有重要意义。
Advancing Machine Learning for Stellar Activity and Exoplanet Period Rotation
This study applied machine learning models to estimate stellar rotation
periods from corrected light curve data obtained by the NASA Kepler mission.
Traditional methods often struggle to estimate rotation periods accurately due
to noise and variability in the light curve data. The workflow involved using
initial period estimates from the LS-Periodogram and Transit Least Squares
techniques, followed by splitting the data into training, validation, and
testing sets. We employed several machine learning algorithms, including
Decision Tree, Random Forest, K-Nearest Neighbors, and Gradient Boosting, and
also utilized a Voting Ensemble approach to improve prediction accuracy and
robustness. The analysis included data from multiple Kepler IDs, providing detailed
metrics on orbital periods and planet radii. Performance evaluation showed that
the Voting Ensemble model yielded the most accurate results, with an RMSE
approximately 50\% lower than the Decision Tree model and 17\% better than the
K-Nearest Neighbors model. The Random Forest model performed comparably to the
Voting Ensemble, indicating high accuracy. In contrast, the Gradient Boosting
model exhibited a worse RMSE compared to the other approaches. Comparisons of
the predicted rotation periods to the photometric reference periods showed
close alignment, suggesting the machine learning models achieved high
prediction accuracy. The results indicate that machine learning, particularly
ensemble methods, can effectively solve the problem of accurately estimating
stellar rotation periods, with significant implications for advancing the study
of exoplanets and stellar astrophysics.