This article aims to investigate the points of equilibrium and the associated convergence basins in a seventh-order generalized Hénon–Heiles potential. Using the well-known Newton–Raphson iterator, we numerically locate the positions of the points of equilibrium, while we also obtain their linear stability. Furthermore, we demonstrate how the two variable parameters, entering the generalized Hénon–Heiles potential, affect the convergence dynamics of the system as well as the fractal degree of the basin diagrams. The fractal degree is derived by computing the (boundary) basin entropy as well as the uncertainty dimension.
{"title":"Fractal Basins of Convergence of a Seventh-Order Generalized Hénon–Heiles Potential","authors":"E. Zotos, F. L. Dubeibe, A. Riano-Doncel","doi":"10.1155/2021/6665238","DOIUrl":"https://doi.org/10.1155/2021/6665238","url":null,"abstract":"This article aims to investigate the points of equilibrium and the associated convergence basins in a seventh-order generalized Hénon–Heiles potential. Using the well-known Newton–Raphson iterator, we numerically locate the positions of the points of equilibrium, while we also obtain their linear stability. Furthermore, we demonstrate how the two variable parameters, entering the generalized Hénon–Heiles potential, affect the convergence dynamics of the system as well as the fractal degree of the basin diagrams. The fractal degree is derived by computing the (boundary) basin entropy as well as the uncertainty dimension.","PeriodicalId":48962,"journal":{"name":"Advances in Astronomy","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2020-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48042712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. Priyatikanto, Lidia Mayangsari, Rudi A. Prihandoko, A. Admiranto
Sky brightness measuring and monitoring are required to mitigate the negative effect of light pollution as a byproduct of modern civilization. Good handling of a pile of sky brightness data includes evaluation and classification of the data according to its quality and characteristics such that further analysis and inference can be conducted properly. This study aims to develop a classification model based on Random Forest algorithm and to evaluate its performance. Using sky brightness data from 1250 nights with minute temporal resolution acquired at eight different stations in Indonesia, datasets consisting of 15 features were created to train and test the model. Those features were extracted from the observation time, the global statistics of nightly sky brightness, or the light curve characteristics. Among those features, 10 are considered to be the most important for the classification task. The model was trained to classify the data into six classes (1: peculiar data, 2: overcast, 3: cloudy, 4: clear, 5: moonlit-cloudy, and 6: moonlit-clear) and then tested to achieve high accuracy (92%) and scores (F-score = 84% and G-mean = 84%). Some misclassifications exist, but the classification results are considerably good as indicated by posterior distributions of the sky brightness as a function of classes. Data classified as class-4 have sharp distribution with typical full width at half maximum of 1.5 mag/arcsec2, while distributions of class-2 and -3 are left skewed with the latter having lighter tail. Due to the moonlight, distributions of class-5 and -6 data are more smeared or have larger spread. These results demonstrate that the established classification model is reasonably good and consistent.
{"title":"Classification of Continuous Sky Brightness Data Using Random Forest","authors":"R. Priyatikanto, Lidia Mayangsari, Rudi A. Prihandoko, A. Admiranto","doi":"10.1155/2020/5102065","DOIUrl":"https://doi.org/10.1155/2020/5102065","url":null,"abstract":"Sky brightness measuring and monitoring are required to mitigate the negative effect of light pollution as a byproduct of modern civilization. Good handling of a pile of sky brightness data includes evaluation and classification of the data according to its quality and characteristics such that further analysis and inference can be conducted properly. This study aims to develop a classification model based on Random Forest algorithm and to evaluate its performance. Using sky brightness data from 1250 nights with minute temporal resolution acquired at eight different stations in Indonesia, datasets consisting of 15 features were created to train and test the model. Those features were extracted from the observation time, the global statistics of nightly sky brightness, or the light curve characteristics. Among those features, 10 are considered to be the most important for the classification task. The model was trained to classify the data into six classes (1: peculiar data, 2: overcast, 3: cloudy, 4: clear, 5: moonlit-cloudy, and 6: moonlit-clear) and then tested to achieve high accuracy (92%) and scores (F-score = 84% and G-mean = 84%). Some misclassifications exist, but the classification results are considerably good as indicated by posterior distributions of the sky brightness as a function of classes. Data classified as class-4 have sharp distribution with typical full width at half maximum of 1.5 mag/arcsec2, while distributions of class-2 and -3 are left skewed with the latter having lighter tail. Due to the moonlight, distributions of class-5 and -6 data are more smeared or have larger spread. These results demonstrate that the established classification model is reasonably good and consistent.","PeriodicalId":48962,"journal":{"name":"Advances in Astronomy","volume":"2020 1","pages":"5102065"},"PeriodicalIF":1.4,"publicationDate":"2020-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1155/2020/5102065","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44067769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
When the Large Hadron Collider resumes operations in 2021, several experiments will directly measure the motion of antihydrogen in free fall for the first time. Our current understanding of the universe is not yet fully prepared for the possibility that antimatter has negative gravitational mass. This paper proposes a model of cosmology, where the state of high energy density of the big bang is created by the collapse of an antineutrino star that has exceeded its Chandrasekhar limit. To allow the first neutrino stars and antineutrino stars to form naturally from an initial quantum vacuum state, it helps to assume that antimatter has negative gravitational mass. This assumption may also be helpful to identify dark energy. The degenerate remnant of an antineutrino star can today have an average mass density that is similar to the dark energy density of the ΛCDM model. When in hydrostatic equilibrium, this antineutrino star remnant can emit isothermal cosmic microwave background radiation and accelerate matter radially. This model and the ΛCDM model are in similar quantitative agreement with supernova distance measurements. Therefore, this model is useful as a purely academic exercise and as preparation for possible future discoveries.
{"title":"Fermi Degenerate Antineutrino Star Model of Dark Energy","authors":"T. Neiser","doi":"10.1155/2020/8654307","DOIUrl":"https://doi.org/10.1155/2020/8654307","url":null,"abstract":"When the Large Hadron Collider resumes operations in 2021, several experiments will directly measure the motion of antihydrogen in free fall for the first time. Our current understanding of the universe is not yet fully prepared for the possibility that antimatter has negative gravitational mass. This paper proposes a model of cosmology, where the state of high energy density of the big bang is created by the collapse of an antineutrino star that has exceeded its Chandrasekhar limit. To allow the first neutrino stars and antineutrino stars to form naturally from an initial quantum vacuum state, it helps to assume that antimatter has negative gravitational mass. This assumption may also be helpful to identify dark energy. The degenerate remnant of an antineutrino star can today have an average mass density that is similar to the dark energy density of the ΛCDM model. When in hydrostatic equilibrium, this antineutrino star remnant can emit isothermal cosmic microwave background radiation and accelerate matter radially. This model and the ΛCDM model are in similar quantitative agreement with supernova distance measurements. Therefore, this model is useful as a purely academic exercise and as preparation for possible future discoveries.","PeriodicalId":48962,"journal":{"name":"Advances in Astronomy","volume":"2020 1","pages":"8654307"},"PeriodicalIF":1.4,"publicationDate":"2020-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1155/2020/8654307","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49148691","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
!e Sun is the energy source of the Earth. !e electromagnetic environment of the Earth is affected by solar activity, and the impact of violent activity bursts can reach the Earth within eight minutes. Hence the detection, recognition, and prediction of solar activity are essential. !e physical mechanisms of solar activity bursts are not yet completely clear. However, a large number of data have been accumulated and solar observation instruments can record the multiwavelength imaging data every day with high cadence. In order to cope with the rapidly growing amount of solar data, there is an increasing need for automatic detection and prediction technologies. !is special issue is focused on solar data mining technology. We invited authors to contribute with original research articles in this special issue. Eleven original research manuscripts have been received. After the peer-reviewed process, seven of them were accepted for publications. !erein, three papers focused on the detection and recognition of regions of interest in the solar images, two papers presented research on the short-term and midterm solar activity prediction, respectively, and one paper discussed the influence of solar activity on economic activities. From these articles, we can find that the machine learning methods, especially the deep learning methods, play an important role in solar activity monitoring and prediction. Finally, we hope that researchers will find this special issue useful. Conflicts of Interest
{"title":"Big Data Processing and Modeling in Solar Physics","authors":"X. Huang, I. Usoskin, L. Zhang, H. N. Wang","doi":"10.1155/2020/6967925","DOIUrl":"https://doi.org/10.1155/2020/6967925","url":null,"abstract":"!e Sun is the energy source of the Earth. !e electromagnetic environment of the Earth is affected by solar activity, and the impact of violent activity bursts can reach the Earth within eight minutes. Hence the detection, recognition, and prediction of solar activity are essential. !e physical mechanisms of solar activity bursts are not yet completely clear. However, a large number of data have been accumulated and solar observation instruments can record the multiwavelength imaging data every day with high cadence. In order to cope with the rapidly growing amount of solar data, there is an increasing need for automatic detection and prediction technologies. !is special issue is focused on solar data mining technology. We invited authors to contribute with original research articles in this special issue. Eleven original research manuscripts have been received. After the peer-reviewed process, seven of them were accepted for publications. !erein, three papers focused on the detection and recognition of regions of interest in the solar images, two papers presented research on the short-term and midterm solar activity prediction, respectively, and one paper discussed the influence of solar activity on economic activities. From these articles, we can find that the machine learning methods, especially the deep learning methods, play an important role in solar activity monitoring and prediction. Finally, we hope that researchers will find this special issue useful. Conflicts of Interest","PeriodicalId":48962,"journal":{"name":"Advances in Astronomy","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2020-03-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1155/2020/6967925","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42933702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jacob Oloketuyi, Yu Liu, Amobichukwu Chukwudi Amanambu, M. Zhao
To investigate the periodic behaviour and relationship of sunspot numbers with cosmic ray intensity and solar wind speed, we present analysis from daily data generated from 1995 January to 2018 December. Cross-correlation and wavelet transform tools were employed to carry out the investigation. The analyses confirmed that the cosmic ray intensity correlates negatively with the sunspot numbers, exhibiting an asynchronous phase relationship with a strong negative correlation. The trend in cosmic ray intensity indicates that it undergoes the 11-year modulation that mainly depends on the solar activity in the heliosphere. On the other hand, the solar wind speed neither shows a clear phase relationship nor correlates with the sunspot numbers but shows a wide range of periodicities that could possibly be connected to the pattern of coronal hole configuration. A number of short and midterm variations were also observed from the wavelet analysis, i.e., 64–128 and 128–256 days for the cosmic ray intensity, 4–8, 32–64, 128–256, and 256–512 days for the solar wind speed, and 16–32, 32–64, 128–256, and 256–512 days for the sunspot numbers.
{"title":"Responses and Periodic Variations of Cosmic Ray Intensity and Solar Wind Speed to Sunspot Numbers","authors":"Jacob Oloketuyi, Yu Liu, Amobichukwu Chukwudi Amanambu, M. Zhao","doi":"10.1155/2020/3527570","DOIUrl":"https://doi.org/10.1155/2020/3527570","url":null,"abstract":"To investigate the periodic behaviour and relationship of sunspot numbers with cosmic ray intensity and solar wind speed, we present analysis from daily data generated from 1995 January to 2018 December. Cross-correlation and wavelet transform tools were employed to carry out the investigation. The analyses confirmed that the cosmic ray intensity correlates negatively with the sunspot numbers, exhibiting an asynchronous phase relationship with a strong negative correlation. The trend in cosmic ray intensity indicates that it undergoes the 11-year modulation that mainly depends on the solar activity in the heliosphere. On the other hand, the solar wind speed neither shows a clear phase relationship nor correlates with the sunspot numbers but shows a wide range of periodicities that could possibly be connected to the pattern of coronal hole configuration. A number of short and midterm variations were also observed from the wavelet analysis, i.e., 64–128 and 128–256 days for the cosmic ray intensity, 4–8, 32–64, 128–256, and 256–512 days for the solar wind speed, and 16–32, 32–64, 128–256, and 256–512 days for the sunspot numbers.","PeriodicalId":48962,"journal":{"name":"Advances in Astronomy","volume":" ","pages":"1-10"},"PeriodicalIF":1.4,"publicationDate":"2020-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1155/2020/3527570","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49446299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we describe a technique, which uses an adaptive background learning method to detect the CME (coronal mass ejections) automatically from SOHO/LASCO C2 image sequences. The method consists of several modules: adaptive background module, candidate CME area detection module, and CME detection module. The core of the method is based on adaptive background learning, where CMEs are assumed to be a foreground moving object outward as observed in running-difference time series. Using the static and dynamic features to model the corona observation scene can more accurately describe the complex background. Moreover, the method can detect the subtle changes in the corona sequences while filtering their noise effectively. We applied this method to a month of continuous corona images, compared the result with CDAW, CACTus, SEEDS, and CORIMP catalogs and found a good detection rate in the automatic methods. It detected about 73% of the CMEs listed in the CDAW CME catalog, which is identified by human visual inspection. Currently, the derived parameters are position angle, angular width, linear velocity, minimum velocity, and maximum velocity of CMES. Other parameters could also easily be added if needed.
{"title":"A CME Automatic Detection Method Based on Adaptive Background Learning Technology","authors":"Z. Qiang, X. Bai, Qinghui Zhang, Hong Lin","doi":"10.1155/2019/6582104","DOIUrl":"https://doi.org/10.1155/2019/6582104","url":null,"abstract":"In this paper, we describe a technique, which uses an adaptive background learning method to detect the CME (coronal mass ejections) automatically from SOHO/LASCO C2 image sequences. The method consists of several modules: adaptive background module, candidate CME area detection module, and CME detection module. The core of the method is based on adaptive background learning, where CMEs are assumed to be a foreground moving object outward as observed in running-difference time series. Using the static and dynamic features to model the corona observation scene can more accurately describe the complex background. Moreover, the method can detect the subtle changes in the corona sequences while filtering their noise effectively. We applied this method to a month of continuous corona images, compared the result with CDAW, CACTus, SEEDS, and CORIMP catalogs and found a good detection rate in the automatic methods. It detected about 73% of the CMEs listed in the CDAW CME catalog, which is identified by human visual inspection. Currently, the derived parameters are position angle, angular width, linear velocity, minimum velocity, and maximum velocity of CMES. Other parameters could also easily be added if needed.","PeriodicalId":48962,"journal":{"name":"Advances in Astronomy","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2019-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1155/2019/6582104","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47972240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Dong Zhao, Long Xu, Linjie Chen, Yihua Yan, Ling-yu Duan
Overexposure may happen for imaging of solar observation as extremely violet solar bursts occur, which means that signal intensity goes beyond the dynamic range of imaging system of a telescope, resulting in loss of signal. For example, during solar flare, Atmospheric Imaging Assembly (AIA) of Solar Dynamics Observatory (SDO) often records overexposed images/videos, resulting loss of fine structures of solar flare. This paper makes effort to retrieve/recover missing information of overexposure by exploiting deep learning for its powerful nonlinear representation which makes it widely used in image reconstruction/restoration. First, a new model, namely, mask-Pix2Pix network, is proposed for overexposure recovery. It is built on a well-known Pix2Pix network of conditional generative adversarial network (cGAN). In addition, a hybrid loss function, including an adversarial loss, a masked L1 loss and a edge mass loss/smoothness, are integrated together for addressing challenges of overexposure relative to conventional image restoration. Moreover, a new database of overexposure is established for training the proposed model. Extensive experimental results demonstrate that the proposed mask-Pix2Pix network can well recover missing information of overexposure and outperforms the state of the arts originally designed for image reconstruction tasks.
{"title":"Mask-Pix2Pix Network for Overexposure Region Recovery of Solar Image","authors":"Dong Zhao, Long Xu, Linjie Chen, Yihua Yan, Ling-yu Duan","doi":"10.1155/2019/5343254","DOIUrl":"https://doi.org/10.1155/2019/5343254","url":null,"abstract":"Overexposure may happen for imaging of solar observation as extremely violet solar bursts occur, which means that signal intensity goes beyond the dynamic range of imaging system of a telescope, resulting in loss of signal. For example, during solar flare, Atmospheric Imaging Assembly (AIA) of Solar Dynamics Observatory (SDO) often records overexposed images/videos, resulting loss of fine structures of solar flare. This paper makes effort to retrieve/recover missing information of overexposure by exploiting deep learning for its powerful nonlinear representation which makes it widely used in image reconstruction/restoration. First, a new model, namely, mask-Pix2Pix network, is proposed for overexposure recovery. It is built on a well-known Pix2Pix network of conditional generative adversarial network (cGAN). In addition, a hybrid loss function, including an adversarial loss, a masked L1 loss and a edge mass loss/smoothness, are integrated together for addressing challenges of overexposure relative to conventional image restoration. Moreover, a new database of overexposure is established for training the proposed model. Extensive experimental results demonstrate that the proposed mask-Pix2Pix network can well recover missing information of overexposure and outperforms the state of the arts originally designed for image reconstruction tasks.","PeriodicalId":48962,"journal":{"name":"Advances in Astronomy","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2019-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1155/2019/5343254","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43404877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jiafeng Zhang, Guangzhong Lin, S. Zeng, S. Zheng, Xiao Yang, Gang-Hua Lin, X. Zeng, Haimin Wang
Prior to the availability of digital cameras, the solar observational images are typically recorded on films, and the information such as date and time were stamped in the same frames on film. It is significant to extract the time stamp information on the film so that the researchers can efficiently use the image data. This paper introduces an intelligent method for extracting time stamp information, namely, the convolutional neural network (CNN), which is an algorithm in deep learning of multilayer neural network structures and can identify time stamp character in the scanned solar images. We carry out the time stamp decoding for the digitized data from the National Solar Observatory from 1963 to 2003. The experimental results show that the method is accurate and quick for this application. We finish the time stamp information extraction for more than 7 million images with the accuracy of 98%.
{"title":"Intelligent Recognition of Time Stamp Characters in Solar Scanned Images from Film","authors":"Jiafeng Zhang, Guangzhong Lin, S. Zeng, S. Zheng, Xiao Yang, Gang-Hua Lin, X. Zeng, Haimin Wang","doi":"10.1155/2019/6565379","DOIUrl":"https://doi.org/10.1155/2019/6565379","url":null,"abstract":"Prior to the availability of digital cameras, the solar observational images are typically recorded on films, and the information such as date and time were stamped in the same frames on film. It is significant to extract the time stamp information on the film so that the researchers can efficiently use the image data. This paper introduces an intelligent method for extracting time stamp information, namely, the convolutional neural network (CNN), which is an algorithm in deep learning of multilayer neural network structures and can identify time stamp character in the scanned solar images. We carry out the time stamp decoding for the digitized data from the National Solar Observatory from 1963 to 2003. The experimental results show that the method is accurate and quick for this application. We finish the time stamp information extraction for more than 7 million images with the accuracy of 98%.","PeriodicalId":48962,"journal":{"name":"Advances in Astronomy","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2019-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1155/2019/6565379","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47854257","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sunspots are darker areas on the Sun’s photosphere and most of solar eruptions occur in complex sunspot groups. The Mount Wilson classification scheme describes the spatial distribution of magnetic polarities in sunspot groups, which plays an important role in forecasting solar flares. With the rapid accumulation of solar observation data, automatic recognition of magnetic type in sunspot groups is imperative for prompt solar eruption forecast. We present in this study, based on the SDO/HMI SHARP data taken during the time interval 2010-2017, an automatic procedure for the recognition of the predefined magnetic types in sunspot groups utilizing a convolutional neural network (CNN) method. Three different models (A, B, and C) take magnetograms, continuum images, and the two-channel pictures as input, respectively. The results show that CNN has a productive performance in identification of the magnetic types in solar active regions (ARs). The best recognition result emerges when continuum images are used as input data solely, and the total accuracy exceeds 95%, for which the recognition accuracy of Alpha type reaches 98% while the accuracy for Beta type is slightly lower but maintains above 88%.
{"title":"Deep Learning for Automatic Recognition of Magnetic Type in Sunspot Groups","authors":"Yuanhui Fang, Yanmei Cui, X. Ao","doi":"10.1155/2019/9196234","DOIUrl":"https://doi.org/10.1155/2019/9196234","url":null,"abstract":"Sunspots are darker areas on the Sun’s photosphere and most of solar eruptions occur in complex sunspot groups. The Mount Wilson classification scheme describes the spatial distribution of magnetic polarities in sunspot groups, which plays an important role in forecasting solar flares. With the rapid accumulation of solar observation data, automatic recognition of magnetic type in sunspot groups is imperative for prompt solar eruption forecast. We present in this study, based on the SDO/HMI SHARP data taken during the time interval 2010-2017, an automatic procedure for the recognition of the predefined magnetic types in sunspot groups utilizing a convolutional neural network (CNN) method. Three different models (A, B, and C) take magnetograms, continuum images, and the two-channel pictures as input, respectively. The results show that CNN has a productive performance in identification of the magnetic types in solar active regions (ARs). The best recognition result emerges when continuum images are used as input data solely, and the total accuracy exceeds 95%, for which the recognition accuracy of Alpha type reaches 98% while the accuracy for Beta type is slightly lower but maintains above 88%.","PeriodicalId":48962,"journal":{"name":"Advances in Astronomy","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1155/2019/9196234","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45924408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Solar flare is one of the violent solar eruptive phenomena; many solar flare forecasting models are built based on the properties of active regions. However, most of these models only focus on active regions within 30° of solar disk center because of the projection effect. Using cost sensitive decision tree algorithm, we build two solar flare forecasting models from the active regions within 30° of solar disk center and outside 30° of solar disk center, respectively. The performances of these two models are compared and analyzed. Merging these two models into a single one, we obtain a full-disk solar flare forecasting model.
{"title":"Full-Disk Solar Flare Forecasting Model Based on Data Mining Method","authors":"Rong Li, Yong Du","doi":"10.1155/2019/5190353","DOIUrl":"https://doi.org/10.1155/2019/5190353","url":null,"abstract":"Solar flare is one of the violent solar eruptive phenomena; many solar flare forecasting models are built based on the properties of active regions. However, most of these models only focus on active regions within 30° of solar disk center because of the projection effect. Using cost sensitive decision tree algorithm, we build two solar flare forecasting models from the active regions within 30° of solar disk center and outside 30° of solar disk center, respectively. The performances of these two models are compared and analyzed. Merging these two models into a single one, we obtain a full-disk solar flare forecasting model.","PeriodicalId":48962,"journal":{"name":"Advances in Astronomy","volume":" ","pages":""},"PeriodicalIF":1.4,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1155/2019/5190353","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44533819","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：