Astronomical big data processing using machine learning: A comprehensive review

Sen, Snigdha; Agarwal, Sonali; Chakraborty, Pavan; Singh, Krishna Pratap

doi:10.1007/s10686-021-09827-4

Cited by 56 publications

(18 citation statements)

References 156 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These techniques aid in characterizing patterns and improving the understanding of the universe by culling out potentially valuable information. Utilizing sophisticated machine learning algorithms, data mining tools, and distributed frameworks can speed up astronomical discoveries (Sen et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

How Does Artificial Intelligence Help Astronomy? A Review

Patel¹

2022

cse

View full text Add to dashboard Cite

Artificial intelligence (AI) is a discipline of computing that focuses mostly on transferring human intelligence and mental processes into machines that can assist humans in many ways. Machine learning (ML) is the approach of choice in AI for creating useful software for computer vision, speech recognition, natural language processing, robot control, and other applications. Some of the most common analyses of large, complicated and multidimensional data sets in astronomy can be performed by using ML methods. It can be used for automating observatory scheduling to increase the effective utilization and scientific return from telescopes. It is also used for image recognition, classification of galaxies and planet recognition. This paper offers an in-depth review of the evolution of artificial intelligence and the use of AI and ML in the field of astronomy, especially for data analysis, image recognition, astronomical scheduling, classification of galaxies and planet recognition. It adds to the existing literature on use of artificial intelligence for astronomical applications and is a useful resource for students and researchers.

show abstract

Section: Discussionmentioning

confidence: 99%

How Does Artificial Intelligence Help Astronomy? A Review

Patel¹

2022

cse

View full text Add to dashboard Cite

show abstract

“…I. Perren et al [14] pre-sented the Automated Star Cluster Analysis package (ASteCA), a set of tools designed to fully automate the conventional tests used to establish the basic properties of stellar clusters. P. H. Barchi et al [7] have used both supervised and unsupervised machine learning algorithms to improve the classifications of galaxies into spiral and elliptical with morphological parameters.Selim et al [17] introduced a novel technique in which 2D and 3D Kmeans, as well as normal distribution features, were employed to predict the most likely galaxies of Virgo clusters and the Virgo center.Sen et al [18] have described a number of machine learning and big data tools that can be used to handle and process massive amounts of astronomical data in their review paper.Snigdha et al [19] proposed a neural network model for interpreting redshift data of celestial objects, and two different ways to train the model were proposed: one utilizing Lipschitz-based adaptive learning rate in a single node/machine, and the other using a multinode clustered environment.…”

Section: Related Workmentioning

confidence: 99%

Experimental investigation to identify galaxy clusters using sparse matrix clustering algorithm

Rai

Sen

Chakraborty

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Recent advances in astronomy have shifted observational astronomy toward data-driven astronomy, with an exponential increase in data associated with celestial objects. If we can handle this massive amount of quickly changing data, we will be able to detect galaxy clusters, revealing a wealth of vital information about the evolution of the universe. In this paper, we have proposed a novel clustering technique that can handle massive amounts of rapidly changing data in real time. In this clustering technique, we have used 3D sparse matrix where each cell of the 3D matrix can be used to locate/identify a neighbor against the central galactic coordinate. In our investigation, we also used HDF5 to store and organize the discovered galaxy clusters so that we didn’t have to re-run our algorithm every time a new coordinate was encountered. Following preparation, the astronomical data containing the galactic coordinates RA, DEC, and radial distance obtained from redshift is input into our developed algorithm to identify, store, and depict the galaxy clusters.

show abstract

“…These consist of terabytes of image data with characterized attributes covering a full range of wavelengths [2]. With the progression of technology, the influx of such data opens a window for more effective digital analysis [9], [10] presenting the application of machine learning to the subject field. Machine learning is a branch of artificial intelligence built on computational learning theory and pattern recognition.…”

Section: Introductionmentioning

confidence: 99%

Space Object Recognition With Stacking of CoAtNets Using Fusion of RGB and Depth Images

et al. 2023

View full text Add to dashboard Cite

Space situational awareness (SSA) system requires recognition of space objects that are varied in sizes, shapes, and types. The space images are challenging because of several factors such as illumination and noise and thus make the recognition task complex. Image fusion is an important area in image processing for various applications including RGB-D sensor fusion, remote sensing, medical diagnostics, and infrared and visible image fusion. Recently, various image fusion algorithms have been developed and they showed a superior performance to explore more information that are not available in single images. In this paper, we compared various methods of RGB and Depth image fusion for space object classification task. The experiments were carried out, and the performance was evaluated using 13 fusion performance metrics. It was found that the guided filter context enhancement (GFCE) outperformed other image fusion methods in terms of average gradient (8.2593), spatial frequency (28.4114), and entropy (6.9486). additionally, due to its ability to balance between good performance and inference speed (11.41 second), GFCE was selected for RGB and Depth image fusion stage before feature extraction and classification stage. The outcome of fusion method is fused images that were used to train a deep ensemble of CoAtNets to classify space objects into ten categories. The deep ensemble learning methods including bagging, boosting, and stacking were trained and evaluated for classification purposes. It was found that combination of fusion and stacking was able to improve classification accuracy largely compared to the baseline methods by producing an average accuracy of 89 % and average F1 score of 89 %.

show abstract

Astronomical big data processing using machine learning: A comprehensive review

Cited by 56 publications

References 156 publications

How Does Artificial Intelligence Help Astronomy? A Review

How Does Artificial Intelligence Help Astronomy? A Review

Experimental investigation to identify galaxy clusters using sparse matrix clustering algorithm

Space Object Recognition With Stacking of CoAtNets Using Fusion of RGB and Depth Images

Contact Info

Product

Resources

About