Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.2
2.6
Journals
Universe
Special Issues
Applications of Artificial Intelligence in Modern Astronomy
share announcement

Applications of Artificial Intelligence in Modern Astronomy

A special issue of Universe (ISSN 2218-1997). This special issue belongs to the section "Astroinformatics and Astrostatistics".

Deadline for manuscript submissions: closed (17 April 2026) | Viewed by 9048

Special Issue Editor

Prof. Dr. Bo Qiu

E-Mail Website
Guest Editor
School of Intelligence Science and Technology, University of Science and Technology Beijing, Beijing 100083, China
Interests: artificial intelligence; machine learning; astronomy

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) has revolutionized modern astronomy, offering innovative solutions to analyze vast amounts of data generated by telescopes and satellites. AI algorithms excel in pattern recognition, making them ideal for detecting celestial objects and phenomena, such as exoplanets, supernovae, and galaxy formations. Machine learning models can sift through terabytes of data to identify subtle patterns that might be missed by human observers. Moreover, AI enhances the efficiency of data processing, allowing astronomers to focus on hypothesis-driven research rather than data management. It also plays a crucial role in predictive modeling, helping to forecast cosmic events and optimize observational strategies. As AI continues to evolve, its applications in astronomy are expected to expand, potentially leading to groundbreaking discoveries about the universe we inhabit.

Prof. Dr. Bo Qiu
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Universe is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • artificial intelligence
  • machine learning
  • astronomy
  • deep learning
  • big data
  • telescope

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

23 pages, 2936 KB  
Article
Lightweight Transient-Source Detection Method for Edge Computing
by Jiahao Zhang, Yutian Fu, Feng Dong and Lingfeng Huang
Universe 2026, 12(4), 101; https://doi.org/10.3390/universe12040101 - 1 Apr 2026
Viewed by 464
Abstract
Transient-source detection without relying on difference images still faces challenges in achieving high accuracy, especially under practical space-based astronomical survey conditions where the data volume is enormous, on-orbit transmission bandwidth is limited, and real-time response is required for rapid follow-up observations. To address [...] Read more.
Transient-source detection without relying on difference images still faces challenges in achieving high accuracy, especially under practical space-based astronomical survey conditions where the data volume is enormous, on-orbit transmission bandwidth is limited, and real-time response is required for rapid follow-up observations. To address these issues, this paper proposes a lightweight detection network that integrates multi-scale feature fusion with contextual feature extraction, enabling efficient real-time processing on resource-constrained edge devices. The proposed model enhances robustness to point-spread-function variations across observation conditions and to complex background environments, while simultaneously improving detection accuracy. To evaluate performance comprehensively, lightweight VGG and lightweight ResNet architectures and other baseline models—commonly used as baselines for transient-source detection—are adopted for comparison. Experimental results show that under the condition that the models have approximately the same number of parameters, the proposed network achieves the best accuracy, obtaining nearly 1% improvement compared with the best-performing baseline model. Based on this design, an ultra-lightweight version with only 7k parameters is further developed by incorporating a compact multi-scale module, improving accuracy by 1% over the version without the multi-scale structure. Moreover, through heterogeneous knowledge distillation and adaptive iterative training, the accuracy of the ultra-lightweight model is further increased from 93.3% to 94.0%. Finally, the model is deployed and validated on an AI hardware acceleration platform. The results demonstrate that the proposed method substantially improves inference throughput while maintaining high accuracy, providing a practical solution for real-time, low-latency, on-device transient-source detection under large data volume and limited transmission conditions. Specifically, the proposed models are trained offline on a high-performance GPU and subsequently deployed on the Fudan Microelectronics 7100 AI board to evaluate their real-world inference efficiency on resource-constrained edge devices. Full article
(This article belongs to the Special Issue Applications of Artificial Intelligence in Modern Astronomy)
►▼ Show Figures

Figure 1

14 pages, 7000 KB  
Article
A Two-Stage Machine Learning Framework for Predicting Sporadic E Occurrence and Intensity
by Licheng Liu and Ding Yang
Universe 2026, 12(2), 50; https://doi.org/10.3390/universe12020050 - 12 Feb 2026
Viewed by 503
Abstract
Sporadic E (Es) layers exhibit strong intermittency and highly skewed intensity distributions, exerting significant impacts on high-frequency communication and navigation systems and posing challenges for data-driven prediction. Conventional single-stage regression models are often dominated by abundant non-event samples and therefore tend to underestimate [...] Read more.
Sporadic E (Es) layers exhibit strong intermittency and highly skewed intensity distributions, exerting significant impacts on high-frequency communication and navigation systems and posing challenges for data-driven prediction. Conventional single-stage regression models are often dominated by abundant non-event samples and therefore tend to underestimate Es intensity during occurrence periods. To address this issue, this study proposes a unified two-stage neural network framework that decouples the prediction of Es occurrence probability from the estimation of Es intensity. The model is trained using multi-station ionosonde observations, incorporating cyclic representations of seasonal and local time variations together with solar and geomagnetic indices and station-aware encoding to enable unified learning across multiple stations. Results show that the proposed two-stage framework achieves event-only MAE values of 0.53–0.76 MHz and RMSE values of approximately 1.0–1.4 MHz at most mid- and low-latitude stations, with larger errors at the high-latitude Casey station (MAE ≈ 1.45 MHz and RMSE ≈ 2.31 MHz). The consistently bounded MRE values (≈0.18–0.23) observed across multiple stations demonstrate that the framework effectively mitigates severe data imbalance and suppresses spurious high-intensity estimates under non-Es conditions. Full article
(This article belongs to the Special Issue Applications of Artificial Intelligence in Modern Astronomy)
►▼ Show Figures

Figure 1

Review

Jump to: Research

50 pages, 4804 KB  
Review
A Brief Review of Unsupervised Machine Learning Algorithms in Astronomy: Dimensionality Reduction and Clustering
by Chih-Ting Kuo, Duo Xu and Rachel Friesen
Universe 2025, 11(12), 412; https://doi.org/10.3390/universe11120412 - 11 Dec 2025
Cited by 2 | Viewed by 2244
Abstract
This review investigates the application of unsupervised machine learning algorithms to astronomical data. Unsupervised machine learning enables researchers to analyze large, high-dimensional, and unlabeled datasets and is sometimes considered more helpful for exploratory analysis because it is not limited by present knowledge and [...] Read more.
This review investigates the application of unsupervised machine learning algorithms to astronomical data. Unsupervised machine learning enables researchers to analyze large, high-dimensional, and unlabeled datasets and is sometimes considered more helpful for exploratory analysis because it is not limited by present knowledge and can therefore be used to extract new knowledge. Unsupervised machine learning algorithms that have been repeatedly applied to analyze astronomical data are classified according to their usage, including dimension reduction and clustering. This review also discusses anomaly detection and symbolic regression. For each algorithm, this review discusses the algorithm’s functioning in mathematical and statistical terms, the algorithm’s characteristics (e.g., advantages and shortcomings and possible types of inputs), and the different types of astronomical data analyzed with the algorithm. Example figures are generated. The algorithms are tested on synthetic datasets. This review aims to provide an up-to-date overview of both the high-level concepts and detailed applications of various unsupervised learning methods in astronomy, highlighting their advantages and disadvantages to help researchers new to unsupervised learning. Full article
(This article belongs to the Special Issue Applications of Artificial Intelligence in Modern Astronomy)
►▼ Show Figures

Figure 1

26 pages, 1275 KB  
Review
Artificial Intelligence Revolutionizing Time-Domain Astronomy
by Ze-Ning Wang, Da-Chun Qiang and Sheng Yang
Universe 2025, 11(11), 355; https://doi.org/10.3390/universe11110355 - 28 Oct 2025
Cited by 1 | Viewed by 2294
Abstract
Artificial intelligence (AI) applications have attracted widespread attention and have proven to be highly successful in understanding messages across various dimensions. These applications have the potential to assist astronomers in exploring the massive amounts of astronomical data. In fact, the integration of AI [...] Read more.
Artificial intelligence (AI) applications have attracted widespread attention and have proven to be highly successful in understanding messages across various dimensions. These applications have the potential to assist astronomers in exploring the massive amounts of astronomical data. In fact, the integration of AI techniques with astronomy began some time ago, significantly advancing our understanding of the universe by aiding in exoplanet discovery, galaxy morphology classification, gravitational wave event analysis, and more. In particular, AI is now recognized as a crucial component in time-domain astronomy, particularly given the rapid evolution of targeting transients and the increasing number of candidates detected by powerful surveys. A notable success is SN 2023tyk, the first transient discovered and spectroscopically classified without human inspection, an achievement made even more remarkable given that it was identified by the Zwicky Transient Facility, which detects millions of alert sources every night. There is no doubt that AI will play a crucial role in future astronomical observations across various messenger channels, aiding in transient discovery and classification, and helping, or even replacing, observers in making real-time decisions. This review paper examines several cases where AI is transforming contemporary astronomy, especially time-domain astronomy. We discuss the AI algorithms and methodologies employed to date, highlight significant discoveries enabled by AI, and outline future research directions in this rapidly evolving field. Full article
(This article belongs to the Special Issue Applications of Artificial Intelligence in Modern Astronomy)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop