| CODE | SSA5075 | |||||||||
| TITLE | Computational Methods for Astronomy | |||||||||
| UM LEVEL | 05 - Postgraduate Modular Diploma or Degree Course | |||||||||
| MQF LEVEL | 7 | |||||||||
| ECTS CREDITS | 5 | |||||||||
| DEPARTMENT | Institute of Space Sciences and Astronomy | |||||||||
| DESCRIPTION | The "Computational Methods for Astronomy" unit offers a comprehensive exploration of the intersection between machine learning and astronomical research. Through a combination of theoretical concepts, practical applications, and hands-on projects, students will gain a deep understanding of the fundamental principles of machine learning and its specific applications in the field of astronomy. The unit will cover key topics such as radio astronomical images and AstroPy, historical developments in machine learning methods within astronomy, radio galaxy morphological classification, radio event detection, analysis of convolutional neural networks (CNNs) for radio source detection, vision transformers for classification and segmentation, as well as challenges related to data augmentation and the utilization of pre-trained models in the astronomy domain. Study-unit Aims: The aims of the "Computational Methods for Astronomy" unit are twofold. Firstly, the unit aims to provide students with a solid theoretical foundation in machine learning techniques and their application to astronomical datasets. Secondly, it seeks to develop students' practical skills in implementing and adapting machine learning algorithms to address specific astronomical research questions. By achieving these aims, the unit aims to foster a new generation of astronomers who are well-versed in the principles and practices of machine learning, enabling them to make significant contributions to the advancement of astronomical knowledge. Learning Outcomes: 1. Knowledge & Understanding By the end of the study-unit the student will be able to: - Demonstrate a comprehensive understanding of the principles and techniques of machine learning in the context of astronomy; - Identify and critically evaluate the historical development of machine learning methods used in astronomy; - Analyze and interpret radio astronomical images using AstroPy and other relevant tools; - Explain the key concepts and algorithms related to radio galaxy morphological classification and radio event detection; - Evaluate the performance and compare the effectiveness of different source finder algorithms; - Assess the strengths and limitations of convolutional neural networks (CNNs) in the context of radio source detection. 2. Skills By the end of the study-unit the student will be able to: - Apply machine learning algorithms to process and analyze astronomical data, including radio astronomical images; - Design and implement novel approaches for radio galaxy morphological classification and radio event detection; - Utilise and modify existing convolutional neural network architectures for radio source detection tasks; - Use vision transformers for classification and segmentation tasks in the astronomy domain; - Address challenges related to data augmentation in deep learning applications for astronomy; - Evaluate the suitability and adaptability of pre-trained models for specific astronomical research questions; - Communicate and present complex scientific ideas effectively, both in written and oral forms; - Demonstrate problem-solving and critical thinking skills. Main Text/s and any supplementary readings: Course material will be provided by the co-ordinator. |
|||||||||
| ADDITIONAL NOTES | Pre-Requisite qualification: B.Sc., B. Eng., or equivalent | |||||||||
| STUDY-UNIT TYPE | Lecture | |||||||||
| METHOD OF ASSESSMENT |
|
|||||||||
| LECTURER/S | ||||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2024/5. It may be subject to change in subsequent years. |
||||||||||