Unravelling The Mysteries Of Giant Star-forming Clumps Using Deep Learning

我之所以选择开放大学，是因为理科理科学士(荣誉)物理学学位对天文学的重视程度很高。受到过去几十年宇宙演化新发现的启发，我想更好地了解星系的形成和现代宇宙学。特别是当事件视界望远镜从黑洞拍摄的第一张图像的报告和出版物提到记录和处理的海量数据时，我看到了将我在大数据分析和机器学习方面的专业技能与天文学结合起来的机会。我真诚地相信，大数据分析将对当前和未来的天体物理研究产生持久的影响。使用本地和基于云的分布式系统进行数据存储、处理和分析使我能够在我的行业职业生涯中开发大规模机器学习模型，用于决策支持和产品开发。多年来，我应用了各种监督和非监督学习模型来进行回归、分类和聚类，主要是使用Python框架，如用于统计和深度学习的SCRICKIT-LINE和KERAS/TensorFlow，或用于大规模数据管道和数据分析的PySpark。以我在大数据分析方面的背景，我希望我能在利用深度学习来分析大天体物理数据集方面做出有意义的贡献

I have chosen the Open University because of the strong focus on Astronomy of the BSc (Honours) Physics degree. Inspired by the last decades full of new discoveries on the evolution of the Universe, I wanted to get a better understanding on the formation of galaxies and modern cosmology. And especially as reports and publications of the first image taken from a black hole by the Event Horizon Telescope have mentioned the huge amount of data recorded and processed, I was seeing an opportunity to combine my professional skills in big data analysis and machine learning with astronomy. I genuinely believe that big data analytics will have a lasting impact on current and future astrophysical research.Using distributed systems, on-premise and cloud-based, for data storage, processing and analysis has enabled me to develop large scale machine learning models for decision support and product development during my industry career. Over the years I have applied various supervised and unsupervised learning models for regression, classification and clustering, mostly using Python frameworks like scikit-learn and Keras/Tensorflow for statistical and deep learning, or PySpark for data pipelines and data analysis at scale. With my background in big data analysis I hope I can make a meaningful contribution in leveraging deep learning to analyse big astrophysical datasets