Machine Learning in the Era of Large Astronomical Surveys

该奖项为2019年卡夫利天体物理暑期计划(KSPA)提供部分支持。今年的主题是《大天文测量时代的机器学习》。该项目将于2019年7月9日至8月16日在加州大学洛杉矶分校校园举行。KSPA是一个独特的研究生培训项目，将世界级科学家和大约15名研究生聚集在一起，解决天体物理学中的热门突出问题。在一周的讲座和讨论之后，这段时间主要用于研究。在指导学生在他们选择的创新研究项目上取得重大进展的同时，教师和博士后也有许多机会就新想法进行合作。许多项目后来被发表在会议记录或经评审的期刊上。2019年KSPA以天文学中的机器学习技术为重点，强调对大型天文数据的分析和可视化。KSPA积极而成功地促进了多学科研究，培养了一批多样化的研究生，其中大多数人在过去继续着一流的学术生涯。该项目强调多样性，其国际性促进了文化交流。对妇女在计算机领域的重视将包括实现和保持性别平衡的最佳做法。另一个重点是让行业专业人士参与他们的最新技术如何帮助天文学。KSPA可以满怀信心地期待继续培养新一代跨学科科学家。通过在学生职业生涯早期向学生介绍数据科学和机器学习，本研讨会将展示与统计、计算机科学和行业同行的合作对于充分利用这些新兴技术是多么关键。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

This award provides partial support for the 2019 Kavli Summer Program in Astrophysics (KSPA). The topic this year is "Machine Learning in the Era of Large Astronomical Surveys". The program will be hosted on the UCSC campus from July 9 to August 16, 2019The KSPA is a unique graduate training program that brings world-class scientists together with about 15 graduate students to solve topical outstanding problems in astrophysics. After an introductory week of lectures and discussion, the time is primarily dedicated to research. While coaching students to make significant progress on their chosen innovative research projects, faculty and postdocs also have many opportunities to collaborate on new ideas. Many projects are later published, in either a conference proceeding or a refereed journal. With a focus on machine-learning techniques in astronomy, the 2019 KSPA emphasizes the analysis and visualization of large astronomical datasets.The KSPA actively and successfully promotes multidisciplinary research, training a diverse group of graduate students, the majority of whom have in the past continued to first-class academic careers. The program emphasizes diversity, and its international nature promotes cultural exchange. An emphasis on women in computing will include best practices towards achieving and maintaining gender balance. Another emphasis is to engage industry professionals in how their latest techniques can help astronomy. The KSPA can confidently expect to continue to train a new generation of cross-disciplinary scientists. By introducing students to data science and machine learning early in their careers, this workshop will demonstrate how collaboration with statistics, computer science, and industry colleagues is critical for fully leveraging these emerging technologies.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.