Research/ Papers

I am a member of the UCLA Astrophysics Data Lab ( ) led by Professor Tuan Do. My research interests include machine learning in astronomy, HPC in CS education, the intersection of data science, computer science, and domain sciences, and the tools and software used therein.

Selected Publications

Note: if any of these are not available to you for free, contact me and I will send you the article.

Boscoe, B., Do, T. Jones, E. “Elements of effective machine learning datasets in astronomy,” NeurIPS, Machine Learning for the Physical Sciences Workshop, New Orleans, December 2022. arXiv:2211.14401v2

Jones, E.,  Do, T., Boscoe, B., Wan, Y., Nguyen, Z, Singal, J. “Photometric Redshifts for Cosmology: Improving Accuracy and Uncertainty Estimates Using Bayesian Neural Networks, NeurIPS , Machine Learning for the Physical Sciences Workshop”, December 2021. 

Scroggins, M., Boscoe, B. (2020). “Once FITS, Always FITS? Astronomical Infrastructure in Transition,” in IEEE Annals of the History of Computing, doi: 10.1109/MAHC.2020.2986745.

Boscoe, B. M. (2020) The What of Data: Defining Which Scientific Research is Appropriate to Share. In A. Sundqvist, G. Berget, J. Nolin, and K. I. Skjerdingstad (Eds.), Sustainable Digital Communities (pp. 687-694). Springer International Publishing.

Scroggins, M., Borgman, C., Pasquetto I., Geiger S., Boscoe, B., Darch, P., Cabasse-Mazel, C., Thompson, C., & Golshan, M. (2020). Thorny problems in data (-intensive) science. Commun. ACM 63, 8 (August 2020), 30–32. DOI:

Boscoe, B. (2019). In Algorithmic Processes, When is Human Intervention Necessary for Transparency?, Annu. Book Freedom Inf. Law (Jahrb. Für Informationsfreiheit Informationsrecht 2018).

Boscoe, B. (2019). Creating Transparency in Algorithmic Processes. Delphi – Interdisciplinary Review of Emerging Technologies, 2(1), 12-22.

Wofford, M. F., Boscoe, B., Borgman, C. L., Pasquetto, I. V., & Golshan, M. S. (2019). Jupyter notebooks as discovery mechanisms for open science: Citation practices in the astronomy community. IEEE Computing in Science & Engineering, Software and Data Citation. DOI: 10.1109/MCSE.2019.2932067. Open access:

Boscoe, B. (2018). Machine Learning Algorithms: Transparent Checkpoints. For Transparency and Society – Between Promise and Peril, Herrenhausen Conference, Berlin-Brandenburg Academy of Sciences and Humanities (BBAW), Berlin, Germany.

(formerly Bernie/ Bernadette Randles)

Pasquetto, I., Randles, B., & Borgman, C. (2017). On the Reuse of Scientific Data. Data Science Journal, 16(0).

Randles, B. M., Pasquetto, I. V., Golshan, M. S., & Borgman, C. L. (2017). Using the Jupyter Notebook as a Tool for Open Science: An Empirical Study. In 2017 ACM/IEEE Joint Conference on Digital Libraries (JCDL) (pp. 1–2).

Randles, B. M. , Sands, A.E. & Borgman, C. L. (2016). Too Big to Share? Scaling up knowledge transfer workflows in computational sciences. Force 16 Conference, Portland, Oregon.

Borgman, C. L. , Golshan, M., Sands, S.E., Wallis, J.C., Cummings, R.L., Randles, B.M. (2016). Data Management in the Long Tail: Social and Technical Opportunities. In Proceedings of the 11th International Digital Curation Conference. Amsterdam.

Yoon, D., Chen, N., Randles, B., Cheatle, A., Lockenhoff, C. E., Jackson, S. J., Sellen, S. & Guimbretiere, F. (2016, February). RichReview++: Deployment of a Collaborative Multi-modal Annotation System for Instructor Feedback and Peer Discussion. In Proceedings of the 19th ACM Conference on Computer-Supported Cooperative Work & Social Computing (pp. 195-205). ACM.

Randles, B., Yoon, D., Cheatle, A., Jung, M., & Guimbretiere, F. (2015, March). Supporting Face-to-Face Like Communication Modalities for Asynchronous Assignment Feedback in Math Education. In Proceedings of the Second (2015) ACM Conference on Learning@ Scale (pp. 321-326). ACM.