Anomaly Detection using Deep Learning for Fundamental Physics Discovery
BIDS Research Affiliate Ben Nachman offered this project through the 2021 NERSC Summer Internships program. Applicants were students actively enrolled in undergraduate or graduate programs (and the project was to be adapted to the experience of the student).... more
AstroPy
The AstroPy Project is a community effort to develop a single core package for astronomy in Python and foster interoperability between Python astronomy packages. The core package has nearly 100 contributors to date and has become one of the most widely used pieces of software in astronomy. The... more
Berkeley Carpentries Club
BIDS' Education & Training Working Group has launched the Berkeley Carpentries Club to connect instructors of research computing workshops in the Berkeley, California, area. The group is a community network of teachers and instructors with diverse interests and backgrounds,... more
Berkeley Conversations: Computing and Data Science In Action
BIDS researchers are participating in interactive discussion webinars as part of the Berkeley Conversations, Campus Conversations, and Computing and Data Science In Action: COVID-19 Response & Recovery series hosted by BIDS and the Berkeley Division of Computing,... more
Berkeley Ecoinformatics Engine
Predicting biodiversity responses to global environmental change is a huge challenge that requires a holistic understanding of the complex interactions and feedbacks among organisms, climate, and their physical and biotic environments across space and time.
Holos: Berkeley Ecoinformatics Engine... more
BIDS Machine Shop
BIDS Senior Research Data Scientist Stéfan van der Walt previously hosted these undergraduate projects through BIDS Undergraduate Internships Program.
As more scientific fields move to intersect with computation, a need arises for software tools that can bridge the gap... more
BIDS-BCHSI Research Xchange Forum
The BIDS-BCHSI Research Xchange Forum was launched in October 2020 as an open discussion platform for the interdisciplinary exchange of ideas and research projects at the intersection of healthcare and data science, enabling participants to support the development, and research of the group's... more
COVID-19 Response: BIDS Data Science Services and Consulting
In April 2020, BIDS is convened researchers and resources to address COVID-19. As the demand for data science and data analysis expertise took on new urgency with the COVID-19 pandemic, BIDS started working with multiple units at UC Berkeley to determine how best to... more
Cryptography of the unknown regions of genomes
BIDS Biodiversity and Environmental Sciences Lead Ciera Martinez originally launched as part of UC Berkeley's Undergraduate Research Apprentice Program (URAP).
As sequencing genomes becomes faster and cheaper, more sophisticated informatics tools are needed to... more
Data Science Coast to Coast
The Data Science Coast to Coast (DSC2C) seminar series was launched in October 2020 and continued through Summer 2021, hosted jointly by seven academic data science institutes — BIDS, NYU’s Center for Data Science, Rice University’s Ken Kennedy Institute, Stanford Data Science, the University of... more
Data Science Discovery Program
The Data Science Discovery Program (formerly known as the BIDS Collaborative) provides undergraduates with opportunities to engage in hands-on, team-based research opportunities by connecting them with cutting-edge data science research projects, community impact groups,... more
Deciding Force
The Deciding Force (DF) project is classifying information from more than 8,000 news articles describing more than 35,000 events in which police and the Occupy movement interacted. These data are considered alongside variables describing the governing contexts in which protests occur (including... more
Detecting change in global biodiversity through large scale network analysis
Global ecosystems that support life are undergoing dramatic pressure and rapid, unprecedented changes. Currently, there are a variety of separate scientific models, each with separate data sources, that can model the activities of diverse parts in an ecosystem, such as soil, bacteria-root... more
Enabling future gamma-ray space missions
The next generation of gamma-ray space telescopes aims to open a new window into gamma-ray astronomy with unprecedented angular resolution, energy resolution, and sensitivity. The goals of these new telescopes range from achieving a better understanding of the element formation in our Galaxy, to... more
Environment and Society: Data Sciences for the 21st Century (DS421)
Environment and Society: Data Science for the 21st Century (DS421) was an interdisciplinary graduate training program and National Science Foundation Research Traineeship at UC Berkeley at the interface of data, social, and natural sciences. The project was led by BIDS Senior Fellow... more
Garbage In, Garbage Out? Do Machine Learning Research Papers Report Where Training Data Comes From?
Supervised machine learning is widely used across fields, but major issues are arising around biased, inaccurate, and incomplete training data. In this project, we investigate to what extent published machine learning application papers give specific details about the training data they used,... more
Hydrologic forecasting for the East River, CO
River flow forecasting is essential for planning reservoir operations, defense strategies against flooding, and fluvial ecosystems management plans. However, flow forecasting is a highly uncertain science. One of the biggest uncertainties lies in resolving the timescales over which water is stored... more
Hydrological forecasting and the water/energy nexus
Clean, available water is a critical and often-overlooked resource for human activity, food production, biological diversity and all aspects of life on our planet. Drawing on data streams from a national network of research collaborators and water sensor networks, the research team is creating and... more
Learning fundamental properties of physical systems with machine learning
Using data-driven methods and statistical modeling to uncover, unguided by existing theory, the fundamental properties of observed physical systems, this team is using software and data to provide a new pathway to develop a theoretical understanding of the physical world. The data for this project... more