Data Science Discovery Fall 2023 Overview

The Costs and Benefits of Buying American | Haas School of Business [Full]

Can We Build Entrepreneurs and Better Negotiators? A Field Experiment in Uganda (Machine Learning and Big Data) | Haas School of Business [Full]

Credit Scoring Algorithms using Alternative Data Sources and Machine-Learning | Berkeley Haas, Institute for Business and Social Impact (IBSI) [Full]

Changes in the Global Economy | UC Berkeley Department of Sociology [Full]

Enhancing Severe Heatwave Forecasting Using Theory and Data Science | UC Berkeley Department of Earth and Planetary Science [Full]

The Sierra Nevada Beaver Project: Estimating How Restored Beaver Populations Influence Water Resources in the Sierra Nevada Under Various Climate Scenarios | UC Berkeley ESPM Department 

Sub-seasonal wildfire burned area prediction with machine learning | Lawrence Berkeley National Laboratory [Full]

Building proactive climate-smart technologies to prevent heat-related human health hazard and mortality | Climformatics Inc.

Discovery of Undocumented Oil and Gas Wells | Lawrence Berkeley National Laboratory

comfortDAT - an open-source data analysis toolkit for thermal comfort research | Center for the Built Environment at UC Berkeley

Building Machine Learning Models for Arctic Ice Restoration |  Climformatics Inc

Resilient Energy Allocation System for Extreme Weather: Balancing AC Demand and Fire Safety | Climformatics Inc

Data Visualization of Biological and Ecological Data | UCSC

Life Cycle Assessment of Building Structures | Forell | Elsesser [Full]

The Bay Twin: A Climate Justice “Digital Twin” for the San Francisco Bay Area | UC Berkeley College of Environmental Design

ML for Biodiversity Monitoring | UC Berkeley Dept. of Environmental Science, Policy and Management [Full]

Deep learning and language | UC Berkeley Department of Linguistics

Computationally evaluating design rationale | Co-Design Lab

Search Query Suggestions | Ithaka (JSTOR) [Full]

Missing Object Library | Art Practice and Berkeley Center for New Media.

AI Machine Translation for Cuneiform | FactGrid Cuneiform Project [Full]

Project AEI | Koer AI, Inc

Automated Quality Control and Analysis of Histopathology Images using deep learning | Merck & Co.

LLM for internal employee use | Andreessen Horowitz (a16z) [Full]

AI-powered development of novel CRISPR-based therapeutics | Scribe Therapeutics [Full]

Mobility Analytics | 99p Labs / Honda [Full]

Data Analyst in a Box | 99P Labs / Honda Research Institute [Full]

GMO acceptance of bioengineered brewer's yeast | Berkeley Yeast [Full]

Lead Identification | Berkeley Yeast [Full]

TranscribeGlass | TranscribeGlass software internship

Transparency in Segmentation Algorithms | Gauge

Image-To-Text for an Accessible Web | Gauge [Full]

Traffic signal conditions tested by a robot | Kiwibot [Full]

Violawalkhome: a mobile safety app | Violawalkhome/UC Berkeley/Stanford University [Full]

Identifying threats in the Web3 ecosystem | AnChain.ai [Full]

Candidate Feedback Report | HUELLA

DSG Interns - Various Projects | Data for Social Good Foundation [Full]

Proving that Public/Private Partnerships Promote Digital Equity | Human-I-T [Full]

Moment Price Estimator | Dapper Labs [Full]

Pagefelt AI Mentor | Pagefelt

Alecto AI | Alecto AI  [Full]

Product Development AI | Rivian [Full]

RecSys - Merlin Models | Allbirds [Full]

Personalized Contextual Product Reviews | Allbirds [Full]

Enterprise Customer Content "Taste" | Coursera [Full]

User Metadata Standardization | Coursera [Full]

Impact of localizing/translating the discovery experience | Coursera [Full]

Monetization journey of existing free users | Coursera [Full]

Data-backed global pricing strategy | Coursera [Full]

Advanced Methods of Time Series Data Analysis | Applied Materials [Full]

Demonstrating Reproducibility in Data Science | Applied Materials [Full]

Sustainability Data Framework | Arm [Full]
 

Strain History Database | Triplebar

Using machine learning to elucidate the genetic underpinnings of multicellularity | UC-Berkeley & HHMI [Full]

The Unnatural Translation Database: Streamlining data entry through automation | NSF Center for Genetically Encoded Materials (C-GEM) 

Enabling drug discovery with AI-powered quantum chemistry | Prescient Design/Genentech [Full]

Identifying the epigenetic and expression profile of regulatory T cells expressing an Ezh2 gain-of-function mutation TBD | UC Berkeley Department of Molecular Cell Biology

Chemoproteomic Analysis of Methionine Redox Sites | UC Berkeley Chemical Biology Lab

LookIt studies: a platform for developmental psychology research | UC Berkeley Department of Psychology

Developing CNN model for segmenting electron microscopy images | Department of Nutritional Sciences and Toxicology [Full]

Evolution of retinal cell types | UC Berkeley Shekhar Lab

Co-evolution inference of key amino acids that allosterically confer protein structure and function from a distance | UC Berkeley Molecular and Cell Biology, UC Berkeley Statistics

TOPH (True Retrieval Of Proteins Homologs): Adapting A Constrastive Question-Answering Framework for Protein Search | Innovative Genomics Institute at UC Berkeley

A computational suite for the RNA universe | Innovative Genomics Institute [Full]

The polymorph evolution of protein two-dimensional crystals | University of Washington

Machine-learning tools for measuring spectral lines | National Institute of Standards and Technology [Full]

Development of Building Component Fragility Database to Support Recovery-Based Seismic Analysis and Design | NIST (National Institute of Standards and Technology) 

Surface Layer Scheme Exploration | NOAA Global System Lab (GSL)

Data on Recovery after Natural Hazard Events | National Institute of Standards and Technology [Full]

Interactive 3D Visualization to enable Visual Analytics for Measurement Science | National Institute of Standards and Technology

Fiber Reinforced Polymer (FRP) Retrofitted Shear Wall Relational Database Development  | National Institute of Standards and Technology

Dataset for Automation of Quantum Dot Devices Control | National Institute of Standards and Technology [Full]

Predicting future water main breaks with pressure data | East Bay Municipal Utility District [Full]

AI applications for Pebble Bed Nuclear Reactor Control and Fuel Management | UC Berkeley Departments of Nuclear Engineering and Geography

SALT Research Group Data Post-Processing App Suite | UC Berkeley Nuclear Engineering

Classification of Dislocation Cores in HCP and BCC Metals | Chrzan Research Group, MSE

Designing Cybersecure Responsive Environments: Evaluating Design Interventions | UC Berkeley, Co-Design Lab

Data Access Pattern of Distributed Disk Cache system | Lawrence Berkeley National Laboratory [Full]

Network performance prediction and anomaly detection |  Lawrence Berkeley National Laboratory [Full]

Graph Neural Network for Online Particle Identification at the Large Hadron Collider | Lawrence Berkeley National Laboratory [Full]

Data Driven Design (Graph Neural Network) of Metamaterials | UC Berkeley Additive Manufacturing and Metamaterials

Detecting illegal sand mining with deep learning and remote sensing | I School

Machine learning to localize particles | UC Berkeley FLOW Lab [Full]

Flexible and Scalable Earthquake Forecasting | The Miller Institute and the Berkeley Seismology Lab

Interaction between Random Heteropolymers and metal ions: Perspective from selective lanthanides separation | UC Berkeley Ting Xu Group

Saving Data from the Archives: Transforming Legacy Engineering Reports into Useful Machine Readable Information | Bureau of Ocean Energy Management (BOEM), Pacific Region

Simplified web-based application to help design high thermal mass radiant systems | Center for the Built Environment

ChatCHW for community health workers | Haas School of Business [Full]

Gamifying cognitive training for emotion regulation | CALM Program

Analyzing Healthcare Prices | UC Berkeley Petris Center [Full]

Does diet reduce antibiotic resistant bacteria in clinical interventional trials | UC Berkeley Computational Biology Program

Exploring Visualization Options with a Django Database | American Heart Association

Trend analysis of birth, acquired, age related disabilities and factors that impact such trends | Voice of Specially Abled People [Full]

EpiNu: Community Nutrition Security in DR Congo | Blum Center for Developing Economies

Homelessness and Mental Illness in California - towards a new scale of outcomes | Healthy Brains Global Initiative [Full]

Recidivism Coding Project: Investigating Potential Changes to Federal Recidivism Tracking | Department of Justice Federal Bureau of Prisons [Full]

Mapping Cultural Institutions in the US | Center for Law, Energy & the Environment (CLEE)

Data on Recovery after Natural Hazard Events | National Institute of Standards and Technology

Predicting lead in tap water | #1471 California State Water Resources Control Board [Full]

Project Sidewalk | Project Sidewalk [Full]

Unmasking Media Bias: Criminal Justice Reform in the News | Criminal Law & Justice Center at UC Berkley Law School 

Do labor market policies reduce racial and ethnic disparities in mental health and substance use? | Institute for Research on Labor and Employment (IRLE), UC Berkeley

Archive of Urban Futures | UC Berkeley Geography Department / Moms 4 Housing

LMC (Language Model Uncertainty) | Moore Accuracy Lab

Adoption of new technologies, women's safety, and trust in formal institutions | UC Berkeley, Stanford University [Full]

The Demise of Urban Renewal and the Invention of Land Banking | UC Berkeley Department of Sociology 

DaanMatch Knowledge Graph | DaanMatch

NGO Insights Dashboard | DaanMatch

Our Way of Life | UC Berkeley School of Social Welfare

Political Party Endorsements of Minority Rights | UC Berkeley Department of Political Science

Community Science Measuring Lead Hazards in Newark, New Jersey | Liberatory Infrastructures Lab

Evidenced-Based Parent Education: The Protective Factors Survey | Aspiranet [Full]

Global Hunger Data & Predictive Model | Bread for the World [Full]

Eviction Research Network | Eviction Research Network

Interrupting Lethal Structures: "No Cop City in San Pablo!" | Berkeley Underground Scholars [Full]

OpenSidewalks: responsible data science for equitable civic analytics | Taskar Center for Accessible Technology

The Opportunities and Risks and its Implications in Clinical Research and Training Development | The Center for Information Technology Research in the Interest of Society and the Banatao Institute (CITRIS)