Skip to main content
Seed-Funded Projects
AI + Science

Developing Artificial Curiosity Algorithms

Creating an AI agent capable of independent, rigorous scientific discovery in a laboratory meta-fluid with complex flows.
AI + Science

Discovering the Design Rules Linking Protein Sequence to Function

Using and developing advanced multi-modal generative AI models to map the relationship between protein sequences and their functions, enabling the design of novel proteins with desired properties.
AI + Science

Machine Learning Models for Predicting Heart Disease Progression

Developing machine learning models for endothelial tissue mechanoresponses to establish a link between force adaptation and heart disease progression.
AI + Science

Building Cyberinfrastructure for Rare-Event Searches

Developing a dedicated cyberinfrastructure for the application of data-demanding machine learning techniques to rare-event searches, using XENONnT, a dark matter search, as a testbed.
AI + Science

Using Field-Effect Transistor Array to Monitor Water Quality

Using a deep-learning approach to overcome the challenges in the sensing accuracy and reliability of field effect transistors sensors and achieve real-time monitoring of multiple nutrient ions simultaneously.
AI + Science

On-Chip Machine Learning for intelligent Pixel Detectors

Developing next generation microelectronics with on-chip machine learning for future intelligent pixel detectors.
AI + Science

Improving Batteries to Combat Climate Change

Establishing a fully automated, research-grade platform for the assembly and evaluation of batteries by integrating AI-driven models for predicting electrolyte properties with a high-throughput (HT) robotic system for battery construction.
AI + Science

Automating Electron Microscopy with AI

Using machine learning to develop a fully automated electron microscopy workflow to greatly increase data acquisition and analysis throughput by automatically acquiring and denoising images and classifying size and shape dispersity.
AI + Science

Improving Prediction of Breast Cancer Patient Response to Therapy

Using high-plex immunofluorescence to develop meaningful and interpretable spatial features of the tumor-immune microenvironment in breast cancer to improve prediction of patient response to therapy.
AI + Science

Predicting Material Properties

Addressing the inherent complexities of materials science by developing a graph neural network to predict material properties.
Data & Democracy

Facebook Messenger Chatbot for Surveys and Intervention Testing

Developing a chatbot that can be used for researching information consumption and messaging interventions for political participation and behavior.
Data & Democracy

Understanding Divergent Interpretations of Political Information

Using a combination of methods from neuroscience, linguistics, and computer science, to refine existing approaches for measuring political bias.
Data & Democracy

Understanding and Auditing Content Moderation Policies

Combining computer science and law approaches to conduct an empirical study of the moderation policies and practices of popular social media platforms.
Data & Democracy

Partisan Polarization and Political Dysfunction

Does polarization produce government dysfunction, or do impediments to lawmaking propagate political extremism?
AI + Science

Examining The Mystery of How Living Organisms Develop

A machine learning pipeline that extracts the underlying principles of cell behavior from experimental data, offering new possibilities for the application of bioengineering in clinical diagnosis.
AI + Science

Advancing Molecular Measurement with Machine Learning

Developing new machine learning techniques to improve spectroscopy and discover new molecules present in your body, your microbiome, and the environment.
AI + Science

Creating Microbiomes That Improve Human and Environmental Health

Using machine learning and statistical modeling to create thousands of synthetic microbiomes that could help safeguard human health and protect the environment.
Internet Equity

Interconnection Measurement Project

Creating a common tool to measure internet traffic across ISPs
"Adenoid cystic carcinoma" by Yale Rosen. https://www.flickr.com/photos/30950973@N03/5600774541
Discovery Challenge

Machine Learning to Improve Targeted Cancer Therapy

Can a combination of AI, genomics, and pathology create more effective personalized cancer treatment?
Discovery Challenge

Advancing the Sociome For Social and Health Equity

Social factors influence health and disease. How can we use them in data-driven medicine?
Discovery Challenge

AI-Driven Tutorials for Radiology Student Training

Can the success of AI for radiology diagnosis help train tomorrow’s radiologists?
A structure called a Sidestream Elevated Pool Aeration station in the Chicagoland Cal-Sag Channel and Calumet River is intended to aerate the river water, which protects fish populations and eliminates odors. Credit: Metropolitan Water Reclamation District
Discovery Challenge

AI-Assisted Molecular Engineering to Detect and Remove Water Contaminants

How can we better detect and remove dangerous contaminants from water?
AI + Science

Learned Emulators of Physics Simulations

Explore the mathematical limits of learned emulators for climate, astrophysics, and high-energy physics models and quantify key trade offs related to accuracy and speed
AI + Science

Real-Time Adaptive Deep Learning for Discovery Science

Design new “system-on-a-chip” hardware to help researchers in data-intensive fields monitor data quality and detect promising results without interrupting the flow of data
AI + Science

Artificially Intelligent Electrochemistry

Use AI to find new, efficient ways of “recycling” CO2 into valuable products such as ethanol and ethylene, using clean electricity generated from the sun and wind
Project

Health Monitoring Based on Wearable Sweat Sensors

Engineer a wearable featuring skin-compatible chemical sensors to enable real time continuous sampling of biomarkers from sweat and open new avenues for medicine.
Project

Automated Prostate Cancer Detection Using MRI and Deep Learning

Apply deep learning methods to cutting-edge medical imaging to improve the diagnostic accuracy of detecting prostate cancer.
Discovery Grant

Deciphering Cuneiform with Artificial Intelligence

Use computer vision to assist researchers by automatically identifying symbols and words in images of cuneiform tablets.
Discovery Grant

Measuring Messages About Race and Gender in Children’s Books

Understand children’s exposure to race- and gender-coded messages with new methods in human-directed, machine-implemented content analysis.
Project

Learning How To Measure Scientific Images

Create a visual, interactive data analysis system that will lower the human cost of creating new ways to study nature.
Project

Computer-Assisted Diagnosis of Indeterminate Thyroid Lesions

Develop a new computer-assisted diagnosis approach to define imaging features of benign, malignant, and indeterminate thyroid lesions on ultrasound.
This undated handout image provided by NASA/JPL-Caltech/University of Michigan, shows The Four Corners area, in red, left, is the major US hot spot for methane emissions in this map showing how much emissions varied from average background concentrations from 2003-2009 (dark colors are lower than average; lighter colors are higher. Satellite data spotted a surprising hot spot of the potent heat-trapping gas methane over part of the American southwest. Those measurements hint that U.S. Environmental Protection Agency considerably underestimates leaks of natural gas, also called methane. In a new look at methane from space, the four corners area of New Mexico, Colorado, Arizona and Utah jump out in glowing red with about 1.3 million pounds of methane a year. That’s about 80 percent more than the EPA figured and traps more heat than all the carbon dioxide produced yearly in Sweden. (AP Photo/NASA, JPL-Caltech, University of Michigan)
Project

Machine Learning and Satellite Imaging to Reduce Methane Emissions

Develop a data-driven approach to methane emissions monitoring and regulation that leverages machine learning and high-resolution emissions measurements from satellites.
Discovery Grant

Disentangling Visual Style and Content

New style transfer models that separate, capture, and manipulate content and style, unlocking potential for art and science.
Discovery Grant

A Data-Driven Trigger System for the Large Hadron Collider

Automate the "trigger system" of the Large Hadron Collider by applying recent advances in artificial intelligence to the energy and intensity frontiers of particle physics.
AI + Science

Automated Experimental Design for Cosmic Discovery

Use AI to automate the design, optimization and forecasting of cosmic survey experiments.
AI + Science

Is Climate Change Changing Clouds?

Use machine learning and computer vision to classify cloud textures and patterns, and how those features have changed over time, in order to improve climate projections.
AI + Science

Neural Network Algorithms to Decode the Octopus Neural Network

Scientists will use computational techniques to map the neural network of an octopus, the largest invertebrate brain, and better understand the fundamental principles of neuroscience.
Project

Clinical Behavior Analysis via Unsupervised Learning

Unsupervised feature clustering to identify and model patient clinical behaviors from their electronic health records.
Project

Identifying Optimal Skill and Relationship Mixtures

Use unprecedented access to the complete LinkedIn dataset to identify mixtures of knowledge, skills, and relationships that maximize income and future potential for participants in the knowledge economy.
Project

A Data Processing Pipeline for Police Communications

Build a pipeline for automatically transcribing law enforcement radio communications, creating a new data source for the study of adverse police outcomes.
Project

Racial Inequality in Financial Resilience

Use data science to study how how households of different racial backgrounds cope with difficult economic shocks.
Project

Mobile Decision-Making for Doctors Without Internet

Create a mobile Android app for physicians working in areas with poor internet coverage, enabling data-driven medical diagnosis and medical record access in the field.
Project

N-body Networks for Jet Physics at the Energy Frontier

Build a new kind of neural network architecture that reflects the physical laws governing subatomic particles, isolating meaningful signal from massive data streams and revealing previously unwitnessed particles and forces.
Project

Rational Protein Engineering using Data-Driven Generative Models

Combine machine learning with high-throughput gene synthesis and rapid assay to learn nature’s rules for protein design and create synthetic proteins with elevated or new properties.
Project

The Role of Rapid Bacterial Evolution in Human Health and Disease

Apply machine learning to capture the diversity of plasmids in the microbiome, the rich population of microorganisms associated with humans and the natural environment.
Project

Quantifying Social Determinants of Cardiovascular Disease

Physicians, epidemiologists, and spatial data scientists produce a new cardiovascular disease model that combines clinical and social risk factors.
Discovery Grant

Exploring Climate and Biodiversity with 3D Deep Learning

Use deep learning and modern 3D imaging technology to understand the impact of climate change on the diversity of global marine species.
arrow-left-smallarrow-right-large-greyarrow-right-large-yellowarrow-right-largearrow-right-long-yellowarrow-right-smallfacet-arrow-down-whitefacet-arrow-downCheckedCheckedlink-outmag-glass