CCT Data Science Incubator

We provide support for your research.

Our group has expertise in managing, analyzing, and visualizing data and more. Incubator projects provide you with up to 80 hours of our team’s time to collaboratively develop a project that you have ownership of. For examples of past incubator projects, see below.

If you’re curious about incubators, please send us an email or visit our drop-in hours. Most incubator projects begin with a series of conversations with our team. For more details, see our project plan guidelines and our Frequently Asked Questions.

Project Plan Guidelines

“Through the incubator project…I learned new skills, including using GitHub to collaborate on code and developing a complex data dashboard in Shiny. Thanks to this project, I've been able to take on more complex work in my role and continue advancing in the field of data science. I would highly recommend an opportunity to work with this team to anyone looking to grow their skills in data science, such as project planning, data wrangling, and visualization.”

- Terrace Ewinghill, Norton School CRED Scientific Analyst

Past Incubator Successes

Screenshot of the landing page at https://viz.datascience.arizona.edu/gsi-dashboard/

Green Stormwater Infrastructure

We created an interactive dashboard and data wrangling and archiving pipeline for the Campus Living Lab Green Stormwater Infrastructure project.

AFS Standard Fish App

An interactive tool to visualize trends in fish body size and compare user-generated data with database averages from the American Fisheries Society.
AZMet QA/QC Dashboard

AZMet QA/QC Dashboard

We created a QA/QC dashboard to quickly spot potential errors in weather data collected by AZMet
uace dashboard

Statewide Needs Assessment Dashboard

We created a dashboard to explore the results of the 2022 UA Cooperative Extension Statewide Needs Assessment
volcalc logo

volcalc: volatility calculator

volcalc is an R package we created for calculating the volatility of organic compounds.
voc timeseries

Visualizing high dimension VOC timeseries

Analysis and interactive visualization of volatile organic compound (VOC) time series data.
sankey

Scoping Review Interactive Sankey Diagram

An interactive visualization to facilitate a scoping review of biological feedback literature.
agbase website

AgBase

AgBase is a curated resource providing functional analysis of agricultural plant and animal gene products.
Clostridium difficile CDC

C-Diff Dashboard

An interactive web portal to visualize and download data on C. diff regulatory networks.
soil app screenshot

RainManSR Soil Moisture Dynamics Analysis and Visualization

An interactive visualization for soil moisture data and developed moisture release curves for the RainMan project.
biomass level1

Statistical Analysis of Rangeland Restoration Experiments

We designed hierarchical Bayesian analysis to facilitate a paper on postfire effects of rangeland restoration treatments.
homepage of rangedocs

RangeDocs

Automated categorization of rangeland science publications using natural language processing to help rangeland managers find the information they want.
greenhouse

RainManSR Open Data Makeover

We coached the RainMan team on best practices in data management and reproducible research.
predictive rates

Trends in US Organic Agriculture

We developed a multivariate hierarchical Bayesian regression model that estimates trends by state, handles missing data, and predicts future growth of organic farming in the US from USDA survey data.
screenshot

SPARC'd

Improved data sharing and search features for the SPARC’d application that manages data from trail cams used to monitor endangered wildcats and other wildlife.
STAC catalog

STAC Jupyter Notebook

STAC (Spatial Temporal Asset Catalog) is a specification for JSON files (and an API) which provide descriptions and links to spatial and temporal data.

Frequently Asked Questions

  • Who is eligible to participate in incubator projects? Only researchers in ALVSCE are eligible due to funding source limitations. Researchers includes faculty, staff, extension agents, post-docs, and graduate students.
  • What is ALVSCE? ALVSCE includes departments in the College of Agriculture and Life Sciences (CALS), Cooperative Extension, Experiments Station, and Veterinary Sciences.
  • What if I'm not in ALVSCE or otherwise not eligible for an incubator? We are still happy to help you during drop-in hours, and can offer assistance through other means, including grants, referrals, and more.
  • What is the time commitment? Expect biweekly meetings for co-working and training for up to 3 months. We can also work with you to develop a more suitable schedule depending on the project.
  • How much does it cost? Our group's time working on incubators is funded by the Hatch Act. We also require a time commitment by you or someone you manage. This person ("primary point-of-contact") will receive training to take responsibility for the project after the incubator concludes. 
  • Can I just hire you to do the work? Yes, we can do this! Work for hire is not suitable for our incubator program, which emphasizes training and enabling researchers. We will work with you to determine the best way to do this.
  • What are some types of project outcomes you have had in the past? There are examples of previous incubator projects on this page.
  • What happens at the end of the project? For most incubators, we transfer responsibility and ownership of the work product (e.g., GitHub repository, Shiny app) to your team. If issues arise after the incubator concludes, we are are always available by email or at drop-in hours. 
  • What if I need more extensive help beyond 80 hours? An incubator can be used to pilot a project even if you know it will eventually need more time. After the 80 hours are up, we can continue to work with you from your funded grants. We can also collaboratively pursue outside funding. 
  • What counts as data science? Our team has a broad set of skills and interests—contact us with your ideas!