Projects

Our group works with collaborators in CALES and throughout the University to help implement computationally-intensive components of grant-funded projects. Click on the cards to read more about our current and past funded collaborations, or reach out if you are interested in working together!

“The CCT Data Science Team has been incredibly helpful to the USA-NPN team, offering trustworthy analytical support and guidance. We have really benefited from their expertise in calculating temporal trends using raster datasets.”

- Dr. Theresa Crimmins, NPN Director & SNRE Associate Professor

Screenshot of RangeDocs homepage, with six people in a field looking at a map

RangeDocs AI/ML

Improved searching and automated categorization of rangeland science publications using large language modeling tools to help rangeland managers find the information they want.
A conceptual graphic of the proposed data analysis pipeline. Each step is represented by a stack of maps of the continental US. The top reads: "For each year, 1981-2023; geographic extent of all maps: NE US". Then, from left to right: "Inputs: Daily mean temperature (source: PRISM)", "Intermediat products: DOY maps for GDD thresholds", "Output: Mean DOY for each threshold, 1991-2020". Pointing downward from the intermediate products is an arrow labeled "Calculation of trends and variation for each thres

Estimating Trends in Phenology

In collaboration with the National Phenology Network, we are creating an analytical pipeline to estimate spatial trends in the time to reach different thresholds of growing degree days in the Northeastern USA.
azmetr logo

AZMet data QA/QC

As a continuation of our Incubator project with Jeremy Weiss, we released a new version of the {azmetr} R package, which facilitates accessing AZMet data and automated QA/QC checks to alert managers to data issues.
A map of Arizona where the standard deviation in AGB is represented by color. There is high standard deviation in areas that roughly correspond to mountain ranges and low standard deviation in lower elevations.

Estimating Uncertainty in Carbon Stores

We are working with David More and Yang Li of the School of Natural Resources & the Environment to build an analytical pipeline characterizing uncertainty in estimates of above-ground biomass, to help stakeholders make informed decisions about which data products to use for their needs.

forestTIME

In collaboration with Margaret Evans's lab and colleagues at the US Forest Service, we are building a suite of tools to facilitate access to the USFS Forest Inventory and Analysis dataset in timeseries form.
The PSInet logo, with a PSI symbol with leaves like a tree and water flowing from the roots to the leaves.

PSInet

Our group is working with colleagues at Indiana University and worldwide to build a global database of plant water potential measurements through the PSInet RCN project.
volcalc hex logo. Purple to white gradient with colored lines and the word "volcalc"

volcalc

In a continuation of our Incubator work with Laura Meredith, and with additional support from the R Consortium, we built and released an R package for calculating estimated relative volatility values of organic compounds.
Flow chart for genopheno envo project showing relationshp among project components.

GenoPhenoEnvo

Our group curated phenotypic and meteorological data for use as part of the NSF Ideas Lab Project "Converging Genomics, Phenomics, And Environments Using Interpretable Machine Learning Models".
ARDN diagram

Agricultural Research Data Network

We joined a cross-institutional collaboration to convert pre-existing agricultural datasets to a standardized format and create an Agricultural Research Data Network, to improve the findability and resuability of agricultural data.
pipeline graphic

Drone Processing Pipeline

Our group built a high-throughput sensor data processing pipeline, including data from drones and other platforms, for agricultural research and beyond.
terra ref in the field

TERRA-REF

We worked with a large network of collaborators to help build the world's largest public domain agricultural dataset to facilitate combining remote sensing, phenomic, genomic, and weather data.
pecan logo

The Predictive Ecosystem Analyzer: PEcAn

We joined a large, multi-institutional collaboration to build accessible tools for running ecosystem models, with applications including models of genetically modified crops and bioenergy crops.

SENTINEL Phytosensors

As part of the SENTINEL: SENsing Threats In Natural Environments project, our group conducted biophysical and ecological modeling to predict the functioning, ecological impact, and physiology of plants that have been genetically modified to act as sensors to detect chemical and biological threats.

“CCT Data Science has been critical in the modernization of AZMet (Arizona Meteorological Network) by setting up our GitHub organization, developing the `azmetr` package for programmatic access to our API in R, and building a data QA/QC dashboard with automated alert features. Their work now supports AZMet in day-to-day operations and sets the stage for further progress. More importantly, their work helps AZMet provide better service to its wide range of stakeholders, from individual growers to government agencies.”

- Dr. Jeremy Weiss, AZMet Program Manager, Cooperative Extension