Projects

Sewanee DataLab projects involve real-world learning.

Working in small teams, students learn to frame client problems, develop and articulate project milestones, and to effectively communicate the value of their work. They also learn to code algorithms in R. Each project is completely unique. From healthcare access in Appalachia to carbon offset in Haiti, projects represent a wide range of social and environmental issues from around the globe.

Equitable Broadband Access

Carbon Sequestration

Image processing

public Health

Equitable Broadband Access

Project Contributors: Pravesh Agarwal, Zachary Shunnarah, Feza Anaise Umutoni

Community Partner: Thrive Regional Partnership

Thrive Regional Partnership is a non-profit based in Chattanooga who collaborated with Sewanee DataLab to highlight the disparity of broadband internet access in its neighboring communities.

Problem: Due to the lack of broadband asset inventory, there is an insufficient understanding of broadband assets and access which restricts the ability to explore trends and patterns in broadband access.

Solution: The DataLab team created an interactive open source map showing the available broadband assets and distribution in 16 counties of Tennessee, Georgia, and Alabama.

Impact: The online dashboard highlights the disparity in broadband assets and distribution, which will allow for necessary intervention to bridge the gap in broadband disparity of the tri state region that was evaluated.

Equitable Broadband Access

Sewanee DataLab

A Sewanee DataLab team of 3 worked to increase equitable internet access

Carbon for Cash

Project Contributors: Kate Baker, Nika Gorski, Caroline Willett

Community Partner: Zanmi Kafe, a carbon offset program in Haiti

Zanmi Kafe’s work offsets carbon emissions by planting trees on Haitian farms, which improves economic stability for the farmers.

Problem: Zanmi Kafe needed a uniform process to pay farmers and to efficiently calculate carbon sequestration using a vast amount of raw data.

Solution: To solve this issue, Sewanee DataLab developed an interactive dashboard that displays and analyzes the data.

Impact: DataLab’s work has allowed Zanmi Kafe to quantify and analyze the carbon sequestration of their project. The dashboard created will continue to calculate data in future years and serve as a model for other small-scale carbon markets.

Carbon for Cash

Sewanee DataLab

Sewanee is in collaboration with the Haitian organization, Zanmi Agrikol, to incentivize 50 family farmers to grow trees instead of selling material for coal through payments made by the Sewanee Green Fund.

Image Processing

Project Contributors: Dirk Kayitare, Ngan Nguyen, Pratham Singhal, Sophie Smith, Katherine Zelaya

Community Partner: 1. Haiti Institute and 2. Ancient Art Archive

Collaborating with the Haiti Institute and the Ancient Art Archive, the Sewanee DataLab photos team applied machine learning techniques to curate photographic evidence of the impact of Sewanee’s work in Haiti.

Problem:

No conclusions or insights have been drawn from the files of photos from Haiti.
Rock art is continuously threatened by people and the environment, and as the rock art disappears so do the stories behind them.

Solution:

Convolutional neural networks were used to quantify objects and humans in the photos, drawing necessary conclusions and insights from the images.
Convolutional neural networks were used to label and digitize rock art objects, allowing the rock art and its stories to be safely stored.

Impact:

The work from the summer measured economic development and informed conversations about development in the community.
The work also created statistical tools for research and preservation of heritage sites.

Image Processing

Sewanee DataLab

The Image Processing team does not have a dashboard or demo video of the dashboard to display since their work did not involve the creation of a dashboard.

Health Care

Project Contributors: Martha Clark, Kirstyn George, Esarrah Hopkins, Mehrael Ibrahim, Shehryar Khan, Jeremiah Studivant

Community Partner: South Cumberland Health Network

The public health team partnered with the South Cumberland Health Network to create a reliable resource to analyze health disparities in the region.

Problem: A wide range of Tennessee health-related information is dispersed across the internet and not organized into one location. Due to the unorganized nature of the health-related information, some hospitals have become overwhelmed with patients due to lack of access.

Solution: The team collected and consolidated the data from various sources into a database which analyzes trends and presents its findings in an online interactive dashboard.

Impact: This project brought together Tennessee health information into one centralized location that will allow for problems to be identified and solutions to be created in response to the findings.