CORVALLIS — A faculty-led, student-driven Oregon State University initiative that uses data science to address issues in rural communities is underway with projects ranging from the impacts of air quality on health in Lane County to regulatory impacts on economic development in eastern Oregon.
Data Science for the Public Good leverages OSU's significant expertise, resources and infrastructure to address community needs. It launched this spring with five Young Scholars teams comprised a total of five graduate students and 10 undergraduate students from five Oregon institutions: OSU, the University of Oregon, Portland State University, Reed College and Southern Oregon University.
The students participated in June in a 10-day training course in data analysis and programming. Through late August they will be guided and mentored by a faculty member with expertise in the relevant area.
The students are learning about data formats, methods in machine learning and statistics, databases and storage, data visualizations, project management and common tools such as R, the statistical programming language, Leaflet, the interactive mapping library, and software development repositories git and GitHub.
The projects were identified by local stakeholders through the OSU Extension Service and focus on analyzing data provided by those stakeholders, who are communicating frequently with the data-science research teams working on their project.
The projects include:
- Wintertime air quality health impacts in the Lane County communities of Oakridge and Westfir;
- Impacts of dam water release policy on Deschutes River health and recreation;
- Forecasting tools for cost analysis of water and wastewater facilities in Oregon small towns and cities;
- Regulatory impacts on economic development in the eastern Oregon border region;
- Water quality requirements for fresh produce growers.
These projects are intended to provide the students with collaborative data science research experiences in real-world settings, and provide rural stakeholders with data science analyses relevant to an issue of interest.
Ten of the 15 students come from rural backgrounds. The initiative serves as a platform to introduce them to careers in the knowledge economy, said Brett Tyler, director of OSU’s Center for Genome Research and Biocomputing who is serving as a co-principal investigator on the grants funding the project.
In addition to student experiential learning, the initiative also focuses on creating a set of online resources for other universities and training Extension staff to bring data science projects into the communities they serve, Tyler said.
Data science, also known as “big data,” can be used in areas such as precision agriculture, resource management, inventory management, and medicine and healthcare. In an increasingly information-driven society, rural communities are facing new challenges, Tyler said. These challenges affect people, towns, local governments, businesses large and small, and industries ranging from manufacturing to agriculture.
The solutions to some of the problems they are facing may be found in the data towns and cities already collect, but lack the resources to access and analyze, Tyler said.
“This is where Data Science for the Public Good steps in,” Tyler said. “There’s a growing disparity between access and the tools available with data science and rural communities. The data science needs for our rural communities is very extensive. The communities that are able to access data science approaches are doing well and those that can’t are falling behind.”
Due to COVID-19, the Young Scholars Program is being conducted entirely online, with faculty, trainers, students, and stakeholders communicating via online messaging platforms.
“A data science summer research experience is uniquely well-suited to a fully online environment,” Tyler said. “It illustrates how rural communities and rural data scientists can connect virtually to expertise across the state.”
Data Science for the Public Good is part of a tri-state collaboration involving the Center for Genome Research and Biocomputing and OSU Extension with the University of Virginia, Iowa State University, Virginia Tech and Virginia State University. It is funded by separate $1 million grants from the U.S. Department of Agriculture National Institute of Food and Agriculture and the Bill and Melinda Gates Foundation.