Country of Residence
United States
Age
17
Project title
x
Project Summary: Describe your project in one sentence
x
Website URL(s) or social media handles.
colicast.com // https://www.linkedin.com/company/colicast/
Project Category
My project is an existing project that I started
Project Stage
Scaling (We’re expanding impact to new locations or in new and innovative ways)
Founding Story: What was the spark that led you to start your project? What was the "Aha!" moment that led you to get started and see the potential for this to succeed?
ColiCast began in my local community, where swimmers often debated whether it was safe to enter the water after rainfall. I wondered why people had to make health decisions with so much uncertainty, so I began researching whether environmental data could help predict E. coli contamination. I spent months building a multivariable regression model, refining variables and analyzing water-quality and environmental data. But, the turning point came when I joined EarthEcho International’s Water Challenge Ambassadors. I saw that the methods I had developed using publicly available tools could extend beyond my own research and reach communities facing similar questions, starting from this global community of changemakers. I also recognized a gap in my own work: the technical language I loved was often inaccessible to the residents making everyday decisions about water safety. A model could produce a strong prediction, but if a swimmer could not understand or use it, nothing had really changed. That idea pushed me to explore a location-based tool and survey high school swimmers in East Haven about the information they needed, and ColiCast grew from an effort to predict contamination into an initiative to make water-quality knowledge accessible, locally relevant, and actionable.
The Problem: What problem are you helping to solve? Why does it matter to you and your community?
Water contamination is often treated as a laboratory problem: collect a sample, test it, and report the result. Yet communities need information between tests, too. E. coli levels can change with rainfall, runoff, land use, and other environmental conditions, while testing may be too costly, infrequent, or geographically inaccessible to provide timely guidance. A beachgoer deciding whether to swim may have no understandable information to help assess that day's risk. I saw this gap while developing my prediction model and speaking with local swimmers. Scientific data existed, but it was not necessarily reaching the people whose health decisions depended on it. The gap is especially consequential in underserved communities, where access to environmental-health education and research resources can be limited. As ColiCast expanded internationally, partners described local concerns ranging from polluted waterways to limited opportunities for young people to learn and conduct research. These communities have the motivation and local knowledge to improve their environments; they need accessible tools and resources to turn that knowledge into informed action. Safe water should not depend on access to a laboratory or the ability to interpret a technical report.
Your Solution: How are you solving this problem? Share your specific solution.
ColiCast connects three approaches: predictive research, community-based water testing, and accessible education. First, I developed an E. coli prediction model combining locally collected water-quality measurements with public environmental and geospatial data, including NOAA rainfall and GIS-based land-use features. Using Python and Google Colab, I examine spatial patterns and rainfall time lags to investigate how surrounding conditions influence contamination risk. In my East Haven research, the model achieved an R² of 0.92, compared with a 0.70 benchmark. I am translating its regression equations into a location-based tool on the ColiCast website, allowing users to explore predicted risk beyond isolated test results. Second, ColiCast works with Regional Directors and community partners to distribute testing resources and adapt monitoring methods to local conditions. Partners identify relevant indicators and concerns, keeping implementation locally relevant. For example, partners have explored microplastic reduction in Uzbekistan and water-quality testing opportunities in Singapore. Their observations help guide what data to collect and which questions to investigate. Third, we turn research into educational materials for young people. Partners adapt lessons to local concerns and languages; in Burundi, for example, materials are being localized for French-speaking learners. Students can use these resources to understand water-quality issues and participate in monitoring. Together, these components create a cycle: communities contribute observations and testing, research helps interpret patterns and estimate risk, and accessible tools and education help people use that information. ColiCast connects scientific analysis with decisions about water safety.
Impact: How has your project created impact / made a difference so far? Or, if at an early stage, what will impact look like?
ColiCast has grown from my independent research into an international initiative active in 40 communities across 23 countries. We have distributed 2,088 water-quality tests, giving local partners and young people resources to engage directly in water monitoring. Based on the populations our partners serve, we estimate that the initiative has the potential to reach approximately 350,000 residents. ColiCast also creates opportunities for youth to participate in environmental-health research and education. I presented the project to approximately 150 students at the Harvard Global Health and Leadership Conference. This project was also named a finalist in the Global Youth Awards’ Educational Innovation category, selected from 237 nominations across 64 countries. My research methodology has also received recognition through the Connecticut Science and Engineering Fair and Connecticut Invention Convention, and an abstract is scheduled for publication through the American Geophysical Union in December. Beyond recognition and distribution numbers, ColiCast is building a network in which students and community partners connect local water concerns with testing, data, and education. I measure its success by whether communities gain better information and greater capacity to understand their water.
Your Innovation: What is different about your project compared to other programs or solutions already out there? How is your project new or innovative?
Many water-quality efforts address only one part of the problem: laboratory tests identify contamination in a collected sample, while predictive models can reveal patterns that remain difficult for residents to interpret or use. ColiCast connects these approaches and brings them into community settings. On the technical side, our model combines locally collected water-quality measurements with public environmental and geospatial datasets, including rainfall and land-use information, to investigate how changing local conditions relate to E. coli risk. In East Haven, the model achieved an R² of 0.92 against a 0.70 benchmark. The idea of multivariable regression is not new, however, but the initiative to make this kind of analysis more accessible and useful in communities that may lack the resources to conduct comparable research. ColiCast also differs in how it is implemented. Predictive tools are paired with localized testing and education through an international network of community partners. Regional Directors adapt monitoring and learning materials to local priorities, while residents contribute knowledge that datasets alone cannot capture. For example, a partner in Ghana described how illegal mining, known locally as Galamsey, had turned once-blue waters rusty yellow. That context helps determine which questions matter and what information communities need. By connecting scientific prediction with local expertise and accessible education, ColiCast makes environmental-health research more participatory and actionable.
How many people are on your team?
42
Your team: What role(s) do your team members play? How do you share leadership with them?
I founded ColiCast and led its research, partnerships, and development. Our international network includes 40+ Regional Directors and community partners who coordinate local testing, adapt monitoring to their environments, and share findings. I also lead educational-materials development for young people. Leadership is shared: partners guide implementation and priorities in their communities, while I provide research methods, tools, resources, and coordination.
What’s Next: What are the next steps you plan to take to grow or strengthen your project over the next year? If your project is still in the idea stage, describe the steps you will take over the next three months to launch or begin developing it.
Over the next year, I plan to strengthen ColiCast in three areas: scientific validation, community usability, and local leadership. First, I will expand the model’s validation using additional water-quality observations from partner communities. Because environmental conditions vary by region, I want to test how well the model transfers across locations, identify where it needs local adjustment, and refine it with new observations, building off of our standard model, instead of sticking rigidly to it. Second, I will improve the location-based tool so users can explore local risk estimates and understand what predictions do and do not mean. Feedback from swimmers and community partners around the world will guide its design and help ensure that the information is understandable and useful for real decisions. Third, I aim to grow the Regional Director network from 40 to 80 communities, provide adaptable educational materials, and create more opportunities for partners to share results and learn from one another. I also plan to build relationships with laboratories and water-focused organizations that can support testing and validation. My goal is to grow ColiCast responsibly: beyond simply distributing more tests, to also help each community build the knowledge and capacity to monitor its water and act on what it learns.
How do you encourage other people to join your project or learn about the problem you’re working on? If you have a new idea, tell us how you will do this in the future.
I invite others into ColiCast by giving them an active role in understanding the water in their own communities. Through our international Regional Director network, students and community partners organize local testing, identify environmental concerns, share findings, and adapt educational materials for their peers. This gives participants opportunities to contribute to environmental-health work, in addition to learning new information. I also recruit students interested in environmental science and global health through direct outreach, and have presented ColiCast to more than 10 nonprofit organizations to develop partnerships and share opportunities across their networks. In these conversations, I emphasize that local knowledge is essential: a model may reveal a pattern, but residents can explain what is changing in a river, how people use it, and what information would help them respond. As the network grows, I plan to create more opportunities for students to lead monitoring efforts, interpret results, and present findings to their communities. I want young people to see themselves as more than just learners, but also contributors to the research and decisions that shape their environment.
