RCI

The RCI project began when a friend invited me to help develop a predictive metric for environmental disaster preparedness. As climate change increases the frequency and severity of natural disasters, the goal of RCI was to shift focus from reactive response to predictive intervention — identifying at-risk regions early and directing resources before disasters occur.

My primary responsibilities included data collection, systems design, modeling, and interface development. I conducted extensive research into public and private datasets, eventually identifying three reliable data sources. I then designed a custom data ingestion and analysis pipeline that normalized these sources onto a unified scale. Using weighted scoring, I helped create a single metric from 1 to 100 that represented how prepared a given region was for disaster response.

I also built a web-based interface that allowed users to enter a ZIP code and receive a computed RCI score along with supporting charts and insights. To improve usability, I implemented an interactive map that allowed users to explore regions visually rather than relying solely on numeric input.

Although the project was paused due to funding limitations, it was a deeply valuable experience in applied data science, predictive modeling, research pipelines, and full-stack development. I remain passionate about environmental data work and predictive systems.