Inspiration
We were inspired by recurring flooding in our own hometowns, to find a way to better protect those impacted.
What it does
HydrOracle uses data available from the United States Geological Survey (USGS) for water level data and the National Weather Service for flood thresholds to create graphs that display flooding data along the Mississippi River. We used 10 stream gages across the river to obtain info on daily streamflow, which totals to 36,000+ pieces of data. We then used integration and linear regression techniques to learn more about how we could predict future trends.
How we built it
We transferred water level data from USGS to Excel for organization and visualization, and then to Taipy for the presentation and formatting of it into an easily interpreted page.
Challenges we ran into
Taipy seems to be very new, and we were able to find very limited tutorials on how to use any of it. Creating predictions also brought a large set of difficulties and consistently raised new obstacles, from how specific we could be, to how much accuracy we could capture.
Accomplishments that we're proud of
We're very proud of delving into unfamiliar data sets and technology that we had very little to absolutely no experience with.
What we learned
We learned a lot about cleaning and formatting data, working with Taipy and new frameworks in general, and working as a team.
What's next for HydrOracle
HydrOracle will be expanding its data sets and predictions to new locations and time frames. Additionally, a full website will make the information even more accessible.
Log in or sign up for Devpost to join the conversation.