Inspiration

analyzing geospatial data and deriving valuable insights from it

What it does

Use the data from GeoDI to show which are areas within Florida having high risk from Mosquito-borne-diseases and take a wholistic public health approach by considering distances to hospitals and population density data. Worked on building an AI-based trip planner that uses historical data to help people plan safer trips. Using GeoDI data, We identified areas in Florida with high risk of mosquito-borne diseases by performing historical risk analysis and creating heatmaps of high-density breeding clusters.

How we built it

We started with reference samples provided on https://geo-di-lab.github.io/emerge-lessons/ for environmental risk mapping and used a hospital dataset from USGS.

Challenges we ran into

We were stumbling across errors from time to time... but we were individually able to get past each. We ran into issues being able to share our datasets across all of our devices while working in Google Colab, but figured out how to use them with our individual Google Drives.

Accomplishments that we're proud of

We are proud of pushing through all the challenges that came with using outside datasets and getting them to display properly on eye-catching maps using our coding skills.

What we learned

We learned how to perform nuanced analysis by combining multiple variables on individual maps.

What's next for Intermediate: Mosquito Risk Mapping

We would like to be able to make a public interactive database with layers where people can see where mosquitoes are actually reported compared to where we map the risk being the greatest. We would like this to also function as a guide for people to access medical resources in their area if they are concerned about mosquito-borne illnesses.

Built With

  • jupyter
Share this project:

Updates