• 

  Low Change In Pollution Early Time Frame Prediction

• 

  Low Change In Pollution Late Time Frame Prediction

• 

  Low Change In Pollution Mid-Time Frame Prediction

• 

  High Change In Pollution Mid-Time Frame Prediction

• 

  High Change In Pollution Early Time Frame Prediction

• 

  High Change In Pollution Late Time Frame Prediction

Plant Resilient USA!!

Application which maps and identifies areas in the Southern part of the U.S. which will be negatively effected by climate change.

Inspiration:

Our team knows so many people from the Florida area, and we would hear about their experience with their change in climate as they grew up in the coastal state. One of our friends really loves plants, and city planning, but the issue was that so many plants would die fairly soon after being planted in Miami, where she originally is from. Therefore we decided to make this application in honor of her passions and worries.

What it does:

This is a climate analysis tool, that utilizes data that we collected and parsed through, and can give predictions of plant hardiness zones by zip code. This can help future city planners, as well as save the lives of many plants that can be methodically planted to ensure their likely survival.

Prediction of High Change In Pollution in an Earlier Time Frame

Prediction of High Change In Pollution in an Mid-Time Frame

Prediction of High Change In Pollution in an Late Time Frame

Prediction of Low Change In Pollution in an Earlier-Time Frame

Prediction of Low Change In Pollution in an Mid-Time Frame

Prediction of Low Change In Pollution in a Late Time Frame

How we built it:

We utilized Python for data collection and climate forecasting to create a dataset for the future hardiness zones in early-, mid- and late-century in Southeastern USA, according to USPS zip codes. The data came from the US Department of Agriculture.

Challenges we ran into:

This was our first ever hackathon! No one on this team has ever competed in a hackathon, and we have very little experience in working in the full stack. Our team had to work on the fly and learn quickly how to best implement this idea with the time constraint and lack of front-end knowledge. This meant that at times we had to consult with AI to help in the design process and implementation of certain features and frameworks.

Accomplishments that we're proud of:

We are incredibly proud of the application and the UI that our team has put together, considering how little we know about front end development. We are also extremely proud of how helpful this tool is and can continue to be!

What we learned:

We learned a lot about the front end part of the stack, as well as data collection and databases! We learned how to best utilize our resources and how to solve our problems in the most time efficient manners!

What's next for Plant Resilient USA:

We plan to take this idea further and upscale it to other regions of the USA, and to include more in depth knowledge of the plants themselves that can be planted in certain regions/hardiness zones. We want to create a database for native plants to local zip codes, employ machine learning to more precisely predict regional temperatures in the future and use unsupervised learning to divide hardiness zones. However, the available data and climate forecast by US Department of Agriculture is robust enough to showcase the changes in hardness zones as climate changes. And of course, we want to make the UI look more appealing when we find the time!

Built With

• chatgpt
• mern