A Blazing Future

Inspiration

We were inspired due to the effects of climate change on the US. We realized the devasting impact of carbon emissions and nonrenewable energy and wanted a way to show what our actions are doing to our globe. Although the effects of global warming are only seen over long periods, making it hard to notice firsthand, we can use predictions and past data to show what global warming is doing to the United States.

What it does

The project takes user input of a year and a state and gives information based on the inputs. The linear regression model shows how much the average temperature in a state changed from 1900-1970, 1970-2020, and the predicted change from 2020 to the inputted year.

How we built it

We used a dataset of over 100 thousand recorded temperatures monthly, from all 50 states. We used this data to train a linear regression model and form an algorithm to predict the temperature in a state at a certain date. We then used the data of past years to calculate the differences and also find a final value for the increase in temperature in the future.

Challenges we ran into

We ran into many challenges with the front-end of our project and also linking our front-end to our back-end. We also had problems with the organization of the dataset, having to refactor it and create two separate models that trained different time periods of data, instead of one overarching model, in order to create better accuracy.

Accomplishments that we're proud of

We believe we created a model that clearly demonstrates the effects of global warming, and used the data efficiently and cleverly to reach our final project. We are not very familiar with the use of Django to present our front-end, so we are proud of our ability to learn it as we went and figure out our mistakes. We ended up with a correlation coefficient of .90, which we were very happy with.