COVID-19, a disease caused by the 2019 novel coronavirus, seems to have become a widespread global pandemic out of nowhere. Governments passing policy aggressively and decisively and spending billions (or trillions) of dollars in trying to combat the disease. It's easy to see the importance of the investment of time and money to combat the pandemic - over the course of the past few months, nearly 700,000 people worldwide have become infected. However, over the past few decades, there's been another pandemic that has been taking lives but still hasn't been addressed by many world governments - climate change. Our goal during this hackathon is to identify the most impactful interventions in mitigating the spread of COVID-19, and identify parallels so that we can model the importance of certain climate interventions in "flattening the curve" of climate change.
What it does
Our program analyzes data from key countries impacted by COVID-19, and models how interventions are taken to mitigate its spread have reduced the growth of the number of cases. We connect this modeling to climate change data, understanding how key investments into climate change have resulted in decreased emissions in a given country.
How I built it
We built a proof-of-concept of our model using Excel and Tableau. Early modeling that we have completed is a simple static model paralleling COVID-19 case growth and climate change intensity growth (measured in ppm CO2). We also used Google Colab for collaboration on the proof-of-concept.
Challenges I ran into
The biggest hurdle in our development was finding the right data to appropriate to the scope of our project. After scouring the web for data sources, we kept the data for our proof-of-concept that we are submitting for the hackathon very simple. However, we are optimistic about how we can expand this project to be applicable to decision-makers that hold the fate of the environment in their hands.
Accomplishments that I'm proud of
We live in an age where data is plentiful, and sorting through that data to find something meaningful is much harder. Because of this challenge, our team learned a lot about how to sort through data to find something meaningful and applicable, and draw parallels between two seemingly different but surprisingly similar global challenges (the COVID-19 pandemic and climate change).
What I learned
We learned about appropriate considerations and approaches in understanding a dataset, and how to frame data in a way given analytical tools and providing context that turns data from numbers to meaningful applications.
What's next for COVID-Climate
This was a very simple version of the end goal we had for this project. First and foremost, we had to limit our study of government interventions for this model. Right now we only compare social interventions to energy expenditures in our model relating COVID to climate change. We would like to build this out to understand how various fiscal and social interventions by the government can incentivize the behavior of private citizens and large corporations alike to take the steps needed to mitigate the spread of COVID and relate that to potential approaches and timings of such approaches in mitigating the intensity of climate change. We know that there are points of no return with the COVID pandemic and climate change, and we want to be able to communicate how being timely in interventions can save lives and the world. We aim to use machine learning on a more expansive data set (which is still being developed) to turn our model into a more dynamic solution that can be used by policymakers, business leaders, and other decision-makers that can take our learnings from COVID-19 to save the world.