1 of 15

GLOBAL WARMING PREDICTION SIMULATION

Eshanvi Kalluri and Aarush Sundararajan

2 of 15

TABLE OF CONTENTS

01

04

02

05

03

THE THEME

THE DATA

THE CODE

THE INTERFACE

THE FINDINGS

3 of 15

THE THEME

01

4 of 15

SUSTAINABILITY & SOCIETAL WELFARE

Predictions of temperature changes by country, based on current global warming trends, show how climate change could harm society and the environment if action isn’t taken. Many countries, especially those with fewer resources, are expected to face serious problems like food shortages, water scarcity, and increased health risks. These challenges make it clear that we need to shift toward more sustainable ways of living, such as using renewable energy, cutting down waste, and consuming more responsibly. Investing in sustainability isn’t just about protecting the planet—it’s about creating a fairer, healthier, and more secure future for everyone.

5 of 15

THE DATA

02

6 of 15

THE PROS

THE CONS

This dataset was highly valuable because it provided detailed, country-specific temperature change measurements with impressive precision. Spanning back to the 1700s, it offered a long-term perspective on climate trends and variability. Its clear and well-organized format made it easy to understand and analyze, combining historical depth, accuracy, and usability to serve as an excellent resource for studying global temperature patterns and their implications.

However, the dataset was not without its flaws. Several rows lacked measurements, which introduced gaps in the data, and the date formatting was inconsistent, requiring conversion into a usable integer format. Additionally, continental data was interspersed with country-specific data, which created confusion and added another layer of complexity. To address these issues, we had to implement a series of advanced data-cleaning functions to fill gaps and standardize date formats.

7 of 15

roc(fy-by)+it+5

THE FORMULA

roc = rate of change

fy = future year; by = base year

it = initial temp; the five accounts for the seasonal variability

IT IS LINEAR BECAUSE THE RATE OF CHANGE FOR THE EXPONENTIAL REGRESSION IS HARD TO FIND, AND CLOSE TO THE LINEAR REGRESSION.

8 of 15

THE CODE

03

9 of 15

THE DATA CORRECTION MECHANISM

10 of 15

OUR ALGORITHM

11 of 15

THE INTERFACE

04

12 of 15

HOW TO USE IT

  • When prompted, type in a country and hit enter

  • Then, type in a FUTURE year of your choice

  • Key Tip: do not enter any spaces after your responses

  • A prediction for the future temperature in that year, will be displayed

(note this temperature applies if the rate of climate change continues)

No actual interface exists as we ran out of time to design a UI :(

13 of 15

THE FINDINGS

05

14 of 15

SO?

This tool can be used for:

  • Predicting which countries will bear the brunt of climate change

  • Comparing year to year differences in temperature

  • Calculating climate change goals using the scalar tool

  • Educating students about their impact on the planet

15 of 15

THANK YOU!