- Germain, Sarah [Browse]
- Senior thesis
- 62 pages
- Vanderbei, Robert [Browse]
- Princeton University. Department of Operations Research and Financial Engineering [Browse]
- Class year
- Restrictions note
- Walk-in Access. This thesis can only be viewed on computer terminals at the Mudd Manuscript Library.
- Summary note
- In this paper, we examine temperature trends in data from the last century, taken
from the National Oceanic and Atmospheric Administration (NOAA) Global Surface
Summary of the Day. Expanding upon the model presented in "Local Warming"
by Vanderbei, we run least absolute deviation and least squares regressions after
applying techniques from major modern surface temperature analyses by NOAA and
Berkeley Earth. To explore the effect of gaps in the datasets, we implement the scalpel
technique from Berkeley Earth and find that, with our model, piecewise regression
is skewed by shorter datasets that are heavily affected by the modeling of the solar
cycle. We also extend our model to consider semiannual seasonality that has dominant
effects on temperature
fluctuations at lower latitudes, with the aim of increasing the
accuracy of our model in the tropics. Finally, we create a framework for displaying
our results via a website that allows people to access information about temperature
trends in their area, with the goal of changing people's perceptions of global warming
on a local basis by providing simple data that is very personally relevant.