← Back to all projects
Rain, Rain, Go Away: Predicting the Chance of Rain using Global Surface Summary of the Day

Rain, Rain, Go Away: Predicting the Chance of Rain using Global Surface Summary of the Day

Dennis Dominic Diego, Jason Dolorso

Asian Institute of Management

Executive Summary

Rain or drizzle is usually associated with abnormal weather that greatly impacts ecosystems, businesses, and daily life. In the United Kingdom, rainfall is one of the prevalent causes of profit warnings, especially in industries like utilities, retail, construction, and agriculture. Considering how much rain affects the country, we wanted to understand how we can predict if it will rain in the UK based on the previous day’s weather and climate information.

Using data from the Global Surface Summary of the Day, retrieved from the Amazon Open Data Registry, we used data collected from 355 weather stations across the UK from 2000-2015 to predict whether it will rain the next day based on the current day’s temperature, sea level pressure, dew point, and whether it rained — resulting in an accuracy of 79.73% and an AUROC of 84.02%. The results of this study can be valuable to businesses, travellers, and UK citizens looking to adjust their plans, and the same methodology can be applied to other locations using only a handful of weather features from the previous day.

Full text article and source codes can be provided upon request.