Online Program Home
My Program

Abstract Details

Activity Number: 121 - SPEED: Data Expo
Type: Contributed
Date/Time: Monday, July 30, 2018 : 8:30 AM to 10:20 AM
Sponsor: Section on Statistical Computing
Abstract #329608
Title: Modeling and Mapping Weather Forecast Accuracy
Author(s): Queen Ikhelowa* and Darren Keeley
Companies: and CSUEB
Keywords: Weather Forecasting; Dynamic Visualisation; Forecasting Accuracy; Interpolation
Abstract:

The purpose of our presentation is to investigate the accuracy of weather forecasts. Particularly, maximum and minimum temperatures and rainfall are considered. We examine the distribution of the errors of these forecasts and how the errors change with the closeness of the forecasts. A regression model is also used to examine other effects on forecast accuracy, such as levels of temperature and rainfall and the previous day's weather. We use an interactive map to visualize our findings, displaying the errors in temperature and precipitation forecasting by month. Interpolation is used to improve the map's ability to generalize to other cities not included in the data. Our project was mostly coded with R, utilizing packages like Shiny, Plotly and Ggplot.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2018 program