From understanding consumer behavior to developing a comprehensive business model, the weather is a variable with significant economic impact.
With a database of more than 750 million forecasts collected over 12 years, ForecastHistory has supplied historical weather data to many weather-sensitive industries, including agriculture, energy, utilities, insurance, transportation and a Major League Baseball team.
We help businesses:
- Know the accuracy of their weather forecast provider
- Make better decisions about weather risks
- Increase confidence in your business decisions
- Improve profitability and overall business performance
A ForecastWatch Case Study
Background:
National Grid, a New England investor-owned utility company, wanted to create a model to predict storm damage and allow for better placement of electrical line crews before, during and after a storm. This efficiency in deploying crews could lead to cost savings.
“Our goal was to create a machine-learning predictive algorithm that could predict damage to our network based on weather forecasts,” said John Williams, network strategy engineer. “Weather data was helpful for our model, but it wasn’t sufficient for our purposes because weather typically deviates a great deal from forecasts. We therefore acquired historical weather forecast data that was comprehensive.”
Approach:
ForecastWatch supplied the weather forecast data crucial to National Grid’s analysis. ForecastHistory provided comprehensive historical weather data to build the database that helped National Grid construct its predictive damage model.
This data contained approximately 5.2 million hourly logs over the course of severe weather events between 2008 and 2012 from 234 stations across Massachusetts.
“The amount and comprehensiveness of ForecastWatch data was a key piece in understanding how the actual weather data related to the information we had before the storms hit,” John said. “And it wasn’t just the amount of data we obtained from ForecastWatch that was valuable, but it was how we could pick and choose and customize by geography. We were provided just the right amount of information without having to sort out through a huge amount of data.”
Results:
Partnering with ForecastWatch and using ForecastHistory’s historical database of weather forecasts, National Grid was able to customize the data it needed to develop a useful predictive model. The process of working with Forecast also helped National Grid recognize that other predictors would provide value in forecasts.
“We discovered that many key predictors of damage, such as pressure, wind gusts and precipitation rates were not part of standard forecasts,” John said. “Using the information we generated, we have challenged weather providers to include those three features in their future forecasts.”