Amazon today launched the Forecast Weather Index, an Amazon Web Services (AWS) product the company says can increase the forecasting accuracy of certain AI models by incorporating local weather information. Starting today, AWS customers can add 14-day weather forecasts for U.S. and several Europe locations to their demand predictions.
As Amazon notes, weather conditions can influence consumer demand patterns, product merchandizing decisions, staffing requirements, and energy consumption needs among other factors. For example, retailers, knowing that a heat wave is around the corner, may choose to overstock air conditioners from distribution centers at specific locations. As for restaurants, weather forecasts help better balance staff dependent on dine-in versus take-out orders. And businesses with warehouses can predict the number of workers that might come in because of disrupted transportation.
Amazon’s Forecast Weather Index — which leverages AWS’ Forecast service — combines multiple weather metrics from historical weather events and current forecasts at a given location to increase demand forecast accuracy. Forecast Weather Index is currently optimized for in-store retail demand planning and local on-demand services, but may still add value to scenarios where weather impacts demand such as power and utilities, Amazon says.
“Acquiring, cleaning, and effectively using live weather information for demand forecasting [has historically been] challenging and required ongoing maintenance,” Amazon senior product manager Namita Das wrote in a blog post. “With the Amazon Forecast Weather Index, you can now automatically include local weather information to your demand forecasts with one click and at no extra cost.”
Amazon isn’t the only tech giant investing in AI for local weather forecasting. Earlier this year, Google announced it would partner with the U.S. National Oceanic and Atmospheric Administration (NOAA) to study and develop machine learning systems that might be infused across NOAA’s enterprise. Microsoft has also funded efforts to identify repeating weather and climate patterns from historical data as a way to improve subseasonal and seasonal forecast models.
