Russian internet company Yandex has announced the launch of a new program for machine-learning weather forecast.
According to a press release, the new machine-based technology will be used for “hyper-local and super-accurate weather forecasting”.
The technology is called Meteum and works by collecting huge volumes of data about past forecasts, and then compares them with weather conditions of the past, to figure out the difference between what was forecasted and what really happened.
The data will be collected from external providers such as WRF or Foreca. It then compiles a mathematical formula to correct and refine future forecasts.
Weather web service and mobile app will be available for both iOS and Android. Meteum calculates a new forecast each time a user consults Yandex.Weather.
It locates a person and shows them a fresh forecast for precisely that spot. The user can choose another place and time for the forecast to see what the weather will be like around their office in an hour or whether it might rain when they go out of town in the evening.
“Using machine learning allows collating a large volume of historical data about forecasts and actual weather, identifying causality in forecasting errors and correcting them,” Yandex said in a blog post describing the technology. “This is quicker and easier, as it doesn’t require factoring in laws of nature for each new forecast, but simply corrects traditional mathematical models and localises the forecast down to specific latitude and longitude. That’s exactly what Meteum does.”