Add to Favourites
To login click here
A team of scientists have applied a deep learning algorithm to analog weather forecasting, which uses past weather conditions to make future forecasts. They found that analyzing surface wind speed and solar irradiance forecasts in Pennsylvania from 2017 to 2019 using machine learning improved analog forecasting accuracy. Analog forecasting is an alternative to numerical weather prediction (NWP), which uses computer models to simulate how initial weather conditions will evolve in the days or weeks ahead. NWP has led to great advances in forecasting, but uncertainties remain which can be addressed by running a number of simulations, called ensembles, which show a range of possible future atmospheric states.
