A time-aware evaluation framework reveals that simple persistence forecasts outperform complex machine learning models while demonstrating that predictive accuracy and explanation quality diverge ...

A machine-learning correction layer built by a team led from MIT has roughly doubled the accuracy of the European Centre for Medium-Range Weather Forecasts model for forecasts two to six weeks ahead, ...

Successful test results of a new machine learning (ML) technique developed at Georgia Tech could help communities prepare for extreme weather and coastal flooding. The approach could also be applied ...

A recent study, “Picking Winners in Factorland: A Machine Learning Approach to Predicting Factor Returns,” set out to answer a critical question: Can machine learning techniques improve the prediction ...

Australian scientists have identified conditions that could predict El Niño and La Niña events up to 12 months in advance.

A team of researchers at the Universities of Lincoln, Sheffield, and Reading have developed a new method to improve the prediction of seasonal weather conditions in the U.K. and Northwest Europe. The ...

Researchers in China have applied a machine learning technology based on temporal convolutional networks in PV power forecasting for the first time. The new model reportedly outperforms similar models ...