Engineers at the University of California, Santa Cruz, developed a new method for time series forecasting, powered by deep learning, that can improve its predictions based on data from the near future.  When they applied this approach to the critical task of seizure prediction using brain wave data, they found that their strategy offers up to 44.8% improved performance for predicting seizures compared to baseline methods.

University of Michigan and Carnegie Mellon University researchers have developed a new tool that makes greener chemistry more accessible. 

A team of researchers at the University of Miami has developed a global atmospheric modeling framework that blends powerful research capabilities with accessibility for students and scientists alike. Written entirely in Python, a high-level, general-purpose programming language, and designed to run on an interactive Jupyter Notebook, the new tool removes longstanding technical barriers, allowing anyone with a standard laptop to explore cutting-edge climate experiments.

In a study of 5- to 11-year-olds in the United States and China, the authors found that children’s belief that their family and friends would support their pursuit of political leadership as adults predicted their expressed motivation to become political leaders—specifically, “president” for children in the US and “chairman” for children in China. In both countries, this relationship was particularly strong for girls compared to boys.

n a new longitudinal study, researchers examined EU and U.S. news and media websites to determine how online content providers adapted their responses to the GDPR over time, and whether restrictions on online tracking affected outcomes such as the quantity of content and visitors’ engagement. The study found that while EU websites made changes and adapted, they continued to produce quality content and engage audiences at levels comparable to their U.S. counterparts.