Scientists Use Machine Learning To Peer Into the Future

The researchers utilize an advanced machine learning method known as next generation reservoir computing. While the past may be a fixed and unchangeable point, machine learning can sometimes make predicting the future easier. Researchers at The Ohio State University have recently discovered a new way to predict the behavior of spatiotemporal chaotic systems, such as changes in Earth's weather, that are particularly difficult for scientists to forecast using a new type of machine learning technique called next generation reservoir computing. The research, which was recently published in the journal Chaos: An Interdisciplinary Journal of Nonlinear Science, makes use of a brand-new, highly efficient algorithm that, when combined with next-generation reservoir computing, can learn spatiotemporal chaotic systems in a fraction of the time required by traditional machine learning algorithms. Researchers put their method to the test by predicting the behavior of an atmospheric weather model, a challenging problem that has been researched extensively in the past.