首页|Research from University of Lausanne Yields New Findings on Machine Learning (Climate-invariant machine learning)
Research from University of Lausanne Yields New Findings on Machine Learning (Climate-invariant machine learning)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
New research on artificial intelligence is the subject of a new report. According to news reporting out of Lausanne, Switzerland, by NewsRx editors, research stated, "Projecting climate change is a generalization problem: We extrapolate the recent past using physical models across past, present, and future climates." Our news correspondents obtained a quote from the research from University of Lausanne: "Current climate models require representations of processes that occur at scales smaller than model grid size, which have been the main source of model projection uncertainty. Recent machine learning (ML) algorithms hold promise to improve such process representations but tend to extrapolate poorly to climate regimes that they were not trained on." According to the news reporters, the research concluded: "To get the best of the physical and statistical worlds, we propose a framework, termed "climate-invariant" ML, incorporating knowledge of climate processes into ML algorithms, and show that it can maintain high offline accuracy across a wide range of climate conditions and configurations in three distinct atmospheric models. Our results suggest that explicitly incorporating physical knowledge into data-driven models of Earth system processes can improve their consistency, data efficiency, and generalizability across climate regimes."
University of LausanneLausanneSwitzerlandEuropeCyborgsEmerging TechnologiesMachine Learning
NETL
NSTL
