Google DeepMind 推出新方法：利用 AI 尋找流體力學百年難題的新解答
Original: Discovering new solutions to century-old problems in fluid dynamics
Google DeepMind has published a new approach aimed at helping mathematicians, physicists, and engineers use artificial intelligence to…
Google DeepMind 發表最新研究，展示如何利用 AI 技術尋找流體力學中的新解。該方法針對描述流體運動的百年難題（如 Navier-Stokes 方程與湍流現象），透過結合深度學習與物理模擬，成功加速尋找「確切相干態（ECS）」等關鍵結構。這項突破將有助於數學、物理與工程學界攻克長期未解的複雜流體控制與預測挑戰。
Google DeepMind has published a new approach aimed at helping mathematicians, physicists, and engineers use artificial intelligence to tackle century-old unsolved problems in fluid dynamics. The heart of fluid dynamics lies in understanding the motion of liquids and gases, most famously described by the Navier-Stokes equations. However, when fluids enter a state of turbulence, their highly chaotic and nonlinear nature makes precise solutions extraordinarily difficult to obtain — one of the most famous unsolved problems in physics and mathematics.
Free shows the 3-line summary; Pro unlocks the full deep summary (~300 words) so you never have to click through.
See Pro plans →Want the original English / full article?
Read on Google DeepMind Blog →Summaries are AI-generated; the original article is authoritative.