当前位置: X-MOL 学术Phys. Rev. E › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Detecting depinning and nonequilibrium transitions with unsupervised machine learning.
Physical Review E ( IF 2.4 ) Pub Date : 2020-04-01 , DOI: 10.1103/physreve.101.042101
D McDermott 1, 2 , C J O Reichhardt 1 , C Reichhardt 1
Affiliation  

Using numerical simulations of a model disk system, we demonstrate that a machine learning generated order-parameter-like measure can detect depinning transitions and different dynamic flow phases in systems driven far from equilibrium. We specifically consider monodisperse passive disks with short range interactions undergoing a depinning phase transition when driven over quenched disorder. The machine learning derived order-parameter-like measure identifies the depinning transition as well as different dynamical regimes, such as the transition from a flowing liquid to a phase separated liquid-solid state that is not readily distinguished with traditional measures such as velocity-force curves or Voronoi tessellation. The order-parameter-like measure also shows markedly distinct behavior in the limit of high density where jamming effects occur. Our results should be general to the broad class of particle-based systems that exhibit depinning transitions and nonequilibrium phase transitions.

中文翻译:

通过无监督的机器学习检测固定和非平衡过渡。

使用模型磁盘系统的数值模拟,我们证明了机器学习生成的类似于阶参数的度量可以检测远离平衡驱动的系统中的固定变形和不同的动态流相。我们专门考虑具有短程相互作用的单分散无源盘,当其被淬灭失调驱动时会经历脱钉相变。机器学习派生的类似阶参数的量度可识别脱销转变以及不同的动力学状态,例如从流动液体到相分离的液固状态的转变,而这种转变无法通过传统手段(例如速度力)轻松区分曲线或Voronoi细分。在出现干扰效应的高密度范围内,类似阶数参数的度量也显示出明显不同的行为。
更新日期:2020-04-03
down
wechat
bug