arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2210.11343cond-mat.mtrl-scicond-mat.dis-nnphysics.comp-ph
收藏

用机器学习预测任意长度尺度的电子结构

Predicting electronic structures at any length scale with machine learning

Lenz Fiedler, Normand A. Modine, Steve Schmerler, Dayton J. Vogel, Gabriel A. Popoola, Aidan P. Thompson, Sivasankaran Rajamanickam, Attila Cangi

AI总结:

针对密度泛函理论(DFT)计算扩展性受限的问题,提出了一个预测任意长度尺度电子结构的机器学习框架,实现最高三个数量级加速并突破DFT计算尺度极限,为多领域应用提供前所未有的建模能力。

摘要:

物质中电子的性质具有根本性的重要性。它们几乎引发了所有的分子和材料性质,并决定了从半导体器件到巨型气态行星内部等各种物体中发生的物理现象。对如此多样化应用进行建模和模拟主要依赖于密度泛函理论(DFT),该方法已成为预测物质电子结构的主要方法。尽管 DFT 计算已被证明非常有用,甚至于 1998 年获得了诺贝尔奖,但其计算扩展性将其限制在小型系统中。我们开发了一个用于预测任意长度尺度电子结构的机器学习框架。它在 DFT 可处理的系统上展现出高达三个数量级的加速,更重要的是,它能够在 DFT 计算不可行的尺度上进行预测。我们的工作展示了机器学习如何克服长期存在的计算瓶颈,并将科学推进到任何现有解决方案都无法处理的前沿。这种前所未有的建模能力在天体物理学、新材料发现以及可持续未来的能源解决方案中开辟了取之不尽的应用范围。

英文摘要:

The properties of electrons in matter are of fundamental importance. They give rise to virtually all molecular and material properties and determine the physics at play in objects ranging from semiconductor devices to the interior of giant gas planets. Modeling and simulation of such diverse applications rely primarily on density functional theory (DFT), which has become the principal method for predicting the electronic structure of matter. While DFT calculations have proven to be very useful to the point of being recognized with a Nobel prize in 1998, their computational scaling limits them to small systems. We have developed a machine learning framework for predicting the electronic structure on any length scale. It shows up to three orders of magnitude speedup on systems where DFT is tractable and, more importantly, enables predictions on scales where DFT calculations are infeasible. Our work demonstrates how machine learning circumvents a long-standing computational bottleneck and advances science to frontiers intractable with any current solutions. This unprecedented modeling capability opens up an inexhaustible range of applications in astrophysics, novel materials discovery, and energy solutions for a sustainable future.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑