Neural downscaling for complex systems: from large-scale to small-scale by neural operator

IF 5.9 1区工程技术 Q1 ENGINEERING, MECHANICAL

Engineering Applications of Computational Fluid Mechanics Pub Date : 2024-09-19 DOI:10.1080/19942060.2024.2399672

Pengyu Lai, Jing Wang, Rui Wang, Dewu Yang, Haoqi Fei, Yihe Chen, Hui Xu

引用次数: 0

Abstract

Researchers have long been working on interpreting and predicting the dynamics of complex systems in various fields. Conventional methods including full-scale simulations and reduced-order models a...

查看原文本刊更多论文

复杂系统的神经降尺度：通过神经算子从大尺度到小尺度

长期以来，研究人员一直致力于解释和预测各领域复杂系统的动态。包括全尺度模拟和降阶模型在内的传统方法都无法对复杂系统的动力学进行解释和预测。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Engineering Applications of Computational Fluid Mechanics ENGINEERING, MULTIDISCIPLINARY-ENGINEERING, MECHANICAL

CiteScore

10.60

自引率

14.80%

发文量

109

审稿时长

3.4 months

期刊介绍： The aim of Engineering Applications of Computational Fluid Mechanics is a continuous and timely dissemination of innovative, practical and industrial applications of computational techniques to solve the whole range of hitherto intractable fluid mechanics problems. The journal is a truly interdisciplinary forum and publishes original contributions on the latest advances in numerical methods in fluid mechanics and their applications to various engineering fields including aeronautic, civil, environmental, hydraulic and mechanical. The journal has a distinctive and balanced international contribution, with emphasis on papers addressing practical problem-solving by means of robust numerical techniques to generate precise flow prediction and optimum design, and those fostering the thorough understanding of the physics of fluid motion. It is an open access journal.