Deep Learning for Flow Sculpting: Insights into Efficient Learning using Scientific Simulation Data.
Deep Learning for Flow Sculpting: Insights into Efficient Learning using Scientific Simulation Data.
复制标题
DOI：
10.1038/srep46368
复制
发表时间：
2017-04-12
影响因子：
4.6
通讯作者：
Ganapathysubramanian B
中科院分区：
文献类型：
--
作者：
Stoecklein D;Lore KG;Davies M;Sarkar S;Ganapathysubramanian B
一种用于塑造微流体流动的新技术，称为流动造型，提供了前所未有的被动流体流动控制水平，在推进微尺度的制造、生物学和化学研究方面具有潜在的突破性应用。然而，有效解决设计用于所需流体流动形状的流动整形装置的逆问题仍然是一个挑战。当前的方法与多对一的设计空间作斗争，需要大量的用户交互和建立直觉的必要性，所有这些都是时间和资源密集型的。深度学习已成为高维空间的一种有效函数逼近技术，并为逆问题提供了快速解决方案，但其在类似定义问题中的实现科学在很大程度上仍未得到探索。我们认为深度学习方法可以完全超越当前的科学反问题方法，同时提供可比的设计。为此，我们展示了设计空间输入的智能采样如何使深度学习方法在准确性方面更具竞争力，同时说明其对样本外预测的泛化能力。
A new technique for shaping microfluid flow, known as flow sculpting, offers an unprecedented level of passive fluid flow control, with potential breakthrough applications in advancing manufacturing, biology, and chemistry research at the microscale. However, efficiently solving the inverse problem of designing a flow sculpting device for a desired fluid flow shape remains a challenge. Current approaches struggle with the many-to-one design space, requiring substantial user interaction and the necessity of building intuition, all of which are time and resource intensive. Deep learning has emerged as an efficient function approximation technique for high-dimensional spaces, and presents a fast solution to the inverse problem, yet the science of its implementation in similarly defined problems remains largely unexplored. We propose that deep learning methods can completely outpace current approaches for scientific inverse problems while delivering comparable designs. To this end, we show how intelligent sampling of the design space inputs can make deep learning methods more competitive in accuracy, while illustrating their generalization capability to out-of-sample predictions.