Neural networks for a quick access to a digital twin of scanning physical properties measurements

Abstract

For performing successful measurements within limited experimental time, efficient use of preliminary data plays a crucial role. This work shows that a simple feedforward type neural networks approach for learning preliminary experimental data can provide quick access to simulate the experiment within the learned range. The approach is especially beneficial for physical properties measurements with scanning on multiple axes, where derivative or integration of data are required to obtain the objective quantity. Due to its simplicity, the learning process is fast enough for the users to perform learning and simulation on-the-fly by using a combination of open-source optimization techniques and deep-learning libraries. Here such a tool for augmenting the experimental data is proposed, aiming to help researchers to decide the most suitable experimental conditions before performing costly experiments in real. Furthermore, this tool can also be used from the perspective of taking advantage of reutilizing and repurposing previously published data, accelerating data-driven exploration of functional materials.

19 pages, 5 figures + 7 pages of Supporting Information

References in corpus (4)

• Machine Learning Guided Discovery of Gigantic Magnetocaloric Effect in HoB${}_2$ Near Hydrogen Liquefaction Temperature
• Deep learning-based statistical noise reduction for multidimensional spectral data
• Optimizing accuracy and efficacy in data-driven materials discovery for the solar production of hydrogen
• Super Resolution Convolutional Neural Network for Feature Extraction in Spectroscopic Data