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

TL;DR

This paper presents a simple neural network approach to quickly simulate physical property measurements from preliminary data, aiding experimental planning and data reuse in materials research.

Contribution

It introduces a fast, easy-to-train neural network method for simulating physical measurements, enabling real-time data augmentation and experimental condition optimization.

Findings

Neural networks can accurately simulate physical measurements within learned ranges.

The approach enables on-the-fly learning and simulation using open-source tools.

It facilitates reuse of published data for accelerated materials exploration.

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.