Machine learning–enabled identification of material phase transitions based on experimental data: Exploring collective dynamics in ferroelectric relaxors

Abstract

Machine learning of dynamic responses allows determination of structural phase transitions in relaxor ferroelectrics.

Smart machine learning or discovering meaningful physical and chemical contributions through dimensional stacking

“…In the past, such datasets have been analyzed with conventional DR by slicing the data into voltage datasets for each composition, D pv ;pc ðt; zÞ, and analyzing the two-dimensional slices independently. [42][43][44][45] Conversely, applying DR with dimensional stacking concatenates the D pv ;pc ðt; zÞ slices along appropriate axes prior to DR analysis, based on physical and chemical understanding of the material. Here, we compare the resulting phenomenological insights obtained through traditional statistical analysis, the conventional DR approach, and DR with dimensional stacking.…”

“…Specifically, dimensional reduction (DR) and machine-learning (ML) techniques have been hailed as a groundbreaking paradigm in materials science, 37 and used to identify superimposed physical and chemical contributors to functional behavior within multidimensional datasets in fields as diverse as multiferroics, 38,39 superconductors, 40 oxide interfaces, 41 and electromechanically active materials. [42][43][44][45] However, while these techniques hold significant promise to revolutionize our understanding of the fundamental material science and guide future design of materials, they are inherently limited by a lack of means to impose physical or chemical constraints to the analysis. 46 In particular, conventional DR analysis on high dimensional datasets is often performed through creation of two-dimensional data slices, where only one single parameter is changed within the slice.…”

ML4Chem: A Machine Learning Package for Chemistry and Materials Science

“…These localized contributions usually account for interactions of an atom and its nearest-neighbor atoms (many-body interactions). Atomistic models are very useful and have been successfully applied for the acceleration of molecular dynamics simulations [17][18][19], identification of phase transitions in materials [20], determination of energy and atomic forces with high accuracy [21,22], the search of saddle-points[23] and the prediction of atomic charges [24,25].This publication is organized as follows: in section II, we will discuss the design and architecture of ML4Chem's atomistic module. Each of its core blocks is introduced in Section III and we will demonstrate the code's capabilities through a series of demonstration examples in Section IV.…”

“…ml4c " , params = " krr / publication . params " )18 Set the reference space20 calc . re fe r en ce _s p ac e = " features .…”

An artificial intelligence atomic force microscope enabled by machine learning

“…Indeed, AI has been demonstrated to be very effective in analyzing data from both microscopy and spectroscopy studies. 6,[11][12][13][14] Nevertheless, many current AI applications in image analysis focus on post-processing of data, 12,[15][16][17] while in both materials sciences and medicines, especially under time-and environment-sensitive circumstance and at elusive points that are not easy to spot, it is often critical to respond to the data acquired on the fly, for example by acquiring additional data in the critical locations of material interfaces or tumors. It is also highly desirable to intervene in real time with manipulative or therapeutic treatments on the spot.…”