Why it is Unfortunate that Linear Machine Learning “Works” so well in Electromechanical Switching of Ferroelectric Thin Films

Abstract

Machine learning (ML) is relied on for materials spectroscopy. It is challenging to make ML models fail because statistical correlations can mimic the physics without causality. Here, using a benchmark band‐excitation piezoresponse force microscopy polarization spectroscopy (BEPS) dataset the pitfalls of the so‐called “better”, “faster”, and “less‐biased” ML of electromechanical switching are demonstrated and overcome. Using a toy and real experimental dataset, it is demonstrated how linear nontemporal ML methods result in physically reasonable embedding (eigenvalues) while producing nonsensical eigenvectors and generated spectra, promoting misleading interpretations. A new method of unsupervised multimodal hyperspectral analysis of BEPS is demonstrated using long‐short‐term memory (LSTM) β‐variational autoencoders (β‐VAEs) . By including LSTM neurons, the ordinal nature of ferroelectric switching is considered. To improve the interpretability of the latent space, a variational Kullback–Leibler‐divergency regularization is imposed . Finally, regularization scheduling of β as a disentanglement metric is leveraged to reduce user bias. Combining these experiment‐inspired modifications enables the automated detection of ferroelectric switching mechanisms, including a complex two‐step, three‐state one. Ultimately, this work provides a robust ML method for the rapid discovery of electromechanical switching mechanisms in ferroelectrics and is applicable to other multimodal hyperspectral materials spectroscopies.

Merits and Demerits of Machine Learning of Ferroelectric, Flexoelectric, and Electrolytic Properties of Ceramic Materials

“…ML is essentially a fitting procedure of many experimental data as a function of many factors called descriptors [ 2 , 4 ]. It has been argued that a lack of interpretability in ML could be a severe problem in terms of the reliability of the predicted values as well as development in scientific research based on causality [ 2 , 4 , 5 , 6 , 7 , 8 ]. On the other hand, the excellent fitting procedure of experimental data by means of ML could result in more accurate predicted values compared to first principles calculations, which could have some intrinsic systematic error [ 9 ].…”