Samuel Andrello, Daniel Alabi, Simon J. L. Billinge
While machine learning has enabled the rapid prediction of inorganic materials with novel properties, the challenge of determining how to synthesize these materials remains largely unsolved. Previous work has largely focused on predicting precursors or reaction conditions, but only rarely on full synthesis pathways. We introduce the ActionGraph, a directed acyclic graph framework that encodes both the chemical and procedural structure, in terms of synthesis operations, of inorganic synthesis reactions. Using 13,017 text-mined solid-state synthesis reactions from the Materials Project, we show that incorporating PCA-reduced ActionGraph adjacency matrices into a $k$-nearest neighbors retrieval model significantly improves synthesis pathway prediction. While the ActionGraph framework only results in a 1.34% and 2.76% increase in precursor and operation F1 scores (average over varying numbers of PCA components) respectively, the operation length matching accuracy rises 3.4 times (from 15.8% to 53.3%). We observe an interesting trade-off where precursor prediction performance peaks at 10-11 PCA components while operation prediction continues improving up to 30 components. This suggests composition information dominates precursor selection while structural information is critical for operation sequencing. Overall, the ActionGraph framework demonstrates strong potential, and with further adoption, its full range of benefits can be effectively realized.
Tanaporn Na Narong, Zoe N. Zachko, Steven B. Torrisi et al.
We used interpretable machine learning to combine information from multiple heterogeneous spectra: X-ray absorption near-edge spectra (XANES) and atomic pair distribution functions (PDFs) to extract local structural and chemical environments of transition metal cations in oxides. Random forest models were trained on simulated XANES, PDF, and both combined to extract oxidation state, coordination number, and mean nearest-neighbor bond length. XANES-only models generally outperformed PDF-only models, even for structural tasks, although using the metal's differential PDFs (dPDFs) instead of total PDFs narrowed this gap. When combined with PDFs, information from XANES often dominates the prediction. Our results demonstrate that XANES contain rich structural information and highlight the utility of species-specificity. This interpretable, multimodal approach is quick to implement with suitable databases and offers valuable insights into the relative strengths of different modalities, guiding researchers in experiment design and identifying when combining complementary techniques adds meaningful information to a scientific investigation.
A major challenge in materials science is the determination of the structure of nanometer sized objects. Here we present a novel approach that uses a generative machine learning model based on diffusion processes that is trained on 45,229 known structures. The model factors both the measured diffraction pattern as well as relevant statistical priors on the unit cell of atomic cluster structures. Conditioned only on the chemical formula and the information-scarce finite-size broadened powder diffraction pattern, we find that our model, PXRDnet, can successfully solve simulated nanocrystals as small as 10 angstroms across 200 materials of varying symmetry and complexity, including structures from all seven crystal systems. We show that our model can successfully and verifiably determine structural candidates four out of five times, with average error among these candidates being only 7% (as measured by post-Rietveld refinement R-factor). Furthermore, PXRDnet is capable of solving structures from noisy diffraction patterns gathered in real-world experiments. We suggest that data driven approaches, bootstrapped from theoretical simulation, will ultimately provide a path towards determining the structure of previously unsolved nano-materials.
The revolution in materials in the past century was built on a knowledge of the atomic arrangements and the structure-property relationship. The sine qua non for obtaining quantitative structural information is single crystal crystallography. However, increasingly we need to solve structures in cases where the information content in our input signal is significantly degraded, for example, due to orientational averaging of grains, finite size effects due to nanostructure, and mixed signals due to sample heterogeneity. Understanding the structure property relationships in such situations is, if anything, more important and insightful, yet we do not have robust approaches for accomplishing it. In principle, machine learning (ML) and deep learning (DL) are promising approaches since they augment information in the degraded input signal with prior knowledge learned from large databases of already known structures. Here we present a novel ML approach, a variational query-based multi-branch deep neural network that has the promise to be a robust but general tool to address this problem end-to-end. We demonstrate the approach on computed powder x-ray diffraction (PXRD), along with partial chemical composition information, as input. We choose as a structural representation a modified electron density we call the Cartesian mapped electron density (CMED), that straightforwardly allows our ML model to learn material structures across different chemistries, symmetries and crystal systems. When evaluated on theoretically simulated data for the cubic and trigonal crystal systems, the system achieves up to $93.4\%$ average similarity with the ground truth on unseen materials, both with known and partially-known chemical composition information, showing great promise for successful structure solution even from degraded and incomplete input data.
Chia-Hao Liu, Christopher J. Wright, Ran Gu et al.
We validate the use of matrix factorization for the automatic identification of relevant components from atomic pair distribution function (PDF) data. We also present a newly developed software infrastructure for analyzing the PDF data arriving in streaming manner. We then apply two matrix factorization techniques, Principal Component Analysis (PCA) and Non-negative Matrix Factorization (NMF), to study simulated and experiment datasets in the context of in situ experiment.
Xiaohao Yang, Pavol Juhas, Christopher L. Farrow et al.
The xPDFsuite software program is described. It is for processing and analyzing atomic pair distribution functions (PDF) from X-ray powder diffraction data. It provides a convenient GUI for SrXplanr and PDFgetX3, allowing the users to easily obtain 1D diffraction pattern from raw 2D diffraction images and then transform them to PDFs. It also bundles PDFgui which allows the users to create structure models and fit to the experiment data. It is specially useful for working with large numbers of datasets such as from high throughout measurements. Some of the key features are: real time PDF transformation and plotting; 2D waterfall, false color heatmap, and 3D contour plotting for multiple datasets; static and dynamic mask editing; geometric calibration of powder diffraction image; configurations and project saving and loading; Pearson correlation analysis on selected datasets; written in Python and support multiple platforms.