Crystal structure prediction (CSP) from powder diffraction data is a central challenge in materials chemistry. Machine learning (ML) models show promise, but most are trained on idealized simulated data, limiting reliability on real experiments. Here, we assess real-world behaviour using the previously published deCIFer model as an example of PXRD-conditioned generative CSP. deCIFer is an autoregressive transformer that conditions each step of structure generation on encoded PXRD data, guiding token-wise predictions of space group, lattice parameters, and atomic positions. Using controlled robustness tests, we quantify performance under realistic artefacts (noise, background, peak asymmetry, and Scherrer broadening) and introduce metrics for accuracy and predictive uncertainty. deCIFer adapts smoothly to signal distortions and improves over unconditioned baselines when diffraction features remain informative, while expressing appropriate uncertainty as the PXRD pattern becomes underdetermined. Experimental PXRD tests recover the known structures of Si and CeO2 and expose the expected limitations for lower-symmetry Fe2O3 and nanocrystalline CeO2. Overall, ML-based CSP is fundamentally limited by the information content of PXRD, but can accelerate expert workflows by rapidly generating chemically plausible candidates and quantifying uncertainty, making such models valuable human-in-the-loop tools for real-world structure determination.
The indexing of powder X-ray diffraction (PXRD) for ab initio determination of unknown crystal structures remains challenging for systems with low-symmetry (e.g., triclinic and monoclinic), large unit cell (V > 1000 ų), and nonideal data due to reliance on heuristic methods with limited robustness. Here, we propose AIdex-R2, a transformer-based end-to-end framework that performs joint inference of the extinction groups (EGs) and unit cell parameters from sequences of low-angle diffraction reflections. The model achieves ∼98.5% top-5 accuracy for EG identification and ∼1.44% mean absolute percentage error (MAPE) for cell parameter prediction (indexing), with an indexing success rate exceeding ∼90% under extremely realistic perturbations (e.g., zero-shift errors ±0.30°, uncertainty noise ±0.15°, reflection absence n = 4, and impurity reflections n = 2). Large-scale benchmarking shows superior performance over classical algorithms (TREOR, ITO, DICVOL) in both speed/efficiency and accuracy. Through interpretability studies of the internal decision-making mechanism, we confirm that the model adopts a discriminant logic dominated by the first diffraction peak (low 2θ) with dynamic weight allocation, providing a novel perspective and evidence for understanding the "black box" of PXRD indexing.
Ke Shu, Wei-Xin Yan, Huai-Hai Li et al.· Journal of Chemical Informat...· 0 citations
This work introduces ED-CSP, a machine learning framework that predicts crystal structures from chemical composition, atom count, and multiple detector-plane ED spot sets and establishes a benchmark for generative crystal structure prediction from sparse ED observations and provides a foundation for future transfer to experimental data.
Powder X-ray diffraction (PXRD) is the routine probe of crystalline matter, yet its analysis is the rate-limiting step as laboratories automate acquisition. Deep-learning analyzers excel on simulated patterns and degrade on measured ones. This simulation-to-real gap is structural, not additive: synthetic denoising gives no measurable lift on real spectra, whereas correcting a small peak-position drift more than doubles median retrieval correlation. Real-spectrum fine-tuning, peak-aligned reranking, and recalibration narrow what remains and restore the coverage synthetic anchors lose. Xtalyst integrates these in an agent-orchestrated system spanning phase identification, refinement, and calibrated property prediction. On a frozen held-out partition (n=534) each module measured on both splits reproduces its development finding -- including the synthetic-anchor under-coverage, whose magnitude differs between the two pools -- while held-out refinement converges and preserves symmetry without reaching profile-quality fits, and on a diffractometer its wet-dry recommend-rescan-reanalyze loop flips a blinded silicon standard to a gated PASS and changes which minor phase is resolved on a multi-metal alloy.
Shaoguang Wang, Weiyu Guo, Ben Fei et al.· 0 citations
We present a machine learning (ML) method to determine unit cell parameters from powder X-Ray diffraction (XRD) data using a novel invariant lattice representation. In ML, the data representation used can have a substantial impact on the prediction quality. Previous approaches have directly predicted lattice parameters ($a,b,c,\alpha,\beta,\gamma$) from XRD inputs. However, these parameters depend strongly on the unit cell reduction or convention used. In this work, we construct an invariant representation of the reciprocal lattice that is independent of primitive cell convention, based on the bispectrum--a descriptor built from spherical harmonic projections of lattice points. The calculation of the lattice bispectrum is differentiable, and we demonstrate how to invert it using a dynamic programming approach. We show that when fixing ML model architecture, using the lattice bispectrum as the ML target rather than the unit cell parameters leads to more accurate lattice parameter predictions. For example, using the MP-20 dataset, the bispectrum reduces length mean absolute percentage error (MAPE) from 11.18% to 2.44% and angle MAPE from 12.74% to 3.07% compared to direct prediction with the same model architecture. We additionally benchmark our approach against pre-existing XRD to crystal structure models such as Crystalyze and assess its performance on the experimental RRUFF dataset. Beyond unit cell representation, we anticipate this invariant lattice representation could serve more broadly as a geometry-aware target for other crystallographic machine learning tasks such as structure generation.
E. Hofgard, Kyucheol Min, Nofit Segal et al.· 1 citation
High-throughput experimentation and self-driving laboratories are drastically accelerating materials discovery, yet automated interpretation of X-ray powder diffraction (XRPD) data remains a critical rate-limiting step. Conventional search-match workflows rely heavily on expert manual intervention, while pure data-driven machine learning approaches suffer from limited generalizability across chemical systems and lack rigorous crystallographic interpretability. Here we present MatDiffract, a material-informed automated analysis platform for high-throughput XRPD characterization. Built on a first-principles density functional theory (DFT)-derived inorganic crystal structure database, Atomly, MatDiffract constructs a perturbation-augmented simulated diffraction database, embeds multi-scale diffraction features into indexable vectors, and integrates hierarchical vector retrieval with full-pattern fitting Rietveld refinement and quantitative phase fitting. Benchmarked on 875 single-phase experimental patterns, the platform achieves 91.3% Top-1 and 97.2% Top-10 identification accuracy after automated refinement. For binary and ternary multiphase mixtures, it delivers 85.0% and 70.0% Top-1 accuracy with mass fraction mean absolute errors as low as 1.2% and 1.8%, respectively. Beyond mere phase labeling, MatDiffract outputs full crystallographic results including refined structural models, fitted profiles, and quantitative compositions within tens of seconds per sample. Its modular vector-based architecture supports seamless incremental expansion to new material systems, providing an end-to-end solution to close the characterization throughput gap for autonomous materials discovery and high-throughput materials development.
Hongqing V. Wang, Ming-Wei Chen, Hong Luo et al.· 0 citations
This work demonstrates how recent foundational machine learning interatomic potentials (MLIPs) trained at the r$^2$SCAN level can be leveraged to improve the agreement of formation energies with experiment, reducing the mean absolute error by more than 40% relative to GGA without requiring any additional DFT calculation.
Timo Reents, Marnik Bercx, Giovanni Pizzi· 0 citations