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.

介绍了一种新颖的机器学习方法，使用多分支深度神经网络和计算的粉末 X 射线衍射，结合部分化学组成信息，实现对结构的成功求解。

利用生成式深度学习从信息受损的衍射数据实现端到端结构解决方案

Towards End-to-End Structure Solutions from Information-Compromised  Diffraction Data via Generative Deep Learning

Recently, the remarkable capabilities of large language models (LLMs) have
been illustrated across a variety of research domains such as natural language
processing, computer vision, and molecular modeling. We extend this paradigm by
utilizing LLMs for material property prediction by introducing our model
Materials Informatics Transformer (MatInFormer). Specifically, we introduce a
novel approach that involves learning the grammar of crystallography through
the tokenization of pertinent space group information. We further illustrate
the adaptability of MatInFormer by incorporating task-specific data pertaining
to Metal-Organic Frameworks (MOFs). Through attention visualization, we uncover
the key features that the model prioritizes during property prediction. The
effectiveness of our proposed model is empirically validated across 14 distinct
datasets, hereby underscoring its potential for high throughput screening
through accurate material property prediction.

利用大型语言模型进行材料属性预测，通过引入模型 MatInFormer，在加工空间群信息的关键词化过程中学习晶体学语法，并通过任务特定数据进一步展示 MatInFormer 的适应性。通过注意力可视化，我们揭示了模型在属性预测过程中重点关注的特征，并在 14 个不同数据集中验证了我们提出模型的有效性，从而强调其在通过准确的材料属性预测进行高通量筛选方面的潜力。

材料信息学变压器：一种用于可解释材料性质预测的语言模型

Materials Informatics Transformer: A Language Model for Interpretable  Materials Properties Prediction

This paper develops geographic-style maps containing 2D lattices in all known
crystals parameterised by recent complete invariants. Motivated by rigid
crystal structures, lattices are considered up to rigid motion and uniform
scaling. The resulting space of 2D lattices is a square with identified edges
or a sphere without one point. The new continuous maps show all Bravais classes
as low-dimensional subspaces, visualise hundreds of thousands of real crystal
lattices from the Cambridge Structural Database, and motivate the development
of continuous and invariant-based crystallography.

本论文开发了新的地理风格地图，其中包含所有已知晶体中参数化的 2D 晶格。通过刚性晶体结构的驱动，晶格被考虑为刚性运动和均匀缩放。最终的 2D 晶格空间是一个具有标识边的正方形或没有一个点的球体。新的连续地图展示了所有的布拉维格点群作为低维子空间，并可视化了上万个实际晶体结构。这些研究成果为连续和基于不变量的晶体学的发展提供了动力。