2022年1月26日 · Here, we present a unique methodology for crystal structure prediction (CSP) that relies on a machine learning algorithm called metric learning. It is shown that a binary classifier, trained on a large number of already identified crystal structures, can determine the isomorphism of crystal structures formed by two given chemical compositions ...

2022年8月5日 · In this study, we present a new paradigm of CSP specifically designed for structurally related molecules, referred to as Quick-CSP, which improves the TMFF accuracy, broadens the concept of fragment-based parameterization to impart transferability, and significantly reduces the extent of ab initio calculations for unprecedented levels of overall...

Crystal structure prediction (CSP) is the calculation of the crystal structures of solids from first principles. Reliable methods of predicting the crystal structure of a compound, based only on its composition, has been a goal of the physical sciences since the 1950s. [1]

2022年8月1日 · Here, we present a unique methodology for crystal structure prediction (CSP) that relies on a machine learning algorithm called metric learning. It is shown that a binary classifier, trained on a large number of already identified crystal structures, can determine the isomorphism of crystal structures formed by two given chemical compositions ...

2024年12月20日 · Crystal structure prediction (CSP) is based on finding the global or local minima of an energy surface within a broad space of atomic configurations, in which...

2024年11月12日 · Here, we present a universal GM for crystal structure prediction (CSP) via a conditional crystal diffusion variational autoencoder (Cond-CDVAE) approach, which is tailored to allow user-defined...

2022年6月2日 · Using results of quantum mechanical calculations for molecular dimers, an accurate two-body, rigid-monomer ab initio-based force field (aiFF) for the crystal is developed. Since CSPs with aiFFs are...

2024年3月4日 · Inspired by the generation-ranking concept of CSP, the present study demonstrates the potential of pure machine learning CSP for organic compounds using the stable crystal structure density, which is more feasible for prediction at this stage, as an indicator for trial structures screening and ranking.

2022年3月1日 · Crystal structure prediction (CSP) pertains to identifying the most stable structures of given classes of crystalline materials. The stability metric for CSP is often defined via a complex energy function, such as a potential energy surface, while in certain cases, other more straightforward metrics such as the structure's cohesive energy may ...

2024年9月30日 · In this review, we present a comprehensive review of the ML models applied in CSP. We first introduce the general steps for CSP and highlight the bottlenecks in conventional CSP methods. We further discuss the representation of crystal structures and illustrate how ML-assisted CSP works.