Four generations of high-dimensional neural network potentials
J Behler - Chemical Reviews, 2021 - ACS Publications
Since their introduction about 25 years ago, machine learning (ML) potentials have become
an important tool in the field of atomistic simulations. After the initial decade, in which neural …
an important tool in the field of atomistic simulations. After the initial decade, in which neural …
Combining machine learning and computational chemistry for predictive insights into chemical systems
Machine learning models are poised to make a transformative impact on chemical sciences
by dramatically accelerating computational algorithms and amplifying insights available from …
by dramatically accelerating computational algorithms and amplifying insights available from …
Physics-inspired structural representations for molecules and materials
The first step in the construction of a regression model or a data-driven analysis, aiming to
predict or elucidate the relationship between the atomic-scale structure of matter and its …
predict or elucidate the relationship between the atomic-scale structure of matter and its …
Liquid-liquid transition in water from first principles
A long-standing question in water research is the possibility that supercooled liquid water
can undergo a liquid-liquid phase transition (LLT) into high-and low-density liquids. We …
can undergo a liquid-liquid phase transition (LLT) into high-and low-density liquids. We …
[HTML][HTML] When do short-range atomistic machine-learning models fall short?
We explore the role of long-range interactions in atomistic machine-learning models by
analyzing the effects on fitting accuracy, isolated cluster properties, and bulk thermodynamic …
analyzing the effects on fitting accuracy, isolated cluster properties, and bulk thermodynamic …
[HTML][HTML] Computational discovery of energy materials in the era of big data and machine learning: a critical review
Z Lu - Materials Reports: Energy, 2021 - Elsevier
The discovery of novel materials with desired properties is essential to the advancements of
energy-related technologies. Despite the rapid development of computational infrastructures …
energy-related technologies. Despite the rapid development of computational infrastructures …
Updates to the DScribe library: New descriptors and derivatives
We present an update of the DScribe package, a Python library for atomistic descriptors. The
update extends DScribe's descriptor selection with the Valle–Oganov materials fingerprint …
update extends DScribe's descriptor selection with the Valle–Oganov materials fingerprint …
Layer-by-layer unsupervised clustering of statistically relevant fluctuations in noisy time-series data of complex dynamical systems
Complex systems are typically characterized by intricate internal dynamics that are often
hard to elucidate. Ideally, this requires methods that allow to detect and classify in an …
hard to elucidate. Ideally, this requires methods that allow to detect and classify in an …
Accurate prediction of heat conductivity of water by a neuroevolution potential
We propose an approach that can accurately predict the heat conductivity of liquid water. On
the one hand, we develop an accurate machine-learned potential based on the …
the one hand, we develop an accurate machine-learned potential based on the …
[HTML][HTML] Phase diagrams—Why they matter and how to predict them
Understanding the thermodynamic stability and metastability of materials can help us to, for
example, gauge whether crystalline polymorphs in pharmaceutical formulations are likely to …
example, gauge whether crystalline polymorphs in pharmaceutical formulations are likely to …