We improved (p)KREG models for an accurate representation of molecular potential energy surfaces (PESs) by including gradient information explicitly in their formalism. Our models are better or on par with other state-of-the-art machine learning models as we show on extensive …
(p)KREG Models for Accurate Molecular Potential Energy Surfaces Read more »
Mario Barbatti, his group and collaborators published an update on Newton-X – a popular open-source platform for surface hopping and nuclear ensembles. An update include extension of the Newton-X platform to supervised (with our MLatom platform) and unsupervised learning (with ulamdyn). The paper is also open access and appeared in the Journal of Chemical Theory and Computation.
We have introduced two new NDDO-based semiempirical quantum-chemical methods ODM2 and ODM3, which are more consistent and accurate than other existing methods of this type.
What is the best semiempirical method to use for your system? Find out in the most extensive benchmark study.
Details about theory and implementation of up-to-now most advanced semiempirical quantum-chemical methods are published.
In our recent study, we propose using machine learning (ML) to correct differences in properties calculated at two quantum chemical (QC) methods with different accuracy. In the Δ-ML approach ML model is trained on differences between some property calculated at …
We propose using machine learning (ML) for improving semiempirical Hamiltonian. Given sufficiently large training set ML can be used to correct parameters of semiempirical quantum chemical (SQC) method individually for any target molecule. Such automatic parametrization technique (APT) stands in …