Our recent article in npj Computational Materials presents an efficient ML protocol for accelerating trajectory surface hopping dynamics, while tackling many key issues making machine learning of excited states difficult. The protocol introduces a new machine learning interatomic potential based …
Are universal machine learning potentials for excited states possible? Such a potential would be a major breakthrough — enabling key applications like the design of advanced photomaterials. We’ve already seen successful universal potentials for ground states — ANI-1ccx, MACE-OFF, our …
Meet OMNI-P2x — the First Universal ML Potential for Excited States! Read more »
Do you want to perform computational chemistry simulations but struggle with complex codes and lack computational resources? Are you conducting experiments without theoretical guidance and feel lost? No worries, the help is on the way! We are pleased to announce …
The Dral’s group is seeking an outstanding postdoc for AI-enhanced atomistic simulations. The position is a unique opportunity to plunge into the frontiers of atomistic research in collaboration with leading experts on related topics.
Another year flew by like a comet. And what a year it was! This year was packed full of updates from my group and, of course, MLatom, which is at the center of our research. MLatom provides us with a …
Highlights of the Year 2024! Last Weekly Update? Read more »
The new release of MLatom, version 3.16.1, provides an interface to DFTB+ and performance improvements. So even if you are not interested in DFTB, please upgrade your MLatom installation for faster calculations via pip: New release allows seamless execution of …
You can now use MLatom to perform TDDFT and TDA calculations with MLatom and parse Gaussian output files.This can be useful for UV/vis spectra simulations via single-point convolution and nuclear-ensemble approach (NEA).We also welcome a new contributor to MLatom: Vignesh Kumar …
TDDFT and TDA calculations + parsing of Gaussian output files Read more »
In our latest tutorial we show how MLatom can be used to simulate UV/vis spectra via single-point convolution and nuclear-ensemble approach (NEA). ML can also be used to increase precision of the NEA spectra at reduced cost. You can watch the detailed introduction and demonstration in the video. All …
If you feel lost in the ocean of various datasets to train your machine learning potential, a comprehensive overview can serve as the compass to help navigate through the resources available. Recently, we published a review on Machine Learning: Science …
MLST: Review on data sets for molecular ML potentials Read more »
Theoretical IR (infrared) spectroscopy is a powerful tool for assisting chemical structure identification. However, approaches based on quantum chemical calculations suffer from either high computational cost (e.g., density functional theory, DFT) or insufficient accuracy (semi-empirical methods). Hence, we introduce a new …
ML-enhanced Fast and Interpretable Simulation of IR Spectra Read more »