People | Locations | Statistics |
---|---|---|
Ferrari, A. |
| |
Schimpf, Christian |
| |
Dunser, M. |
| |
Thomas, Eric |
| |
Gecse, Zoltan |
| |
Tsrunchev, Peter |
| |
Della Ricca, Giuseppe |
| |
Cios, Grzegorz |
| |
Hohlmann, Marcus |
| |
Dudarev, A. |
| |
Mascagna, V. |
| |
Santimaria, Marco |
| |
Poudyal, Nabin |
| |
Piozzi, Antonella |
| |
Mørtsell, Eva Anne |
| |
Jin, S. |
| |
Noel, Cédric |
| |
Fino, Paolo |
| |
Mailley, Pascal |
| |
Meyer, Ernst |
| |
Zhang, Qi |
| |
Pfattner, Raphael | Brussels |
|
Kooi, Bart J. |
| |
Babuji, Adara |
| |
Pauporte, Thierry |
|
Muller, K.
in Cooperation with on an Cooperation-Score of 37%
Topics
Publications (11/11 displayed)
- 2016Cloud water composition during HCCT-2010: Scavenging efficiencies, solute concentrations, and droplet size dependence of inorganic ions and dissolved organic carboncitations
- 2015Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Spacecitations
- 2011Search for Contact Interactions in $e^{%5Cpm}p$ Collisions at HERAcitations
- 2010Active packaging functions. Part 2. Functional films
- 2008A Search for Excited Neutrinos in e-p Collisions at HERAcitations
- 2003The high field project at Dresden/Rossendorf: A pulsed 100 T/10 ms laboratory at an infrared free-electron-laser facilitycitations
- 2003Search for new physics in $e^{pm}q$ contact interactions at HERA
- 2002THE DRESDEN 100 T/10 ms PROJECT: A HIGH MAGNETIC FIELD FACILITY AT AN IR-FEL
- 2002Search for excited neutrinos at HERAcitations
- 2000Search for compositeness, leptoquarks and large extra dimensions in $e q$ contact interactions at HERAcitations
- 2000A Search for excited fermions at HERAcitations
Places of action
article
Machine Learning Predictions of Molecular Properties: Accurate Many-Body Potentials and Nonlocality in Chemical Space
Abstract
Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the “holy grail” of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. In addition, the same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies.