Abstract
Machine-learning force fields have been increasingly employed in order to extend the possibility of current first-principles calculations. However, the transferability of the obtained potential cannot always be guaranteed in situations that are outside the original database. To study such limitation, we examined the very difficult case of the interactions in gold–iron nanoparticles. For the machine-learning potential, we employed a linearized formulation that is parameterized using a penalizing regression scheme which allows us to control the complexity of the obtained potential. We showed that while having a more complex potential allows for a better agreement with the training database, it can also lead to overfitting issues and a lower accuracy in untrained systems.
Highlights
Atomistic modeling is often divided in two different types of simulations
In Fig. 2.a, we show the fitting error measured as the root mean square error (RMSE) for the five different types of descriptors
In the cases of GTO and STO functions, much fewer descriptors were selected in comparison to the peak functions. It remains that the LassoLars algorithm allows one to drastically decrease the number of employed descriptors with respect to the number of available descriptors
Summary
Atomistic modeling is often divided in two different types of simulations. On the one hand, quantum methods including Hartree-Fock and DFT approaches are considered the most accurate and are employed for virtually any types of chemical species[1, 2]. Numerous approaches are currently considered including Artificial Neural Networks[8], Gaussian approximation methods[9], Linearized potentials[10, 11], Spectral Neighbor Analysis Potential[12], Symmetric Gradient Domain Machine learning[13, 14] and Moment Tensor Potentials[15] The success of these techniques is recognized by the large variety of materials that were successfully tackled: pure metals[16,17,18,19,20], organic molecules[21,22,23,24], oxides[25, 26], water[27,28,29,30,31], amorphous materials[32,33,34,35,36,37] and hybrid perovskites[38]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
