Skip to Main content Skip to Navigation
Journal articles

Regression Machine Learning Models Used to Predict DFT-Computed NMR Parameters of Zeolites

Abstract : Machine learning approaches can drastically decrease the computational time for the predictions of spectroscopic properties in materials, while preserving the quality of the computational approaches. We studied the performance of kernel-ridge regression (KRR) and gradient boosting regressor (GBR) models trained on the isotropic shielding values, computed with density-functional theory (DFT), in a series of different known zeolites containing out-of-frame metal cations or fluorine anion and organic structure-directing cations. The smooth overlap of atomic position descriptors were computed from the DFT-optimised Cartesian coordinates of each atoms in the zeolite crystal cells. The use of these descriptors as inputs in both machine learning regression methods led to the prediction of the DFT isotropic shielding values with mean errors within 0.6 ppm. The results showed that the GBR model scales better than the KRR model
Complete list of metadata

https://hal-cnrs.archives-ouvertes.fr/hal-03669040
Contributor : Tzonka Mineva Connect in order to contact the contributor
Submitted on : Monday, May 16, 2022 - 12:09:35 PM
Last modification on : Thursday, May 19, 2022 - 3:43:34 AM

File

computation-10-00074.pdf
Publisher files allowed on an open archive

Identifiers

Collections

Citation

Robin Gaumard, Dominik Dragún, Jesús Pedroza-Montero, Bruno Alonso, Hazar Guesmi, et al.. Regression Machine Learning Models Used to Predict DFT-Computed NMR Parameters of Zeolites. Computation, MDPI, 2022, 10 (5), pp.74. ⟨10.3390/computation10050074⟩. ⟨hal-03669040⟩

Share

Metrics

Record views

3

Files downloads

4