Alternative approach to chemical accuracy: a neural networks-based first-principles method for heat of formation of molecules made of H, C, N, O, F, S, and Cl.

作者: Jian Sun , Jiang Wu , Tao Song , LiHong Hu , KaiLu Shan

DOI: 10.1021/JP502096Y

关键词:

摘要: The neural network correction approach that was previously proposed to achieve the chemical accuracy for first-principles methods is further developed by a combination of Kennard–Stone sampling and Bootstrapping methods. As result, calculated heat formation improved further, moreover, error bar each result can be determined. An enlarged database (Chen/13), which contains total 539 molecules made common elements H, C, N, O, F, S, Cl, constructed divided into training (449 molecules) testing (90 data sets with method. Upon correction, mean absolute deviation (MAD) B3LYP/6-311+G(3df,2p) reduced from 10.92 1.47 kcal mol–1 14.95 1.31 sets, respectively. Furthermore, method, broadly used statistical employed assess neu...

参考文章(42)
David R. Lide, CRC handbook of chemistry and physics on CD-ROM Chapman&Hall , CRC Press. ,(2000)
Larry A. Curtiss, Krishnan Raghavachari, Paul C. Redfern, John A. Pople, Assessment of Gaussian-3 and density functional theories for a larger experimental test set Journal of Chemical Physics. ,vol. 112, pp. 7374- 7383 ,(2000) , 10.1063/1.481336
Matthew D. Wodrich, Clémence Corminboeuf, Reaction enthalpies using the neural-network-based X1 approach: the important choice of input descriptors. Journal of Physical Chemistry A. ,vol. 113, pp. 3285- 3290 ,(2009) , 10.1021/JP9002005
Peter R. Schreiner, Andrey A. Fokin, Robert A. Pascal,, Armin de Meijere, Many density functional theory approaches fail to give reliable large hydrocarbon isomer energy differences. Organic Letters. ,vol. 8, pp. 3635- 3638 ,(2006) , 10.1021/OL0610486
Jerzy Cioslowski, Michael Schimeczek, Guang Liu, Vesselin Stoyanov, A set of standard enthalpies of formation for benchmarking, calibration, and parametrization of electronic structure methods Journal of Chemical Physics. ,vol. 113, pp. 9377- 9389 ,(2000) , 10.1063/1.1321306
Larry A. Curtiss, Christopher Jones, Gary W. Trucks, Krishnan Raghavachari, John A. Pople, Gaussian‐1 theory of molecular energies for second‐row compounds Journal of Chemical Physics. ,vol. 93, pp. 2537- 2545 ,(1990) , 10.1063/1.458892
Jörg Behler, Roman Martoňák, Davide Donadio, Michele Parrinello, Metadynamics Simulations of the High-Pressure Phases of Silicon Employing a High-Dimensional Neural Network Potential Physical Review Letters. ,vol. 100, pp. 185501- ,(2008) , 10.1103/PHYSREVLETT.100.185501