Application of kernel ridge regression in predicting neutron-capture reaction cross-sections
Tianxiang Huang, Xinhui Wu, P. W. Zhao
Abstract
Abstract This article provides the first application of the machine-learning approach in the study of the cross-sections for neutron-capture reactions with the kernel ridge regression (KRR) approach. It is found that the KRR approach can reduce the root-mean-square (rms) deviation of the relative errors between the experimental data of the Maxwellian-averaged <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" overflow="scroll"> <mml:mo stretchy="false">(</mml:mo> <mml:mi>n</mml:mi> <mml:mo>,</mml:mo> <mml:mi>γ</mml:mi> <mml:mo stretchy="false">)</mml:mo> </mml:math> cross-sections and the corresponding theoretical predictions from 69.8% to 35.4%. By including the data with different temperatures in the training set, the rms deviation can be further significantly reduced to 2.0%. Moreover, the extrapolation performance of the KRR approach along different temperatures is found to be effective and reliable.