Application of kernel ridge regression in predicting neutron-capture reaction cross-sections

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 (n, gamma) 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.

Automated summary

This article presents the first application of machine-learning and kernel ridge regression (KRR) in studying neutron-capture reactions' cross-sections. The KRR approach effectively reduces the relative errors between experimental data and theoretical predictions, achieving high accuracy in cross-section determination.