论文标题
通过使用深层神经网络测定稳定的P壳核上的光核反应截面
Determination of Photonuclear Reaction Cross-Sections on stable p-shell Nuclei by Using Deep Neural Networks
论文作者
论文摘要
高能光子诱导的光核反应是核结构研究中重要的反应之一。在此反应中，靶材料会受到伽马射线能量范围内能量的光子的轰击，并且光子可以在统计上被目标材料中的核吸收。为了摆脱激发靶核的过量能量，它可以根据分离能阈值首先发射质子，中子，alpha和光颗粒。在发射过程之后，通常可以形成不稳定的核。通过对光核反应后这种产品形成的研究，可以获得核结构信息。在目前的工作中，已经使用神经网络方法估算了稳定的P壳核上的（γ，N）光核反应横截面。这项研究的主要目的是找到对横截面的最佳估计的神经网络结构，并将它们彼此和可用的文献数据进行比较。根据结果，该方法适合此任务。
The photonuclear reactions which is induced by high-energetic photon are one of the important type of reactions in the nuclear structure studies. In this reaction, a target material is bombarded by photons with the energies in the range of gamma-ray energy scale and the photons can statistically be absorbed by a nucleus in the target material. In order to get rid of the excess energies of the excited target nuclei, it can first emit protons, neutrons, alphas and light particles according to the separation energy thresholds. After this emitting process, generally an unstable nucleus can be formed. By the investigation of this products forming after photonuclear reactions, nuclear structure information can be obtained. In the present work, (γ, n) photonuclear reaction cross-sections on stable p-shell nuclei have been estimated by using neural network method. The main purpose of this study is to find neural network structures that give the best estimations on the cross-sections and to compare them with each other and available literature data. According to the results, the method is convenient for this task.
