结合机器学习算法提高从头算方法对HF/HBr/H^(35)Cl/Na^(35)Cl振动能谱的预测性能  

Combining machine learning algorithm to improve prediction performance of ab initio method for vibrational energy spectra of HF/HBr/H^(35)Cl/Na^(35)Cl

作　　者：杨章章 刘丽 万致涛 付佳 樊群超 谢锋[2] 张燚 马杰[4] Yang Zhang-Zhang;Liu Li;Wan Zhi-Tao;Fu Jia;Fan Qun-Chao;Xie Feng;Zhang Yi;Ma Jie(School of Science,Key Laboratory of High Performance Scientific Computation,Xihua University,Chengdu,610039,China;Institute of Nuclear and New Energy Technology,Collaborative Innovation Center of Advanced Nuclear Energy Technology,Key Laboratory of Advanced Reactor Engineering and Safety of Ministry of Education,Tsinghua University,Beijing,100084,China;College of Advanced Interdisciplinary Studies,National University of Defense Technology,Changsha 410073,China;State Key Laboratory of Quantum Optics and Quantum Optics Devices,Laser Spectroscopy Laboratory,College of Physics and Electronics Engineering,Shanxi University,Taiyuan 030006,China)

机构地区：[1]西华大学理学院,高性能科学计算四川省高校重点实验室,成都610039 [2]清华大学核能与新能源技术研究院、先进核能技术协同创新中心、先进反应堆工程与安全教育部重点实验室,北京100084 [3]国防科技大学,前沿交叉学科学院,长沙410073 [4]山西大学物理与电子工程学院,量子光学与量子光学器件国家重点实验室,太原030006

出　　处：《物理学报》2023年第7期172-180,共9页Acta Physica Sinica

基　　金：国家自然科学基金(批准号:11904295);四川省科学技术计划(批准号:2021ZYD0050);极端光学协同创新中心开放研究基金项目(批准号:KF2020003)资助的课题.

摘　　要：高精度振动能谱蕴含着分子体系的大量量子特征,是人们认识和操控分子的重要基础数据.目前,从头算方法在计算分子的振动能谱方面取得了大量成果,但是仍然面临着精度和计算量上的挑战.本文提出了一种综合从头算方法与机器学习算法进行能谱预测的新方法,在提高振动能级精度的同时大幅降低了计算量.针对HF、HBr、H^(35)Cl和Na^(35)Cl等卤素分子的研究结果表明,相较于单独的CCSD(T)/cc-pV5Z计算方法,新方法将误差减少了50%以上,同时将计算量降低了一个数量级.Halides play an important role in atmospheric chemistry,corrosion of steel,and also in controlling the abundance of O3.Moreover high-precision vibrational energy spectra contain a large amount of quantum information of molecular system and are basic data for people to understand and manipulate molecules.At present,ab-initio methods have achieved many calculation results of the potential energy surfaces and corresponding vibrational energy of molecules,but they still face challenges in terms of accuracy and computational cost.Recently,data-driven machine learning methods have demonstrated very strong capability of extracting high-dimensional functional relationships from massive data and have been widely used in spectrum studies.Therefore,a theoretical approach to combining ab-initio method and machine learning algorithm is presented here to predict the vibrational energy of diatomic systems,which improves the accuracy and simultaneously reduces the computational cost.Firstly,the vibrational energy levels of 42 diatomic molecules are obtained by using different CCSD(T)methods to calculate the configurations from simple to complex and the corresponding experimental results are also collected.A machine learning algorithm is then used to learn the difference between the CCSD(T)method calculated vibrational results and the experimental vibrational results,and a high-dimensional error function is finally constructed to improve the original CCSD(T)computational accuracy.The results for HF,HBr,H^(35)Cl and Na^(35)Cl(they did not appear in the training set)and other halogen molecules show that compared with the CCSD(T)/cc-pV5Z calculation method alone,the present method reduces the prediction error by more than 50%and the computational cost by nearly one order of magnitude.It is worth noting that the method proposed in this paper is not only limited to the energy level prediction of diatomic systems,but also applicable in other fields where data can be obtained by ab initio methods and experimental methods simultaneously,

关 键 词：振动能谱 从头算 机器学习 卤素分子 

分 类 号：O561[理学—原子与分子物理] TP181[理学—物理]