最小二乘支持向量机方法用于提高低水平量子化学方法计算吸收能的精度  

Improving the Accuracy of Low Level Quantum Chemical Calculation for Absorption Energies Based on Least Squares Support Vector Machine

作　　者：高婷[1] 韩博[1] 李辉[1] 李鸿志[1] 吕英华[1] 苏忠民[2] 

机构地区：[1]东北师范大学计算机科学与信息技术学院,智能信息处理吉林省高校重点实验室,长春130117 [2]东北师范大学化学学院,功能材料化学研究所,长春130024

出　　处：《高等学校化学学报》2012年第12期2734-2738,共5页Chemical Journal of Chinese Universities

基　　金：国家“九七三”计划项目(批准号:2009CB623605);国家自然科学基金(批准号:20903020);吉林省科技发展计划项目(批准号:20110364,20100114)资助

摘　　要：运用B3LYP/STO-3G和ZINDO两种低水平的量子化学方法计算了160个有机分子的UV-Vis吸收光谱,然后提取合适的物理参数,并以实验值为基础,引入最小二乘支持向量机方法以提高吸收能的计算值精度.结果表明,最小二乘支持向量机方法可有效提高量子化学计算精度,体系的吸收能误差均方根分别从0.95和0.46 eV降低到0.16和0.15 eV.最小二乘支持向量机校正方法的引入可在较少的机时和计算资源下得到比单一的量子化学计算方法更为稳定和精确的计算结果,且可在现有计算条件下预测现有计算能力达不到的精度.因此,将最小二乘支持向量机方法用于量子化学数据分析,为化学研究准确、快捷地预测分子性质提供了一种新的研究手段.Least squares support vector machine （LS-SVM） was introduced to improve the calculation accuracy of low level density functional theory. As a demonstration, this approach combined low level quantum mechanical calculation with LS-SVM correction has been applied to evaluate the absorption energies of 160 organic molecules. After LS-SVM correction, the root mean square （RMS） deviations of the calculated absorption energies reduce from 0. 95 and 0. 46 eV to 0. 16 and 0. 15 eV for B3LYP/STO-3G and ZINDO methods, respectively. The LS-SVM correction may be a potential better method to predict high accurate absorption energies comparing with quantum chemical calculations when time and resource are limited or it is hard to achieve high accurate results by either quantum chemical calculation or measurement. This method provides a new means for accurately and quickly predicting of the molecular properties in quantum chemistry study.

关 键 词：有机小分子 吸收能 最小二乘支持向量机 密度泛函理论 

分 类 号：O641[理学—物理化学]