QSBR study of substituted phenols and benzoic acids
The biodegradability of 30 substituted phenols and benzoic acids was determined by BOD technique. The molecular weight (MW), heat of formation (Hf) and the energy of the highest occupied molecular orbital (EHOMO) of the studied compounds were calculated by the quantum chemical method MOPAC6.0-AM1. The quantitative structure-biodegradability relationships (QSBRs) were developed by the linear regression method and neural network approach, respectively. It has been shown that the neural network method is able to provide a superior fit to the training set data and test se t data and produce a lower prediction error than the linear regression method.
作 者: LU Guang-hua WANG Chao YUAN Xing ZHAO Yuan-hui 作者单位: LU Guang-hua,WANG Chao(College of Water Resources and Environment, Hohai University, Nanjing 210098, China)YUAN Xing,ZHAO Yuan-hui(Department of Environmental Science, Northeast Normal University, Changchun 130024, China)
刊 名: 环境科学学报(英文版) ISTIC SCI 英文刊名: JOURNAL OF ENVIRONMENTAL SCIENCES 年,卷(期): 2003 15(1) 分类号: X131.2 关键词: BOD regression artificial neural network prediction