摘要
Water pollution affects plants and organisms living in these bodies of water; and, in almost all cases the effect is damaging not only to individual species and populations, but also to the natural biological communities. Genetic algorithm and kernel partial least square （GA-KPLS） and Levenberg- Marquardt artificial neural network （L-M ANN） techniques were used to investigate the correlation between retention time （tR） and descriptors for 150 organic contaminants in natural water and wastewater, which are obtained by gas chromatography coupled to high-resolution time-of-flight mass spectrometry （GC-TOF MS）. The L-M ANN model gave a significantly better performance than the GA-KPLS model. This indicates that L-M ANN can be used as an alternative modeling toot for quantitative structure-retention relationship （QSRR） studies.
Water pollution affects plants and organisms living in these bodies of water; and, in almost all cases the effect is damaging not only to individual species and populations, but also to the natural biological communities. Genetic algorithm and kernel partial least square （GA-KPLS） and Levenberg- Marquardt artificial neural network （L-M ANN） techniques were used to investigate the correlation between retention time （tR） and descriptors for 150 organic contaminants in natural water and wastewater, which are obtained by gas chromatography coupled to high-resolution time-of-flight mass spectrometry （GC-TOF MS）. The L-M ANN model gave a significantly better performance than the GA-KPLS model. This indicates that L-M ANN can be used as an alternative modeling toot for quantitative structure-retention relationship （QSRR） studies.
