Finding
Fuzzy c-mean clustering and Genetic Algorithm can predict soil saturated hydraulic conductivity (Ks) accurately, making it a recommended technique due to the laborious and expensive nature of direct measuring.
Paper
Fuzzy c-mean (FCM) clustering and Genetic Algorithm capability in predicting saturated hydraulic conductivity
Citations: 4
Full text
Semantic ScholarAbstract
Soil saturated hydraulic conductivity (Ks) is one of the key parameters as a main input for many water transport models in environmental studies. Direct measuring of this parameter is laborious, time consuming and expensive. So indirect prediction techniques such as Fuzzy c-mean (FCM) clustering and Genetic Algorithm was used to predict Ks parameter from other easily available metadata. FCM algorithm was used to cluster data, after that a Fuzzy Inference System had been generated based on this clusters by 12 rules, 6 numbers of inputs and saturated hydraulic conductivity as output. The FIS was trained by seventy percent of database using Genetic Algorithm. Based on statistical indexes (Pearson correlation coefficient, Maximum Error, Root Mean Square Error, Modeling Efficiency and Coefficient of Determination), results showed that in most cases, estimated KsWas close to the measured Ks. Therefore, the use of FCM and GA techniques for estimating Ks is recommended.
Authors
Benyamin Taraghi, V. Jalali
Journal
2014 International Congress on Technology, Communication and Knowledge (ICTCK)