This study was conducted to establish the refined model for prediction of
flocculation/sedimentation efficiency in factual drinking water treatment plants using
model tree technique. In order to carry out machine leaning for determining each linear
model, five parameters time, coagulant dose, raw water turbidity, SCD and conductivity,
which were measured and collected from the field(K_DWTP), were selected and used. The
existing analytical models developed by previous researchers were used only to examine
closely the mechanism of flocculation rather than to apply it for practical purpose.
The refined model established using model tree technique in this study could predict
the factual sedimentation effciency accurately (below 9percentage of average absoute
error). Also, in aspect of engineering convenience, without any additional manipulation
of parameters, it can be applied to practical works.
