Neural Network Predictive Tool of Ground Settlement Due to Dewatering Activities

The present paper reports the implementation of a neural network technique to predict ground settlement as occasioned by dewatering activities of a long-term large-scale drainage project. The objective of the project is to lower and maintain the level of the ground water table in urban areas through a system of a non-stop pumping wells whose layout and operation rate are determined and implemented in a pilot project at a district level. To make use of the wealth of data collected and to aid in the decision making regarding extending the project to other areas, a neural network predictive tool is developed to estimate ground settlement induced by the drainage activities near and further away from the pumping wells. ]’he backpropagation architecture is employed to design two networks for drawdownsettlement relationship and attenuation of settlements further away from the pumping wells. Incorporating relevant soil properties in the input nodes considerably improved the performance of both networks. Introduction A pilot drainage project (Mossaad, Sadek, and Ghoneim 1997) has been constructed to lower the water table in a 1 km2 residential urban area in Kuwait City. The drainage system consists of six 50 m deep pumping wells with the objective of lowering the water table to about 4 m below ground surface without adversely affecting the existing buildings, Fig. I. .................. -~.~ .4./,:.~’~’~’ , ~. °".,~’,~-~.=~.~f ̄ ̄ . "--’. I ’: .’7 .f’~! L. "~’:-’~ " "~ ,’%’" ",~--~-"/-.~/ ~’~’-~ .¢; ~.... ~I:’"~=..-J~ z,Y’.’.. ~’,-,’F~ ,,~ ~.,,.f .~,’ ,~:,~, P -.. lli "~;,’,~ ̄ Z"£ ’-’-’ "~’~ .~." :;,’t ..,... , ’.,,,. . ̄ "~ ":’ ’ ..... " ".’:i~ ’::’~’ ~’~’ ....... -.~f, .~,,4,,. v ,,,. --. ~=~;. ~. ~.-.,;. -:-~-~=~, "~, ~ .... .~ .... ~ L_~,.~.~I/~ ~ ......... & ;~ "/.’.~ "--~" t----t’ "~y -"’~ ~..~" ..... ,...