Research Article

Evaluation of Several Machine Learning Models for Field Canal Improvement Project Cost Prediction

Table 2

The statistical properties of the dataset selected for the testing modeling phase.

 ParameterCD
Parameter nameCost of FCIPDuration of FCIP constructionArea servedTotal length of PVC pipelineNumber of irrigation valuesConstruction yearGeographical zone
UnitLE/FCIPDayHectareMeterNumberYearZone

Mean352714.3577.0048.46807.578.412013.231.29
Standard error7469.770.811.2427.650.260.090.05
Median318652.9276.0045.68720.827.462014.002.00
Mode201587.4466.0051.00630.005.002014.002.00
Standard deviation112791.0912.1918.79417.583.961.410.79
Sample variance12721830134.86148.62352.92174372.8315.711.990.63
Kurtosis0.052.090.210.066.340.12−1.18
Skewness0.881.220.840.761.72−1.14−0.58
Range503217.1067.0086.001916.1527.875.002.00
Minimum198035.5459.0019.00119.001.022010.000.00
Maximum701252.64126.00105.002035.1528.892015.002.00
Sum80418872.5317556.0011049.13184125.651917.50459016.00295.00
Count228.00228.00228.00228.00228.00228.00228.00
Confidence level (95.0%)14718.961.592.4554.490.520.180.10