Research Article
Evaluation of Several Machine Learning Models for Field Canal Improvement Project Cost Prediction
Table 1
The statistical properties of the dataset selected for the training modeling phase.
| Parameter | C | D | | | | | | Parameter name | Cost of FCIP | Duration of FCIP construction | Area served | Total length of PVC pipeline | Number of irrigation values | Construction year | Geographical zone | Unit | LE/FCIP | Day | Hectare | Meter | Number | Year | Zone |
| Mean | 353463.30 | 76.34 | 49.41 | 813.83 | 8.18 | 2013.20 | 0.00 | Standard error | 7539.45 | 0.78 | 1.28 | 26.10 | 0.23 | 0.10 | 0.00 | Median | 320292.58 | 75.00 | 45.90 | 753.75 | 8.00 | 2014.00 | 0.00 | Mode | 514778.00 | 64.00 | 51.00 | 530.00 | 5.00 | 2014.00 | 0.00 | Standard deviation | 113843.24 | 11.71 | 19.31 | 394.03 | 3.52 | 1.48 | 0.00 | Sample variance | 12960283390.67 | 137.20 | 372.83 | 155258.84 | 12.36 | 2.18 | 0.00 | Kurtosis | −0.22 | 1.90 | −0.07 | −0.24 | 2.72 | −0.13 | −1.18 | Skewness | 0.77 | 1.04 | 0.75 | 0.60 | 0.94 | −1.05 | −0.58 | Range | 518824.50 | 69.00 | 85.00 | 1956.45 | 26.00 | 5.00 | 0.00 | Minimum | 186825.98 | 58.00 | 19.00 | 119.00 | 1.00 | 2010.00 | 0.00 | Maximum | 705650.48 | 127.00 | 104.00 | 2075.45 | 27.00 | 2015.00 | 0.00 | Sum | 80589633.51 | 17405.00 | 11265.43 | 185554.07 | 1866.02 | 459010.00 | 0.00 | Count | 228.00 | 228.00 | 228.00 | 228.00 | 228.00 | 228.00 | 228.00 | Confidence level (95.0%) | 14856.26 | 1.53 | 2.52 | 51.42 | 0.46 | 0.19 | 0.00 |
|
|