Using CART algorithm in predicting groundwater table fluctuations inside and outside of an irrigation system (case study: irrigating area of Qazvin)

Document Type : Research Paper

Authors

1 University of Zabol

2 Dept. of Water Engineering, Faculty of Water and Soil, University of Zabol.

3 Associate Professor, Dept. of Irrigation and Drainage, Faculty of Agriculture and Natural Resources, University of Tehran

4 Assistant Professor, Dept. of Water Engineering, Faculty of Agriculture, University of Zanjan

Abstract

Due to importance of predicting groundwater table fluctuations as an important and key factor in agricultural activities, the main aim of this study is finding the model and effective factors in predicting groundwater table fluctuations by using CART tree algorithm in data mining package of "SPSS modeler 18.0 IBM", in Qazvin irrigating area during 15 years from 2001 to 2015. Input variables to the model were the degree of effectiveness of each piezometer, net water requirements, the amount of consumption in each piezometer, rainfall depth, inflow and outflow from Taleghan reservoir, cropping area, and inflow to the irrigation system, the model output as objective function is groundwater table fluctuations. The predictability of the model was determined by the criteria such as correlation coefficient and mean absolute error. The results showed that the performance of the CART algorithm in predicting water table fluctuations inside the irrigation system is better than the outside of it. Furthermore, the results show that the most important parameter effective in predicting groundwater table fluctuations inside of the irrigation system is inflow to reservoir.

Keywords

Main Subjects

References

AbbasNezhad, A and Shahidasht, A. (2013). Vulnerability of Sirjan Plain Due to Aquifer Over Abstraction. Journal of Geography and Urban Planning – Regional 3(7), 85-96. (In Farsi)
Barikani, A., Ahmadian, M. and  Khalilian, S. (2011). Optimal Sustainable Use of groundwater resources in agriculture: Case Study Subsector in Qazvin Plain. Journal of Agricultural Economics and Development 25(2), 253-262. (In Farsi)
Chattamvelli, R. (2011). Data Mining Algorithms, (1th ed.). Oxford: Alpha Science, PP: 274-290.
Corona, O. L., Fuentes, O. E., Casique, E.M., Longoria, P.P. and Moran, T. G. (2016). Data Mining of Historic Hydrogeological and Socioeconomic Data Bases of the Toluca Valley, Mexico. Journal of Water Resource and Protection, 8(4), 522-533.
Gupta, G.K. (2011) Introduction to Data Mining with Case Studies, (2th ed.), Prentice hall of India.
Huajie, D., Zhengdong, D. and Feifan, Deng. (2016). Classification of groundwater potential in chaoyang area based on quest algorithm. College of Defense Engineering, advancing the understanding of our living planet, Beijing, China, 19: 890-893.
Jang, C.S., Chen., S.K. and Ku, Y.M. (2013). Applying indicator-based geostatistical approaches to determine potential zones of groundwater recharge based on borehole data. Catena, 101, 178–187.
Khan, S., Gabriel, H. F. and Rana, T. (2008). Standard precipitation index to track drought and assess impact of rainfall on watertables in Irrigation and Drainage Systems, 22, 159–177.
Kolli, K. and R, Seshadri. (2013). Ground Water Quality Assessment using Data Mining Techniques. International Journal of Computer Applications, 76(15): 39-45.
Kotsiantis, S., Kostoulas, A., Lykoudis S., Argirio, A. and Menagias, K. (2008). Using data mining techniques for estimating minimum, maximum and average daily temperature value. IJMPES. 1(2): 117-121.
Mohammadi, M., Mohammadi Ghaleney, M. , Ebrahimi, K. (2011). Spatial and Temporal Variations of Groundwater Quality of Qazvin plain, Water Research Iran, 5(8), 41-51. (In Farsi)
Naghibi, S. A., Pourghasemi, H. R. and Dixon, B. (2016). GIS-based groundwater potential mapping using boosted regression tree, classification and regression tree, and random forest machine learning models in Iran. Environmental Monitoring and Assessment, 188(1):44
Oorkavalan, G., Chidambaram, S. M., Mariappan, V., Kandaswamy, G. and Natarajan. S. (2016). Cluster Analysis to Assess Groundwater Quality in Erode District, Tamil Nadu, India. Circuits and Systems, Computer Science & Communications, 7(6): 877-890
Sotoodehnia, A. Sotoodehnia, S. (2016).The Assessment of the role of Taleghan reservoir dam construction on sedimentation in Ghazvin plain irrigation network,14-15 Dec., Faculty of Engineering and Technology, Imam Khomeini International University, Ghazvin, Iran, pp.1-9. (In Farsi)
Stumpp, C., J. Zurek, A.J., Wachniew, P., Gargini, Gemitzi, A., Filippini, M. and Witczak, S. (2016). A decision tree tool supporting the assessment of groundwater vulnerability. Environmental Earth Sciences, 75(1057), 1-7.
Zhao, Y., Li, Lifen., Y and Zhang, L. and Wang, Q. (2016). Groundwater level prediction of landslide based on classification and regression tree. geodesy and geodynamics, l7(5), 348-355.
 
 
 
Iranian Journal of Soil and Water Research
Volume 49, Issue 2
May and June 2018
Pages 385-395

Files

Share

How to cite

Statistics