References
[1]العاني ، افتخار عبد الجواد عبد الحميد (2007) “أنموذج شبكة عصبية اصطناعية لتقدير التبخر _نتح المرجعي لمنطقة الموصل ” اطروحة دكتوراه ،كلية الهندسة،جامعة الموصل
[2] Allen, R. G., Pereira, L. S., Raes, D., and Smith, M. (1998), “ Crop Evapotranspiration: Guidelines for Computing Crop Water Requirement.” Irrigation and Drainage paper No. 56, Food and Agriculture Organization of the United Nations (FAO), Rome.
[3] AL-Hatem, N. T. ,(2004), “Rainfall– Discharge Modeling of Tigris Basins Using Artificial Neural Network”,Ph. D. Thesis, College of Engineering, Mosul University.
[4] ASCE Task Committee on Application of Artificial Neural Networks in Hydrology , (2000), “ Artificial Neural Networks in Hydrology: Hydrology Applications”, Journal of Hydrologic Engineering, ASCE, 5(3): 124-137.
Tikrit Journal of Engineering Sciences (2009) 16(2) 43- 50
Using of Learning Vector Quantization Network for Pan Evaporation Estimation
Kamel A. Abdulmuhsin | Iftekhar A. Al-Ani |
|
Water Resources Eng. Dept., University of Mosul, Iraq | Water Resources Technical Institute, Mosul, Iraq |
Abstract
A modern technique is presented to study the evaporation process which is considered as an important component of the hydrological cycle. The Pan Evaporation depth is estimated depending upon four metrological factors viz. (temperature, relative humidity, sunshine, and wind speed). Unsupervised Artificial Neural Network has been proposed to accomplish the study goal, specifically, a type called Linear Vector Quantitization, (LVQ). A step by step method is used to cope with difficulties that usually associated with computation procedures inherent in these kind of networks. Such systematic approach may close the gap between the hesitation of the user to make use of the capabilities of these type of neural networks and the relative complexity involving the computations procedures. The results reveal the possibility of using LVQ for of Pan Evaporation depth estimation where a good agreement has been noticed between the outputs of the proposed network and the observed values of the Pan Evaporation depth with a correlation coefficient of 0.986.
Download Full-Text PDF
Keywords: Evaporation, Neural network