Evaluation of Bayesian Network Model for Estimation of Pan Evaporation

Document Type : Research Paper


1 Phd of Water Resoursec Engineering, University of Tabriz, Iran

2 Associate Professor, Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Iran.

3 Assistant Professor, Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Iran

4 Assistant Professor, Department of Water Engineering, Faculty of Agriculture, University of Tabriz, Iran.


Evaporation is one of the main elements of hydrologic cycle. Accurate estimation of pan evaporation is very important in many water-related activities such as irrigation and drainage projects, water balance studies, reservoir operation, and the like. The class A pan is one of the main pan evaporation instruments, which is used in standard synoptic weather stations in Iran. Direct measurement of evaporation is expensive and time-consuming. Therefore, different empirical models, which use different meteorological variables, can be used to estimate pan evaporation. This is so crucial in arid and semi-arid countries such as Iran, where the climate is mostly hyper-arid and it is not easy to measure evaporation directly. In the recent decades, by the development of computers many data driven models have been created for estimating evaporation. One of the intelligent models widely used to hydrologic processes is Bayesian Network Model, which was introduced by Bentin in 1990, and then applied for neural networks by MacKey (1992). Bayesian networks (BNs), also known as belief networks (or Bayes nets for short), belong to the family of probabilistic graphical models (GMs). These graphical structures are used to represent knowledge about an uncertain domain. In particular, each node in the graph represents a random variable, while the edges between the nodes represent probabilistic dependencies among the corresponding random variables. These conditional dependencies in the graph are often estimated by using known statistical and computational methods. Hence, BNs combine principles from graph theory, probability theory, computer science, and statistics. GMs with undirected edges are generally called Markov random fields or Markov networks. These networks provide a simple definition of independence between any two distinct nodes based on the concept of a Markov blanket. Markov networks are popular in fields such as statistical physics and computer vision. BNs correspond to another GM structure known as a directed acyclic graph (DAG) that is popular in statistics, machine learning, and artificial intelligence societies. They enable an effective representation and computation of the joint probability distribution (JPD) over a set of random variables (Reggiani and Weerts, 2008). In addition, BNs model the quantitative strength of the connections between variables, allowing probabilistic beliefs about them to be updated automatically as new information becomes available. In this model, the unknown relationships between parameters in processes can be shown by a diagram. This diagram is non-circular, and has directions composed of nodes and curves for showing the possible relationships in parameters (Money et al, 2012). Therefore, the main objective of this study is modeling of daily class A pan evaporation using the Bayesian Network model in six stations of East Azerbaijan Province.


Main Subjects

1-       Alizadeh, A., 2004. Water and soil-plant relationship. Publication of Imam Reza (AS), Mashhad.
2-      Baran, E. and Jantunen, T., 2004. Stakeholder consultation for Bayesian decision support systems in environmental management.  Journal of Forest, 27(35), pp. 1-37.
3-      Bowker, H. and Lieberman, G. J., 1972. Engineering Statistics. Prentice-Hall, pp. 852.
4-      Brandt, G. and Henriksen, H., 2003. Protection of drinking water sources for quality and quantity:
geological survey of denmark and greenland, in future senarios for water management in europe. In FIRMA conference, Barcelona.
5-      Cain, J., 2001. Planning improvement in natural resource management: guideline for using Bayesian networks to support the planning and management of development program in the water sector and beyond. Centre for Ecology and Hydrology (CEH), Wallingford, UK.
6-       Dehghani, R., Ghorbani, M.A., Teshnehlab, M., Rikhtehgar Gheasi, A. and Asadi, E., 2015. Comparison and evalution of bayesian neural network, gene expression programming, support vector machine and multiple linear regression in river discharge estimation (Case Study: Sufi Chay Basin). Journal of Irrigation and Water Engineering, 5 (20), pp. 66-85. (In Persian).
7-      Farmani, R., Henriksen, H.J. and Savic, D., 2009. An evolutionary Bayesian belief network methodology for optimum management of groundwater contamination. Environmental Modelling and Software, 24(3), pp. 303-310.
8-       Ghobadian, R., Yaghobi, M. and Heidari, M.T., 2008. Preparation model predictions of surface evaporation within the city of kermanshah using neural network and compared with experimental relations. In The third Water Resources Management Conference, University of Tabriz, Iran. (In Persian).
9-       Ghorbani, M.A., Asadi, E. and Dehghani, R., 2013. Estimate the groundwater level in Tabriz using Bayesian neural network. In The Fifth Conference on Water Resources, University of Shahid Beheshti Tehran, Iran. (In Persian).
10-   Hozhabr, H., Moazed, H. and ShokriKhoochak, S., 2013. Estimation of reference evapotranspiration (ETo) using empirical models, artificial neural network modeling and their comparison with lysimeter data in urmia kahrizi station.Journal of Irrigation and Water Engineering, 4(15), pp. 13-25. (In Persian).

11-   Irmak, S., Haman, D. and Jones, J.w., 2002. Evaluation of class A pan coefficients for estimating reference evapotranspiration in a humid location. Journal of Irrigation and Drainage EngineeringASCE, 128 (3), pp. 153–159.

12-   Khanteymoori, A. and Sameni, M., 2011. Precipitation modeling using bayesian networks (BN). In The fifth Iran data mining conference, Amirkabir University of Technology Tehran, Iran. (In Persian).
13-   Lee, K.S. and Kim, S.U., 2008. Identification of uncertainty in low flow frequency analysis using Bayesian MCMC method. Hydrological Processes, 22, pp. 1949- 1964.
14-  MacKay, D. J. C., 1992. Bayesian interpolation. Neural Computation, 4, pp. 415-447.
15-  Madadgar, Sh. and Moradkhani, H., 2014. Spatio-temporal drought forecasting within Bayesian networks. Journal of Hydrology, 512, pp. 134-146.
16-  Maidement, R.,1993. Handbook of Hydrology. Mc GRAW-Hill, INC.
17-  McCann, R., Marcot, B. and Ellis, R., 2009. Bayesian belief networks: application in ecology and natural resource management. Journal of Forest Research, 36(12), pp. 3053-3062.
18-   Mohajerani, H., Mosaedi, A., Kholghi, M., Meftah Halghi, M. and Saadoddin, A., 2010. Introduction to Bayesian networks and their application in water resource management.In The first national conference on water resources management, coastal land, Faculty of Agricultural Sciences and Natural Resources Sari, Iran. (In Persian).
19-   Money, E.S., Reskhow, K.H. and Wiesner, M.R., 2012. The use of Bayesian networks for nanoparticle risk forecasting: Model formulationand baseline evaluation. Journal of Science of the Total Environment, 426, pp. 436- 445.
20-  Reggiani, P. and Weerts, A., 2008. Bayesian approach to decision-making under uncertainty: An application to real time forecasting in the river Rhine. Journal of Hydrology, 356, pp. 56-69.
21-  Sadeghi Hesar, A., Tabatabaee, H. and Jalili, M., 2012. A Surface water evaporation estimation model using bayesian belief networks with an application to the Persian gulf. Journal of Advances in Computer Research Quarterly, 3(1), pp. 13-22.
22-  Sadoddin, A., Letcher, RA., Jackeman, A.J. and Newham, L.T.H.A., 2005. Bayesian decision network approach forassessing the ecological impact of salinity management. Mathematics and Computer in Simulation. 69, pp. 162-176.
23-  Sajjad Khan, M.S. and Coulibaly, P., 2006. Bayesian network for rainfall- runoff modelling. Journal of Water Resource Research, 42(7), pp. 130-143.
24-  Salas, J.D., 1993. Analysis and modeling of hydrological time series. Handbook of hydrology, McGraw-Hill, New York.
Volume 43, Issue 2
July 2020
Pages 93-106
  • Receive Date: 22 June 2017
  • Revise Date: 28 June 2018
  • Accept Date: 01 July 2018
  • First Publish Date: 21 June 2020