首页 » 文章 » 文章详细信息
Advances in Meteorology Volume 2016 ,2016-12-30
Methodology for Developing Hydrological Models Based on an Artificial Neural Network to Establish an Early Warning System in Small Catchments
Research Article
Ivana Sušanj 1 Nevenka Ožanić 1 Ivan Marović 2
Show affiliations
DOI:10.1155/2016/9125219
Received 2015-09-29, accepted for publication 2015-11-10, Published 2015-11-10
PDF
摘要

In some situations, there is no possibility of hazard mitigation, especially if the hazard is induced by water. Thus, it is important to prevent consequences via an early warning system (EWS) to announce the possible occurrence of a hazard. The aim and objective of this paper are to investigate the possibility of implementing an EWS in a small-scale catchment and to develop a methodology for developing a hydrological prediction model based on an artificial neural network (ANN) as an essential part of the EWS. The methodology is implemented in the case study of the Slani Potok catchment, which is historically recognized as a hazard-prone area, by establishing continuous monitoring of meteorological and hydrological parameters to collect data for the training, validation, and evaluation of the prediction capabilities of the ANN model. The model is validated and evaluated by visual and common calculation approaches and a new evaluation for the assessment. This new evaluation is proposed based on the separation of the observed data into classes based on the mean data value and the percentages of classes above or below the mean data value as well as on the performance of the mean absolute error.

授权许可

Copyright © 2016 Ivana Sušanj et al. 2016
This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

图表

ANN predictive model development flowchart for the small catchments (green direction: forward movement in procedure; red direction: backward movement in procedure).

Artificial neuron node model (x1,x2,…,xm: input data; w1,w2,…,wm: weight coefficient; vk is the sum of products of the weight coefficients; φ is the activation function of the neuron node; ok is the response of the neuron node in the kth epoch of the calculation) [8].

ANN implementation procedure.

Multilayer perceptron (MLP) model [8].

Location of the investigated area according to the Republic of Croatia map, with an aerial photograph of the Slani Potok catchment area [33].

Slope map of the Slani Potok catchment area.

Schematized geologic map of the Vinodol valley with the Slani Potok catchment area [33].

Location of the monitoring points in the Slani Potok catchment.

Schematized ANN model structure.

Schematized ANN prediction model.

Graphical presentation of the target water level data and response water level data for the ANN model during validation: (a) S15, (b) S30, and (c) S60.

Graphical presentation of the target water level data and response water level data for the ANN model during validation: (a) S15, (b) S30, and (c) S60.

Graphical presentation of the target water level data and response water level data for the ANN model during validation: (a) S15, (b) S30, and (c) S60.

Graphical presentation of the target data and response of the ANN prediction model during evaluation: (a) S15, (b) S30, and (c) S60.

Graphical presentation of the target data and response of the ANN prediction model during evaluation: (a) S15, (b) S30, and (c) S60.

Graphical presentation of the target data and response of the ANN prediction model during evaluation: (a) S15, (b) S30, and (c) S60.

Evaluation classes of the target water level data.

通讯作者

Ivana Sušanj.Department of Hydrology and Geology, Faculty of Civil Engineering, University of Rijeka, 51000 Rijeka, Croatia, uniri.hr.isusanj@uniri.hr

推荐引用方式

Ivana Sušanj,Nevenka Ožanić,Ivan Marović. Methodology for Developing Hydrological Models Based on an Artificial Neural Network to Establish an Early Warning System in Small Catchments. Advances in Meteorology ,Vol.2016(2016)

您觉得这篇文章对您有帮助吗?
分享和收藏
2

是否收藏?

参考文献
[1] D. R. Legates, G. J. McCabe. (1999). Evaluating the use of ‘goodness-of-fit’ measures in hydrologic and hydroclimatic model validation. Water Resources Research.35(1):233-241. DOI: 10.1016/j.jhydrol.2008.08.023.
[2] S. Trajkovic, B. Todorović, M. Stanković. (2003). Forecasting of reference evapotranspiration by artificial neural networks. Journal of Irrigation and Drainage Engineering.129(6):454-457. DOI: 10.1016/j.jhydrol.2008.08.023.
[3] S. O. Haykin. (1994). Neural Networks: A Comprehensive Foundation. DOI: 10.1016/j.jhydrol.2008.08.023.
[4] K. P. Sudheer, P. C. Nayak, K. S. Ramasastri. (2003). Improving peak flow estimates in artificial neural network river flow models. Hydrological Processes.17(3):677-686. DOI: 10.1016/j.jhydrol.2008.08.023.
[5] P. J. Werbos. (1974). Beyond regression: new tools for prediction and analysis in the behavioural sciences [Ph.D. thesis]. DOI: 10.1016/j.jhydrol.2008.08.023.
[6] K. Smith. (2013). Environmental Hazards: Assessing Risk and Reducing Disaster. DOI: 10.1016/j.jhydrol.2008.08.023.
[7] S. O. Haykin. (2009). Neural Networks and Learning Machines. DOI: 10.1016/j.jhydrol.2008.08.023.
[8] D. E. Rumelhart, G. E. Hinton, R. J. Williams. (1986). Learning representations by back-propagating errors. Nature.323(6088):533-536. DOI: 10.1016/j.jhydrol.2008.08.023.
[9] A. Rabi, M. Hadzima-Nyarko, M. Šperac. (2015). Modelling river temperature from air temperature in the river Drava (Croatia). Hydrological Sciences Journal.60(9):1490-1507. DOI: 10.1016/j.jhydrol.2008.08.023.
[10] R. J. Abrahart, P. E. Kneale, L. M. See. (2004). Neural Networks for Hydrological Modelling. DOI: 10.1016/j.jhydrol.2008.08.023.
[11] D. Norbiato, M. Borga, S. Degli Esposti, E. Gaume. et al.(2008). Flash flood warning based on rainfall thresholds and soil moisture conditions: an assessment for gauged and ungauged basins. Journal of Hydrology.362(3-4):274-290. DOI: 10.1016/j.jhydrol.2008.08.023.
[12] K. Yano, A. Daido. (1965). Fundamental study on mud-flow. Bulletin of the Disaster Prevention Research Institute.14(2):69-83. DOI: 10.1016/j.jhydrol.2008.08.023.
[13] W. S. Cleveland. (1979). Robust locally weighted regression and smoothing scatterplots. Journal of the American Statistical Association.74(368):829-836. DOI: 10.1016/j.jhydrol.2008.08.023.
[14] M. Campolo, A. Soldati, P. Andreussi. (2003). Artificial neural network approach to flood forecasting in the river Arno. Hydrological Sciences Journal.48(3):381-398. DOI: 10.1016/j.jhydrol.2008.08.023.
[15] R. J. Abrahart, L. See. (2000). Comparing neural network and autoregressive moving average techniques for the provision of continuous river flow forecasts in two contrasting catchments. Hydrological Processes.14(11-12):2157-2172. DOI: 10.1016/j.jhydrol.2008.08.023.
[16] D. Aljinović, V. Jurak, M. Mileusnić, D. Slovenec. et al.(2010). The origin and composition of flysch deposits as an attribute to the excessive erosion of the Slani Potok valley (‘Salty Creek’), Croatia. Geologia Croatica.63(3):313-322. DOI: 10.1016/j.jhydrol.2008.08.023.
[17] C.-C. Young, W.-C. Liu, W.-L. Hsieh. (2015). Predicting the water level fluctuation in an Alpine lake using physically based, artificial neural network, and time series forecasting models. Mathematical Problems in Engineering.2015-11. DOI: 10.1016/j.jhydrol.2008.08.023.
[18] W. B. Chen, W. C. Liu. (2015). Water quality modelling in reservoirs using multivariate linear regression and two neural network models. Advances in Artificial Neural Systems.2015-12. DOI: 10.1016/j.jhydrol.2008.08.023.
[19] C. G. Collier. (2007). Flash flood forecasting: what are the limits of predictability?. Quarterly Journal of the Royal Meteorological Society.133(622):3-23. DOI: 10.1016/j.jhydrol.2008.08.023.
[20] T. Takahashi. (2014). Debris Flow: Mechanics, Prediction and Countermeasures. DOI: 10.1016/j.jhydrol.2008.08.023.
[21] H. R. Maier, G. C. Dandy. (2000). Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications. Environmental Modelling and Software.15(1):101-124. DOI: 10.1016/j.jhydrol.2008.08.023.
[22] D. C. Black, P. J. Wallbrink, P. W. Jordan. (2014). Towards best practice implementation and application of models for analysis of water resources management scenarios. Environmental Modelling and Software.52:136-148. DOI: 10.1016/j.jhydrol.2008.08.023.
[23] H. B. Demuth, M. H. Beale. (2004). Neural Network Toolbox, User's Guide. DOI: 10.1016/j.jhydrol.2008.08.023.
[24] D. W. Marquardt. (1963). An algorithm for least-squares estimation of nonlinear parameters. Journal of the Society for Industrial and Applied Mathematics.11(2):431-441. DOI: 10.1016/j.jhydrol.2008.08.023.
[25] M. R. Mustafa, R. B. Rezaur, H. Rahardjo, M. H. Isa. et al.(2015). Artificial neural network modeling for spatial and temporal variations of pore-water pressure responses to rainfall. Advances in Meteorology.2015-12. DOI: 10.1016/j.jhydrol.2008.08.023.
[26] A. M. Kaleth. (2008). Rainfal-runoff modelling using artificial neural networks (ANNs): modelling and understanding. Caspian Journal of Environmental Sciences.6(1):53-58. DOI: 10.1016/j.jhydrol.2008.08.023.
[27] K. Madsen, N. B. Nielsen, O. Tingleff. (2004). Methods for Nonlinear Least Squares Problems. DOI: 10.1016/j.jhydrol.2008.08.023.
[28] R. J. Abrahart, L. M. See. (2007). Neural network modelling of non-linear hydrological relationships. Hydrology and Earth System Sciences.11(5):1563-1579. DOI: 10.1016/j.jhydrol.2008.08.023.
[29] V. V. Krzhizhanovskaya, G. S. Shirshov, N. B. Melnikova. (2011). Flood early warning system: design, implementation and computational modules. Procedia Computer Science.4:106-115. DOI: 10.1016/j.jhydrol.2008.08.023.
[30] I. N. Daliakopoulos, P. Coulibaly, I. K. Tsanis. (2005). Groundwater level forecasting using artificial neural networks. Journal of Hydrology.309(1–4):229-240. DOI: 10.1016/j.jhydrol.2008.08.023.
[31] N. Do Hoai, K. Udo, A. Mano. (2011). Downscaling global weather forecast outputs using ANN for flood prediction. Journal of Applied Mathematics.2011-14. DOI: 10.1016/j.jhydrol.2008.08.023.
[32] C. W. Dawson, R. L. Wilby. (2001). Hydrological modelling using artificial neural networks. Progress in Physical Geography.25(1):80-108. DOI: 10.1016/j.jhydrol.2008.08.023.
[33] D. N. Moriasi, J. G. Arnold, M. W. Van Liew, R. L. Bingner. et al.(2007). Model evaluation guidelines for systematic quantification of accuracy in watershed simulations. American Society of Agricultural and Biological Engineers.50(3):885-900. DOI: 10.1016/j.jhydrol.2008.08.023.
[34] A. Colman, M. Davey. (1999). Prediction of summer temperature, rainfall and pressure in Europe from preceding winter North Atlantic Ocean temperature. International Journal of Climatology.19(5):513-536. DOI: 10.1016/j.jhydrol.2008.08.023.
文献评价指标
浏览 282次
下载全文 123次
评分次数 0次
用户评分 0.0分
分享 2次