Application of Statistical, Fuzzy and Perceptron Neural Networks in Drought Forecasting (Case Study: Gonbad-e Kavous Station)

آب و خاک

Article 12, Volume 30, Issue 1 - Serial Number 45, March 2016, Pages 247-259   

Document Type: Research Article

DOI: 10.22067/jsw.v30i1.37304

Authors

S.M. Hosseini-Moghari^* ; Sh. Araghinejad

University of Tehran

Abstract

Introduction: Due to economic, social, and environmental perplexities associated with drought, it is considered as one of the most complex natural hazards. To investigate the beginning along with analyzing the direct impacts of drought; the significance of drought monitoring must be highlighted. Regarding drought management and its consequences alleviation, drought forecasting must be taken into account (11). The current research employed multi-layer perceptron (MLP), adaptive neuro-fuzzy inference system (ANFIS), radial basis function (RBF) and general regression neural network (GRNN). It is interesting to note that, there has not been any record of applying GRNN in drought forecasting.
Materials and Methods: Throughout this paper, Standard Precipitation Index (SPI) was the basis of drought forecasting. To do so, the precipitation data of Gonbad Kavous station during the period of 1972-73 to 2006-07 were used. To provide short-term, mid-term, and long-term drought analysis; SPI for 1, 3, 6, 9, 12, and 24 months was evaluated. SPI evaluation benefited from four statistical distributions, namely, Gamma, Normal, Log-normal, and Weibull along with Kolmogrov-Smirnov (K-S) test. Later, to compare the capabilities of four utilized neural networks for drought forecasting; MLP, ANFIS, RBF, and GRNN were applied. MLP as a multi-layer network, which has a sigmoid activation function in hidden layer plus linear function in output layer, can be considered as a powerful regressive tool. ANFIS besides adaptive neuro networks, employed fuzzy logic. RBF, the foundation of radial basis networks, is a three-layer network with Gaussian function in its hidden layer, and a linear function in the output layer. GRNN is another type of RBF which is used for radial basis regressive problems. The performance criteria of the research were as follows: Correlation (R2), Root Mean Square Error (RMSE), Mean Absolute Error (MAE).
Results Discussion: According to statistical distribution analysis, the optimal precipitation distribution in many cases was not Gamma distribution. The various time-scales of SPI revealed that, at least in 50% of the events, Gamma was not the selected distribution. Throughout the drought forecasting on the basis of SPI time-series with four aforementioned networks, 80% of the data was allocated to the training process whilst the rest of them considered for the test process. The proper parameters of the networks were chosen via trial and error. Moreover, Cross-validation was used to overcome the over-estimation. The results revealed that the long-term SPIs outdid the others. Performance of the networks promoted with increases in time scales of SPI. In other words, the performance criteria improved proportional to the increases in the time-scales. Based on the Table 3, the least and best performance were contributed to SPI1 and SPI24, respectively. In this regard, R2 of MLP for observed and estimated values of SPI vitiated from 0.009 to 0.949. Similar to MLP, correlation of ANFIS, RBF, and GRNN increased from 0.021 to 0.925, 0.263 to 0.953, and 0.210 to 0.955. Comparison of observed and estimated mean values via Z test indicated that null hypothesis of equal mean observed and estimated values was only rejected for SPI1 with α=0.01. Hence, except SPI1 forecasting, the all other scenarios have remained the mean of observed time series which highlighted the robustness of artificial intelligence in drought forecasting.
Conclusion: The main objective of the ongoing research was monitoring and forecasting of drought based upon various time scales of SPI. In doing so, the precipitation data of Gonbad Kavous station during the period of 1972-73 to 2006-07 were used. Based on K-S test, the best statistical distribution test for different time scales of SPI evaluation was chosen, and then, the SPI was calculated based on the most fitted distribution. After generating the time-series, MLP, ANFIS, RBF, and GRNN were applied for drought forecasting. According to the findings, the lowest performance of forecasting belonged to SPI1 where its RBF’s best performance for R2, RMSE, and MAE were 0.263, 0.806, and 0.989. Furthermore, increases in SPI time-scale promoted the performance of networks. Thus, the worst and best performance belonged to SPI1 and SPI24, respectively. Among the utilized models, ANFIS stood superior to the others, and GRNN followed up after it.

Keywords

Artificial Intelligence; Generalized regression neural network; Radial basis functions; Standardized Precipitation Index

References

Alipour H. 2011. Effects of drought on socio-economic status of farmers: A case study on the Nehbandans wheat farmers. Watershed Management Research (Pajouhesh & Sazandegi), 99: 113-125. (In Persian with English abstract)

2- Araghinejad S. 2014. Data-driven Modeling: Using MATLAB in Water Resources and Environmental Engineering. Springer.

3- Bacanli U.G., Firat M., and Dikbas F. 2009. Adaptive neuro-fuzzy inference system for drought forecasting. Stochastic Environmental Research and Risk Assessment, 23(8): 1143-1154.

4- Behzadi J. 2010. Drought Monitoring and Analysis of Its Characteristic in Golestan Province. M A K A N Geography and Land Management, 1(1): 21-36.

5- Belayneh A., and Adamowski J. 2012. Standard precipitation index drought forecasting using neural networks, wavelet neural networks, and support vector regression. Applied Computational Intelligence and Soft Computing, 6: 1-13.

6- Chu P.S., Nash A.J., and Porter F.Y. 1993. Diagnostic studies of two contrasting rainfall episodes in Hawaii: Dry 1981 and wet 1982. Journal of climate, 6(7): 1457-1462.

7- Durdu Ö.F. 2010. Application of linear stochastic models for drought forecasting in the Büyük Menderes river basin, western Turkey. Stochastic Environmental Research and Risk Assessment, 24(8): 1145-1162.

8- Ebrahimi R., Zahraie B., and Nasseri M. 2010. Mid-term Prediction of Meteorological Drought Using Fuzzy Inference Systems. Water and Wastewater, 22(78): 112-125. (in Persian with English abstract)

9- Eivazi M., Mosaedi A., and Dehghani, A.A. 2009. Comparison of different approaches for predicting SPI. Journal of Water and Soil Conservation, 16(2): 145-167. (in Persian with English abstract)

10- Ghasemi M., Eslamian S.S, and Soltani S. 2008. Monitoring and Regionalization of Meteorological Drought in Karkhe Watershed Using Standardized Precipitation Index and Precipitation Deciles. Agricultural research: water, soil and plants in agriculture, 8(3): 23-35. (in Persian with English abstract)

11- Ghamghami M., and Bazrafshan J. 2011. Prediction of meteorological drought conditions in Iran using Markov chain model. Journal of Water and Soil Resources Conservation, 1(3):1-12. (in Persian with English abstract)

12- Gocic M., and Trajkovic S. 2013. Analysis of precipitation and drought data in Serbia over the period 1980–2010. Journal of Hydrology, 494: 32-42.

13- Guttman N.B. 1999. Accepting the Standardized Precipitation Index: a calculation algorithm. Journal of the American Water Resources Association, 35(2): 311-322.

14- Hassanzadeh Y., Abdi Kordani A., and Hassanzadeh A. 2011. Drought Forecasting Using Genetic Algorithm and Conjoined Model of Neural Network-Wavelet. Water and Wastewater, 23(83): 59-48. (in Persian with English abstract)

15- Hejabi S. 2010. An Adaptive Study of Meteorological Drought Forecasting Methods in Dry and Wet Climates of Iran. Master Thesis, University of Tehran. (in Persian with English abstract)

16- Hejabi S., and Bazrafshan J. 2012. Evaluation of several model in forecasting time series of standardized precipitation index. Journal of Water Research in Agriculture, 27(3): 429-444.

17- Hosseini-Moghari S.M., and Araghinejad S. 2015. Monthly and seasonal drought forecasting using statistical neural networks. Environmental Earth Science, 74(1): 397-412.

18- Jang J.S. 1993. Anfis: adaptive-network-based fuzzy inference systems. Journal of IEEE Transactions on, 23(3): 665–685.

19- Kampragou E., Apostolaki S., Manoli E., Froebrich j., and Assimacopoulos D. 2011. Towards the harmonization of water-related policies for managing drought risks across the EU. Environmental science and policy, 14(7): 815-824.

20- Karamouz M., and Araghinejad S. 2009. Advanced Hydrology. Amirkabir University Press. Tehran.

21- McKee T.B., Doesken N.J., and Kleist J. 1993. The relationship of drought frequency and duration to time scales. In Proceedings of the 8th Conference on Applied Climatology, 17(22): 179-183.

22- McKee T.B., Doesken N.J., and Kleist J. 1995. Drought monitoring with multiple time scales, Ninth Conference on Applied Climatology, American Meteorological Society, Boston, Massachusetts, 233-236.

23- Mishra A.K., and Desai V.R. 2005. Drought forecasting using stochastic models. Stochastic Environmental Research and Risk Assessment, 19(5): 326-339.

24- Mishra A.K., and Desai,V.R. 2006. Drought forecasting using feed-forward recursive neural network. Ecological Modelling, 198(1): 127-138.

25- Mishra A.K., Desa V.R., and Singh V.P. 2007. Drought Forecasting Using a Hybrid Stochastic and Neural Network Model. Journal of Hydrologic Engineering, 12(6): 626–638.

26- Morid S., Smakhtin V., and Bagherzadeh K. 2007. Drought forecasting using artificial neural networks and time series of drought indices. International Journal of Climatology, 27(15): 2103-2111.

27- Palmer W.C. 1965. Meteorological drought. Washington, DC, USA: US Department of Commerce, Weather Bureau.

28- Rezaeian-Zadeh M., and Tabari H. 2012. MLP-based drought forecasting in different climatic regions. Theoretical and Applied Climatology, 109(3-4): 407-414.

29- Specht D.F. 1991. A general regression neural network, Neural Networks, IEEE Transactions on, 2(6):568-576.

30- Thom H.C.S. 1958. A note on gamma distribution. Monthly Weather Review, 86: 117–122.

31- Vafakhah M., and Bashari M. 2011. Probability study of hydrological drought and wet period’s occurrence using markov Chain in Kashafrood Watershed. Watershed Management Research (Pajouhesh & Sazandegi), 25(1): 1-9. (In Persian with English abstract)

32- Wilhite D.A., and Pulwarty R.S. 2005. Drought and water crises: lessons learned and the road ahead. Drought and water crises.

33- Wilhite D.A., Hayes M.J., Knutson C., and Smith K.H. 2000. Planning for Drought: Moving from Crisis to Risk Management. Journal of the American Water Resources Association, 36(4): 697-710.

34- Wilhite D.A., Svoboda M.D., and Hayes M.J. 2007. Understanding the complex impacts of drought: a key to enhancing drought mitigation and preparedness. Water Resources Management, 21(5): 763-774.

35- Zare-Zade-Mehrizi M., and Morid S. 2011. Application of Reservoir Level and Meteorological Indices for Drought Monitoring (Case Study: Zayandeh Rud Water System). Iranian Journal of Soil and Water Reseach, 1(42): 19-26.