Advertisement

Evaluating the efficiency of the neural network to other methods in predicting drought in arid and semi-arid regions of western Iran

  • E. Azizi
  • Mohsen TavakoliEmail author
  • H. Karimi
  • M. Faramarzi
Original Paper
  • 20 Downloads

Abstract

Drought as one of the natural phenomena and one of the greatest climate problems has been of central importance and investigated as a matter of necessity. In recent decades, Iran and especially Ilam province faced drought problem and this research was conducted with the aim of predicting drought in Ilam (semi-arid region) and Dehloran (arid area) stations, as well as evaluating the efficiency of the neural network. In this study, the data of temperature, precipitation, relative humidity, wind speed, and monthly sunny hours in the period of 1983–2013 were used to calculate the standardized precipitation index (SPI) and moving average of 3, 5, and 7 years. Also, artificial neural network was employed for monitoring the drought in Ilam (semi-arid region) and Dehloran (arid region) stations. Accordingly, the artificial neural network (ANN) was modeled after determining the best input composition and the best number of data using the backpropagation algorithm and C-Sharp programming language. Then, the possible future drought was predicted in both stations. The architecture of network was optimized in form of 5-30-1, 5 neurons in input layer (precipitation, temperature, relative humidity, wind speed, and sunny hours); 30 neurons in the hidden layer and a neuron in the output layer (SPI) after training and repeated errors. In order to evaluate ANN performance in climate elements simulation, four designed models were investigated using different learning functions and the number of variously hidden neurons and the error was calculated using MAE, RMSE, and R2 indices. The results showed that in the stations, bipolar sigmoid function pattern and updating weights by the method of the moment were introduced as the optimal model, due to the lowest error rate and highest correlation between input and output data. Then, outputs of the program were compared with observed SPI. The results of statistic method and output of network showed that the stations entered a prolonged drought phase from 1996–1997 to 2012. Although the stations showed short periods of wet year, the trend of these droughts has continued so far, with the difference that the severity of droughts in Dehloran station (Arid region) was higher and in this long period of drought, short, 7-, 5-, and 3-year droughts occurred and it was completely consistent with the definition of drought.

Keywords

ANN SPI Moving average Ilam Iran 

References

  1. Al Shamisi MH, Assi AH, Hejase HAN (2011) Using MATLAB to develop artificial neural network models for predicting global solar radiation in Al Ain City – UAE. Engineering Education and Research Using MATLAB, Edited By Dr. Ali Assi, InTech, UAE.  https://doi.org/10.5772/25213 Google Scholar
  2. Ali Z, Hussain I, Faisal M et al (2017a) Forecasting drought using multilayer perceptron artificial neural network model, Adv Meteo, pp 9Google Scholar
  3. Ali Z, Hussain I, Faisal M, Nazir HM, Hussain T, Shad MY, Mohamd Shoukry A, Hussain Gani S (2017b) Forecasting drought using multilayer perceptron artificial neural network model. Adv Meteorol 2017:1–9.  https://doi.org/10.1155/2017/5681308 CrossRefGoogle Scholar
  4. American Meteorological Society (1997) Meteorological drought-policy statement. Bull Am Meteorol Soc 78:847–849CrossRefGoogle Scholar
  5. Andreu J, Haro D, Solera A et al (2015) Drought indicators: monitoring, forecasting and early warning at the case study scale, In DROUGHT-R&SPI (Fostering European Drought Research and Science-Policy Interfacing), Collaborative Project funded by the European Commission under the FP7 Cooperation Work Programme: Theme 6: Environment (Grant agreement no: 282769), pp 53Google Scholar
  6. Aqil M, Ichiro K, Akira Y et al (2007) A comparative study of artificial neural networks and neuro-fuzzy in continuous modeling of the daily and hourly behaviour of runof. J Hydrodyn 337(1-2):22–34CrossRefGoogle Scholar
  7. Bacanli UG, Firat M, Dikbas F (2009) Adaptive neuro-fuzzy inference system for drought forecasting. Stoch Env Res Risk A 23(8):1143–1154CrossRefGoogle Scholar
  8. Bhalme HN, Mooley DA (1980) Large-scale droughts/ floods and monsoon circulation. Mon Weather Rev 108(8):1197–1211CrossRefGoogle Scholar
  9. Choubin B, Malekian A, Golshan M (2016) Application of several data-driven techniques to predict a standardized precipitation index. Atmósfera 29(2):121–128CrossRefGoogle Scholar
  10. Dastorani MT, Afkhami H (2011) Evaluation of the application of artificial neural networks on drought prediction in Yazd (Iran). Journal of Desert 16(1):39–49Google Scholar
  11. Deo RC, Şahin M (2015) Application of the extreme learning machine algorithm for the prediction of monthly Effective Drought Index in eastern Australia. Atmos Res 153:512–525CrossRefGoogle Scholar
  12. Esfahanian E, Nejadhashemi AP, Abouali M (2016) Defining drought in the context of stream health. Ecol Eng 94:668–681CrossRefGoogle Scholar
  13. Guttman NB (1999) Accepting the standardized precipitation index: a calculation algorithmm. J Am Water Resour Assoc 35(2):311–322CrossRefGoogle Scholar
  14. Hamed Y, Hadji R, Redhaounia B, Zighmi K, Bâali F, El Gayar A (2018) Climate impact on surface and groundwater in North Africa: a global synthesis of findings and recommendations, Euro Mediterr J Environ Integr, 3(1).  https://doi.org/10.1007/s41207-018-0067-8
  15. Haykin M, Kosaka M, Yajima H et al (1994) Application of neural network to technical analysis of stock market prediction. Stud Inform Control 7(3):111–120Google Scholar
  16. Huang YF, Ang JT, Tiong YJ, Mirzaei M, Amin MZM (2016) Drought forecasting using SPI and EDI under RCP-8.5 climate change scenarios for Langat River Basin, Malaysia. Procedia Engineer 154:710–717CrossRefGoogle Scholar
  17. IPCC (2012) Summary for policymakers: a special report of working groups I and II of the intergovernmental panel on climate change. In: Field, C.B., et al. (Eds.), Managing the Risks of Extreme Events and Disasters to Advance Climate Change Adaptation, Cambridge University Press, Cambridge, UKGoogle Scholar
  18. Kalogirou SA (2001) Artificial neural networks in renewable energy systems applications: A review. Renew Sust Energ Rev 5(5):373–401CrossRefGoogle Scholar
  19. Khadr M (2016) Forecasting of meteorological drought using hidden Markov model (case study: the upper Blue Nile river basin, Ethiopia). Ain Shams Eng J 7(1):47–56CrossRefGoogle Scholar
  20. Khan MMH, Muhammad NS, El-Shafie A (2018) Wavelet-ANN versus ANN-based model for hydrometeorological drought forecasting. Water 10:998CrossRefGoogle Scholar
  21. Kim TW, Valdes JB (2003) Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. J Hydrol Eng 8(6):319–328CrossRefGoogle Scholar
  22. Kumar R, Aggarwal RK, Sharma JD (2013) Energy analysis of a building using artificial neural network: a review. Energ Buildings 65:352–358CrossRefGoogle Scholar
  23. Lloyd-Hughes B, Saunders MA (2002) A drought climatology for Europe. Int J Climatol 22(13):1571–1592CrossRefGoogle Scholar
  24. McAlpine CA, Syktus J, Ryan JG et al (2009) A continent under stress: interactions, feedbacks and risks associated with impact of modified land cover on Australia’s climate. Glob Chang Biol 15(9):2206–2223CrossRefGoogle Scholar
  25. McKee TB, Doesken NJ, Kleist J (1993a) The relationship of drought frequency and duration to time scales, American Meteorological Society, 8th Conference on Applied Climatology, 179-184.Google Scholar
  26. McKee TB, Doesken NJ, Kleist J (1993b) The relationship of drought frequency and duration to time scales, Proceedings of the 8th Conference on Applied Climatology, 17:179-183.Google Scholar
  27. Mishra AK, Desai MR (2005) Drought forecasting using stochastic models. Stoch Env Res Risk A 19(5):326–339CrossRefGoogle Scholar
  28. Mishra AK, Singh VP (2010) A review of drought concepts. J Hydrol 391(1–2):202–216CrossRefGoogle Scholar
  29. Mishra AK, Desai VR, Singh VP (2007) Drought forecasting using a hybrid stochastic and neural network model. J Hydrol Eng 12(6):626–638CrossRefGoogle Scholar
  30. Mishra AK, Singh VP, Desai VR (2009) Drought characterization: a probabilistic approach. Stoch Env Res Risk A 23(1):41–55CrossRefGoogle Scholar
  31. Mokadem N, Demdoum A, Hamed Y, Bouri S, Hadji R, Boyce A, Laouar R, Sâad A (2015) Hydrogeochemical and stable isotope data of groundwater of a multi-aquifer system: Northern Gafsa basin - Central Tunisia. J Afr Earth Sci.  https://doi.org/10.1016/j.jafrearsci.2015.11.010 CrossRefGoogle Scholar
  32. Morid S, Smakhtin V, Moghaddasi M (2006) Comparison of seven meteorological indices for drought monitoring in Iran. Int J Climatol 26:971–985CrossRefGoogle Scholar
  33. Morid S, Smakhtin V, Bagherzadeh K (2007) Drought forecasting using artificial neural networks and time series of drought indices. Int J Climatol 27(15):2103–2111CrossRefGoogle Scholar
  34. Mpelasoka F, Hennessy K, Jones R, Bates B (2008) Comparison of suitable drought indices for climate change impacts assessment over Australia towards resource management. Int J Climatol 28(10):1283–1292CrossRefGoogle Scholar
  35. Najah A, El-Shafie A, Karim OA, El-Shafie AH (2013) Application of artificial neural networks for water quality prediction. Neural Comput & Applic 22(1):187–201CrossRefGoogle Scholar
  36. Nasir MFM, Abdul Zali M, Juahir H et al (2012) Application of receptor models on water quality data in source apportionment in Kuantan River Basin. J Environ Health Sci Eng 9(1):18CrossRefGoogle Scholar
  37. Palmer WC (1968) Keeping track of crop moisture conditions, nationwide: the new crop moisture index. Weatherwise 21(4):156–161CrossRefGoogle Scholar
  38. Paulo AA, Ferreira E, Coelho C, Pereira LS (2005) Drought class transition analysis through Markov and Log linear models, an approach to early warning. Agric Water Manag 77(1-3):59–81CrossRefGoogle Scholar
  39. Richard R, Heim J (2002) A review of twentieth-century drought indices used in the United States. B Am Meteorol Soc 83:1149–1165Google Scholar
  40. Riebsame WE, Changnon SA, Karl TR (1991) Drought and natural resources management in the United States, impacts and implications of the 1987-89 drought, Westview Press Inc, pp 174.Google Scholar
  41. Safavi HR, Malek Ahmadi K (2015) Prediction and assessment of drought effects on surface water quality using artificial neural networks: case study of Zayandehrud River, Iran. J Environ Health Sci Eng 13(68):1–14Google Scholar
  42. Shafer BA, Dezman LE (1982) Development of a surface water supply index (swsi) to assess the severity of drought conditions in snowpack runoff areas, 50th Annual Western Snow Conference, 50:164–175Google Scholar
  43. Shamsipour AA, Alavipanah SK, Mohammadi H (2010) Efficiency of vegetation and thermal indices of NOAAAVHRR Satellite in ecological drought analysis of Kashan Region. Iranian Journal of Range and Desert Research 3(40):445–465Google Scholar
  44. Sheffield J, Wood EF (2012) Drought: past problems and future scenarios, Earthscan, London, Washington, NDMC, Types of Drought, http://drought.unl.edu/DroughtBasics/ CrossRefGoogle Scholar
  45. Sholahudin S, Han H (2016) Simplified dynamic neural network model to predict heating load of a building using Taguchi method. Energy 115(3):1672–1678CrossRefGoogle Scholar
  46. Stahl K, Van Lanen H (2014) Guidelines for monitoring and early warning of drought in Europe, DROUGHT-R &SPI, pp 24.Google Scholar
  47. Van Rooy M (1965) A rainfall anomaly index independent of time and space. Notos 14:43–48Google Scholar
  48. Vicente-Serrano SM, Beguer’ıa S, L’opez-Moreno JI (2010) A multiscalar drought index sensitive to global warming: the standardized precipitation evapotranspiration index. J Clim 23(7):1696–1718CrossRefGoogle Scholar
  49. Vyas SS, Bhattacharya BK, Nigam R (2015) A combined deficit index for regional agricultural drought assessment over semi-arid tract of India using geostationary meteorological satellite data. Int J Appl Earth Obs 39:28–39CrossRefGoogle Scholar
  50. Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE T Image Process 13(4):600–612CrossRefGoogle Scholar
  51. Weghorst K (1996) The reclamation drought index: guidelines and practical applications, proceedings of the North American Water and Environment Congress & Destructive Water, 637– 642.Google Scholar
  52. Wilhite DA, Hayes MJ, Knutson C, Smith KH (2000) Planning for drought: moving from crisis to risk management. J Am Water Res Assoc 36(4):697–710CrossRefGoogle Scholar
  53. Zare AH (2012) Evaluation of multivariate linear regression and artificial neural networks in prediction of water quality parameters. J Environ Health Sci 12:40Google Scholar
  54. Zulifqar A, Hussain I, Faisal M et al (2017) Forecasting drought using multilayer perceptron artificial neural network model. Adv Meteorol 2:9Google Scholar

Copyright information

© Saudi Society for Geosciences 2019

Authors and Affiliations

  • E. Azizi
    • 1
  • Mohsen Tavakoli
    • 1
    Email author
  • H. Karimi
    • 1
  • M. Faramarzi
    • 1
  1. 1.Natural Resources Dept., Agriculture FacultyIlam UniversityIlamIran

Personalised recommendations