Comparative Evaluation of Statistical Models and Artificial Intelligence for Drought Prediction in Isfahan Synoptic Station

Document Type : Original Article

Authors

1 PhD Student in Desert Management and Control, Department of Desertification, Faculty of Natural Resources and Earth Sciences, University of Kashan, Kashan, Iran.

2 Associate Professor, Department of Desertification, Faculty of Natural Resources and Earth Sciences, University of Kashan, Kashan, Iran.

3 Assistant Professor, Department of Statistics, Faculty of Mathematical Sciences, University of Kashan, Kashan, Iran.

4 Associate Professor, Department of New Energy and Environment, Faculty of Modern Science and Technology, University of Tehran, Tehran, Iran.

5 Assistant Professor, Department of Watershed Management, Faculty of Natural Resources and Earth Sciences, University of Kashan, Kashan, Iran.

Abstract

Meteorological drought is a complex natural disaster that occurs everywhere in the world. Predicting the occurrence and severity of drought can be effective in managing water crises and their impacts. The purpose of the current study is to select the most appropriate model from statistical models and artificial intelligence (artificial neural networks) to predict drought in Isfahan synoptic station during the span period of 1990-1920 using the Z-Score index (ZSI). In this study, the capability and efficiency of the SARIMA stochastic linear model and three advanced learning machine models of the Feedforward Neural Networks (FNNs), Multi-layer Perceptron (MLP), and Extreme Learning Machines (ELM) were evaluated based on Root Mean Squared Error (RMSE), Mean Absolute Square Error (MASE) and Mean Absolute Error (MAE). The results showed that among the many models made, the Feedforward Neural Networks (FNNs) model with RMSE of 0.33, MASE of 0.02, and MAE of 0.22 were selected as the best model. Using the superior model, precipitation for the period of 2025-2021 of Isfahan synoptic station was predicted, then based on the ZSI drought index, drought intensity of forecast precipitation data in 3, 6, 9, 12-month time scales, 18, and 24 months was calculated. The results of drought severity predicting showed that severe drought in 3 and 6 month time scales in 2021 and 2023 and in 9 and 18 month time scales in 2024, moderate drought in all time scales in 2024, and weak droughts occurred at the 3, 6, and 24-month time scales in 2024 and 2025, respectively. Overall, the results showed that the use of feed neural network model was more efficient. Since predicting drought at all time scales can reveals drought more accurately, this predicting in turn to facilitate the development of water resources management strategies for management of drought is effective.

Keywords

References

  1. Adnan, S., Ullah, K., Li, S., Gao, S., Hayat Khan, A., & Mahmood, R. (2017). Comparison of Various Drought Indices to Monitor Drought Status in Pakistan, Climate Dynamics, 51(5/6), 1885-1899.
  2. Afkhami, H., Dastorani, M. T., Malekinejad, H., & Mobin, M. H. (2010). Effects of Climatic Factors on Accuracy of ANN-Based Drought Prediction in Yazd Area. Agriculture and Natural Resources, 14(51), 157-169. (in Farsi)
  3. Alizadeh, S., & Toosi, A. (2008).Development of a Model for Monitoring and Forecasting Drought (Case Study: Khorasan Razavi Province). Water and Soil, 22(1), 223-235. (in Farsi)
  4. Alsumaiei, A. A., & Alrashidi, M. S. (2020). Hydrometeorological Drought Forecasting in Hyper-Arid Climates Using Nonlinearautoregressive Neural Networks. Water, 12(9), 2611.
  5. Arjmandi Harat, Z., & Asadi Zarch, M. A. (2021). Performance Analysis of NAR Model for Short and Long-Term Drought Forecasting in Arid Regions, Desert Management, 9(2), 103-120. (in Farsi)
  6. ASCE Task Committee on Application of Artificial Neural Networks in Hydrology. (2000). Artificial Neural Networks in Hydrology. I: Preliminary Concepts, Hydrologic Engineering, 5(2), 124–137.
  7. Biranvand, S., & Sahraeian, K. (2018). Types of Neural Networks and Their Applications, 3rd International Conference on Management and Humanities Research in Iran, Non-Governmental Organizations and Centers, Modbar Management Research Institute, 3, University of Tehran. (in Farsi)
  8. Boustani, , Ulke A., (2020). Investigation of Meteorological Drought Indices for Environmental Assessment of Yesilirmak Region, Environmental Treatment Techniques, 8(1), 374-381.
  9. Box, G., Jenkins, G. M., & Reinsel, G. C. (1994). Time Series Analysis, Forecasting and Control (3rd edn). Prentice-Hall. Englewood Cliffs. NJ.
  10. Byzedi, M., Siosemardeh, M., & Asragah, A. (2017). Prediction and Analysis of Meteorological Drought Based on Time Series (Case Study: Salmas Watershed). Environmental and Water Engineering, 2(4), 346-359. (in Farsi)
  11. Deo, R. C., & Sahin, M. (2016). An Extreme Learning Machine Model for The Simulation of Monthly Mean Streamflow Water Level in Eastern Queensland, Environmental Monitoring and Assessment, 188(2).
  12. Deo, C., & Sahin, M. (2015). Application of The Extreme Learning Machine Algorithm for the Prediction of Monthly Effective Drought Index in Eastern Australia, Atmospheric Research, 153, 512-525.
  13. Eivazi, M., Mosaedi, A., & Dehghani, A. A. (2009). Comparison of Different Approaches for Predicting SPI. Water and Soil Conservation, 16(2), 145-167. (in Farsi)
  14. Fallah Ghalhari, GH., Bayatani, A. F., & Fahiminezhad, E. (2015). Comparing the Forecasting Accuracy of the Box–Jenkins Models in Modeling Seasonal Precipitation (Case Study: The South of Kerman Province, Iran). Applied Environmental and Biological Sciences, 5(12) 64-78.
  15. M. (2013). Climatic Hazards in Iran. Tehran, SAMT Press. (in Farsi)
  16. Faris, H., Hassonah, M. A., Al-Zoubi, A. M., & Mirjalili, S. (2018). A Multi-Verse Optimizer Approach for Feature Selection and Optimizing SVM Parameters Based on A Robust System Architecture, Neural Computing and Applications, 30(8), 2355–2369.
  17. Flood, I., & Kartam, N. (1994). Neural Networks in Civil Engineering I: Principles and Understanding. Computing in Civil Engineering, 8(2), 131–148.
  18. Fung, K. F., Huang, Y. F., Koo, C. H., & Soh, Y. W. (2020). Drought Forecasting: A Review of Modelling Approaches 2007–2017, Water and Climate Change, 11(3), 771–799.
  19. Haltiner, G. J., & Williams, R. T. (1989). Numerical Prediction and Dynamic Eteorology, 2nd Eddition. New York, Wiley & Sons.
  20. Han, P., Wang, P. X., Zhang, S. Y., & Zhu, D. (2010). Drought Forecasting Based on the Remote Sensing Data Using ARIMA Models. Mathematical and Computer Modelling, 51, 1398-1403.
  21. Hejazizadeh, Z., & Javizadeh, S. (2017). Introduction to Drought and its Indicators. Tehran, Samt Press. (in Farsi)
  22. Hosseini-Moghari, S. M., & Araghinejad, Sh. (2016). Application of Statistical, Fuzzy and Perceptron Neural Networks in Drought Forecasting (Case Study: Gonbad-e Kavous Station), Water and Soil, 30(1), 247-259. (in Farsi)
  23. Huang, G., Huang, G. B., Song, S., & You, K. (2015). Trends in Extreme Learning Machines: A Review. International Neural Network Society, 61, 32–48.
  24. Hyndman, R. J., & Koehler. A. B. (2006). Another Look at Measures of Forecast Accuracy. Forecasting, 22, 679–688.
  25. Kardavani, P. (2001). Drought and ways to deal with it in Iran. Tehran, University of Tehran (In Farsi).
  26. Kaur, A., & Sandeep, K. S. (2020). Deep Learning Based Drought Assessment and Prediction Framework, Ecological Informatics, 57(9).
  27. Kaviani, M. R., & Alikhani, B. (2016). Basics of meteorology. Tehran, Samt Press. (in Farsi)
  28. Khalili, K., Hesari, B. (2004). Prediction of Drought Trend Using Time Series Statistical Models (Case Study of Urmia Synoptic Station). 1th Water Resources Management Conference, Tehran. (in Farsi)
  29. Khorrami, M., A. Bozorgnia. 2007. Analysis of Time Series with MINITAB Software 14. Sokhan Gostar Publications, 336. (in Farsi)
  30. Khosravi, I., Akhondzadeh, M., & Khoshgoftaar, M. (2015). Modeling and Predicting the Drought Indices Time Series Using Machine Learning Methods in Order to Managing Hazards (Case Study: Eastern District of Isfahan), Environmental Management Hazards, 2(1), 51-65. (in Farsi)
  31. Kisi, O., Karahan, M., & Sen, Z. (2006). River Suspended Sediment Modeling Using Fuzzy Logic Approach. Hydrological Processes, 20(2), 4351-4362.
  32. Malekian, A., Dehbozorgi, M., & Ehsani, A. H. (2015). Evaluation the Efficiency of Using Artificial Neural Networks in Predicting Meteorological Droughts in North-West of Iran. Researches in Geographical Sciences, 15(36), 139-156. (in Farsi)
  33. Malekian, A., Dehbozorgi, M., Ehsani, A., & Keshtkar, A. (2014). Application of Artificial Neural Networks in Simulating and Forecasting of Meteorological Drought Decile Percentage Index (Case Study: Sistan & Balouchestan Province), Range and Watershed Management, 67(1), 127-139.
  34. Masoumpour Samakosh, J., Jalilian, A., & Yari, E. (2016). The Analysis of Seasonal Precipitation Time Series in Iran. Physical Geography Research, 49(3), 457-475. (in Farsi)
  35. Meteorological Organization of the Country. (2021). Meteorological of Isfahan Province, 26-149. (in Farsi)
  36. Mirzaei, A. A., & Sabe, Gh. A. (2011). Water Engineering Specialized Software. Kian Academic Publication, Tehran, Iran. (in Farsi)
  37. Mishra, K., & Desai, V. R. (2006). Drought Forecasting Using Feed-Forward Recursive Neural Network, Ecological Modelling, 198(1), 127-138.
  38. Mishra, K., & Desai, V. R. (2005). Drought Forecasting Using Stochastic Models. Stoch Environ Res Risk Assess, 19(2), 326-339.
  39. Moharrampour, M., Mehrabi, A., Hajikandi, H., Sohrabi, S., & Vakili, J. (2013). Comparison of Support Vector Machines (SVM) and Autoregressive Integrated Moving Average (ARIMA) in Daily Flow Forecasting. River Engineering, 1(1), 1–8.
  40. Nazari Pouya, H., Khosroshahi, M. (2013). Determining the Most Appropriate Meteorological Drought Index for Evaluation of Drought in Hamedan Province, Range and Desert Research, 20(4), 625-633. (in Farsi)
  41. Niromand, H., & Bozorgnia, S. A. (2002). Introduction to Time Series Analysis (Edition 2). Translation. Ferdowsi University Press, Mashhad, Iran. (in Farsi)
  42. Niromand, H., & Bozorgnia, S. A. (2011). Time Series (Edition 5). Payam Noor University Press, Tehran. (in Farsi)
  43. Nourani, V., Alami, M. T., & Aminfar, M. H. (2009). A Combined Neural-Wavelet Model for Prediction of Ligvanchai Watershed Precipitation. Engineering Applications of Artificial Intelligence, 22(2), 466–472.
  44. Pahlavanravi, A., & Ghasemi, H. (2008). Estimation of Wet and Drought Periods Using Z-Score Index in Zabol, International Water Crisis Conference, Ministry of Science, Research and Technology, March 20-22, First Course, Zabol University.
  45. Rahdan, H., Moradi, H. R., & Sharifi, K. M. (2015). Comparison of the Efficiency of Some Meteorological Indicators to Determine the Drought in Isfahan, 4th National Conference on Health, Environment and Sustainable Development, Islamic Azad University, Bandar Abbas Branch. (in Farsi)
  46. Rostami, M., Pahlavanravi, A., & Moghaddamnia, A. (2016). Comparison of Artificial Neural Network Models and Adaptive Neuro-Fuzzy Inference System in Predicting the Drought Mond Basin of Fars Province. Natural Environmental Hazards, 4(6), 21-32. (in Farsi)
  47. Rumelhart, D. E., & McClelland, L. (1986). Parallel Distributed Processing: Exploratins in the Microstructure of Cognition, V. 1: Foundations. London, The MIT Press.
  48. Saadati, S., Soltani, S., & eslamian, S. (2009). Statistical Analysis of Return Period of Drought Conditions in Isfahan Province Using the Standardized Precipitation Index, Range and Watershed Management, 62(2), 257-270. (in Farsi)
  49. Sadeghian, M., Karami, H., & Mousavi, S. F. (2018). Selection of a Proper Model to Predict Monthly Drought in Semnan Using Weather Data and Linear and Nonlinear Models, Water and Soil Science, 21(4). (in Farsi)
  50. Sánchez-Monedero, J., Salcedo-Sanz, S., Gutiérrez, P., Casanova-Mateo, C., & Hervás-Martínez, C. (2014). Simultaneous Modelling of Rainfall Occurrence and Amount Using a Hierarchical Nominal–Ordinal Support Vector Classifier, Engineering Applications of Artificial Intelligence, 34, 199–207.
  51. Salas, J. D. (1980). Applied Modeling of Hydrologic Time Series: Water Resources Publication.
  52. Shafiee, M., Champion, B., Ansari, H., & Sharifi, B. (2011). Stochastic Simulation of Drought Severity Based on Palmer Index, Water and Irrigation Management, 1(1), 1-13. (in Farsi)
  53. Shcherbakov, M. V., Brebels, A., Shcherbakova, N. L., & Tyukov, A. P. (2013). A Survey of Forecast Error Measures. World Applied Sciences, 24, 171-176.
  54. Soh, Y. W., Koo, C. H., Huang, Y. F., & Fung, K. F. (2018). Application of Artificial Intelligence Models for The Prediction of Standardized Precipitation Evapotranspiration Index (SPEI) at Langat River Basin, Malaysia, Computers and Electronics in Agriculture, 144, 164–173.
  55. O., & Shen. H. (2019). Training of Feedforward Neural Networks for Data Classification Using Hybrid Particle Swarm Optimization, Mantegna Levy Flight and Neighborhood Search. Helion, 5, e01275.
  56. Tokar, A. S., & Markus, M. (2000). Precipitation - Run off Modeling Using Artificial Neural Network and Conceptual Models. Hydrologic Engineering, 4(3), 156-161.
  57. Torabipodeh, H., Dehghani, R., & Rostami, S. (2019). Estimation Drought in Lorestan Using Intelligent Networks. Climate Research, 1397(35), 41-52. (in Farsi)
  58. Toufani, P., Mosaedi, A., &Fakheri Fard, A. (2010). Prediction of Precipitation Applying Wavelet Network Model (Case Study: Zarringol Station, Golestan Province, Iran). Water and Soil (Agricultural Science and Technology), 5(25), 1217-1226. (in Farsi)
  59. Vidyarthi, V. K., & Jain, A. (2020). Knowledge Extraction from Trained ANN Drought Classification Model. Hydrology, 585.
  60. Wilhite, D. A., Rosenberg, N. J., & Glantz, M. H. (1986). Improving Federal Response to Drought, Climate and Applied Meteorology, 25, 332–342.
  61. Yeh, H. F., & Hsu, H. L. (2019). Stochastic Model for Drought Forecasting in the Southern Taiwan Basin, Water, 11(10), 2041.
  62. Younesi, , Shahraki, N., Marofi, S., & Nozari, H. (2017). Drought Forecasting Using Artificial Wavelet Neural Network Integrated Model (WA-ANN) and Time Series Model (ARIMA), Irrigation Sciences and Engineering, 41(2), 167-181.
Desert Management
Volume 10, Issue 1 - Serial Number 21
6 Articles
June 2022
Pages 15-36

Files

History

  • Receive Date: 08 December 2021
  • Revise Date: 17 January 2022
  • Accept Date: 25 January 2022

Share

How to cite

Statistics