Iranian Water Research Journal

Iranian Water Research Journal

Drought prediction using a collaborative LSTM model (Case study: North of Isfahan province)

Authors
Maliheh Ghabraie 1
Abolfazl Ranjbar Fordoie 2
Mohammad Ehteram 3
1 Department of Arid Environments, Faculty of Natural Resources and Earth Sciences, University of Kashan.
2 Department of Desert Management and Control, Faculty of Natural Resources and Earth Sciences, University of Kashan, Kashan, Iran.
3 Ph D Fradutaet of Department of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering, Semnan, Iran.
10.22034/IWRJ.2025.14963.2637
Abstract
Introduction:
Drought is a natural phenomenon that significantly impacts human life and ecosystems. Lack of rainfall can cause various problems, including damage to crops and a shortage of drinking water for local communities. These effects can lead to devastating economic and social disasters, such as famine, forced migration away from drought-affected areas, and conflicts over remaining resources. Predicting drought indices, such as the Standardized Precipitation Index (SPI), is crucial for assessing this phenomenon in water resource management. The SPI is a tool for evaluating and measuring the intensity and duration of drought, allowing for drought analysis on both short-term and long-term time scales, and providing accurate information on drought severity to water resource managers and policymakers. However, predicting the SPI can be challenging due to the complex interactions of influencing factors.
While deep learning models, especially Long Short-Term Memory (LSTM) networks, have shown promise in predicting SPI, they also have key limitations. First, the LSTM model has parameters that need fine-tuning. Second, selecting the best input combination for the LSTM model is complex and challenging. The inputs required for drought prediction are usually associated with various time lags. Choosing the best input combination from a large number of inputs is important, as it affects the performance of the LSTM model. The third challenge is that the LSTM model lacks connections that directly transfer information from the model's memory to its computation gates, which can lead to the loss of important information.
Materials and Methods:
This study investigates the challenges and aims to improve the performance of the Long Short-Term Memory (LSTM) model in predicting the drought index (SPI) at 3-, 6-, and 9-month time scales (SPI-3, SPI-6, and SPI-9) in the northern region of Isfahan Province. To achieve this, a novel "Collaborative LSTM" model was proposed and a binary genetic algorithm was developed. Various large-scale climate indices were utilized as input data for the prediction models. To optimize model performance, the binary genetic algorithm was employed to select the optimal input scenario and fine-tune the model parameters. In the first step, the input data, including time series, were divided into training and test datasets. Eighty percent of the input data were selected for training, and twenty percent were used for testing to minimize prediction error. The algorithm then selected the best input parameters from large-scale climate signals with different delays. Each chromosome comprised two parts: the first part contained the model inputs, and the second part contained the initial parameter values. Binary chromosomes were encoded based on 0 and 1 values, indicating the absence or presence of a factor in the modeling process, respectively. Each binary value in the second part determined how the initial value of a particular parameter was chosen. A new version of the LSTM model was then built with three additional weighted connections compared to the original LSTM model. The Collaborative LSTM incorporates three novel weight connections that facilitate the flow of crucial information from the memory cell to the input, forget, and output gates, enhancing information retention and improving prediction accuracy. The performance of the Collaborative LSTM was compared against traditional LSTM, Multilayer Perceptron (MLP), Radial Basis Function Neural Network (RBFNN), and Multiple Linear Regression (MLR) models. Multiple error metrics were used to assess model accuracy. The modeling process involved a multi-step approach: (1) optimal input scenario selection using the binary genetic algorithm, (2) model parameter optimization using the genetic algorithm, and (3) development and evaluation of the Collaborative LSTM model for SPI prediction.
Result and Discussion:
The results demonstrated the effectiveness of the binary genetic algorithm in optimizing both input selection and model parameters. The Collaborative LSTM consistently outperformed other models, achieving a 2.1-6.1% improvement in the Willmott Index (WI) for SPI-3, 1.1-5.1% for SPI-6, and 1.1-2.2% for SPI-9. Statistical analysis revealed that the predicted SPI values from the Collaborative LSTM closely resembled the observed SPI data. The superior performance of the Collaborative LSTM can be attributed to its enhanced information flow architecture, which enables more effective utilization of past information stored in the memory cell. Boxplots further visualized the improved accuracy of the Collaborative LSTM in predicting SPI values across different scenarios. The findings of this study demonstrate the potential of the Collaborative LSTM model as a reliable tool for accurate drought index forecasting. By addressing the limitations of traditional LSTMs and incorporating optimized input selection and parameter tuning, this novel approach offers significant advancements in drought prediction capabilities.
Keywords
Drought
Predictive models
Drought index deep
Learning models
1.     Allahverdipour, P. and Sattari, M. T., 2023. Comparing the performance of the multiple linear regression classic method and modern data mining methods in annual rainfall modeling (Case study: Ahvaz city). Water and Soil Managementand Modeling, 3(2), pp. 125-142. DOI:10.22098/mmws.2022.11337.1120 [in Persian].
 
2.     Aote, S. S., Pimpalshende, A., Potnurwar, A. and Lohi, S., 2023. Binary Particle Swarm Optimization with an improved genetic algorithm to solve multi-document text summarization problem of Hindi documents. Engineering Applications of Artificial Intelligence, 117, pp. 105575. DOI:10.1016/j.engappai.2022.105575
 
3.     Danandeh Mehr, A., Rikhtehgar Ghiasi, A., Yaseen, Z. M., Sorman, A. U. and Abualigah, L., 2023. A novel intelligent deep learning predictive model for meteorological drought forecasting '. Journal of Ambient Intelligence and Humanized Computing, 14(8), pp. 10441-10455. DOI :10.1007/s11356-021-15325-z
 
4.     Ehteram, M., Afshari Nia, M., Panahi, F. and Farrokhi, A., 2024. Read-First LSTM model: A new variant of long short term memory neural network for predicting solar radiation data. Energy Conversion and Management, 305, 118267). DOI: 10.1016/j.enconman.2024.118267
 
5.     Gyaneshwar, A., Mishra, A., Chadha, U., Raj Vincent, P.M.D., Rajinikanth, V., Pattukandan Ganapathy, G. and Srinivasan, K., 2023. A Contemporary Review on Deep Learning Models for Drought Prediction. Sustainability, 15(7), 6160.  DOI:10.3390/su15076160
 
6.     Jurasz, J., Guezgouz, M., Campana, P. E., Kaźmierczak, B., Kuriqi, A., Bloomfield, H., Hingray, B., Canales, F. A., Hunt, J. D., Sterl, S. and Elkadeem, M. R., 2024. Complementarity of wind and solar power in North Africa: Potential for alleviating energy droughts and impacts of the North Atlantic Oscillation. Renewable and Sustainable Energy Reviews, 191, pp. 114181. DOI: 10.1016/j.rser.2023.114181
 
7.     Kheyruri, Y., Sharafati, A. and Neshat, A., 2023. Predicting agricultural drought using meteorological and ENSO parameters in different regions of Iran based on the LSTM model. Stochastic Environmental Research and Risk Assessment, 37(9), 3599-3613.  DOI :10.1007/s00477-023-02465-6
 
8.     McKee, T. B., Doesken, N. J. and Kleist, J., 1993. The Relationship of Drought Frequency and Duration to Time Scales'. Journal of the American Meteorological Society,17(22), 179-183.
9.     Mohammad-Rezaei, M., Soltani, S. and Modarres, R., 2020. Evaluating The Effect of Ocean- Atmospheric Indices on Drought in Iran. Theoretical and Applied Climatology, 140, 219-230. DOI: 10.1007/s00704-019-03058-6
 
10. Nandgude, N., Singh, T. P., Nandgude, S. and Tiwari, M., 2023. Drought Prediction: A Comprehensive Review of Different Drought Prediction Models and Adopted Technologies. Sustainability, 15(15), 11684. DOI: 10.3390/su151511684
 
11. Nguyen, T. T. H., Li, M. H., Vu, T. M. and Chen, P. Y., 2023. Multiple drought indices and their teleconnections with ENSO in various spatiotemporal scales over the Mekong River Basin. Science of the Total Environment, 854, 158589. DOI: 10.1016/j.scitotenv.2022.158589
 
12. Pande, C. B., Costache, R., Sammen, S. S., Noor, R. and Elbeltagi, A., 2023. Combination of data-driven models and best subset regression for predicting the standardized precipitation index (SPI) at the Upper Godavari Basin in India. Theoretical and Applied Climatology, 152, 535–558.  DOI: 10.1007/s00704-023-04426-z
 
13. Parvin nia, M. and Riahi Farsani, M., 2016. Drought survey of Shahrekord plain using nstandardized precipitation index and gamma distribution, 1(2), pp. 41-50 [in Persian].
 
14. Rezaei, A., 2023. Teleconnections between ocean–atmosphere circulations and historical integrated drought in the Middle East and North Africa. Environmental Monitoring and Assessment, 195(755), 1-21. DOI: 10.1007/s10661-023-11386-4
 
15. Shah, W., Chen, J., Ullah, I. and Shah, M. H., 2024. Application of RNN-LSTM in Predicting Drought Patterns in Pakistan: A Pathway to Sustainable Water Resource Management. Water, 16(11), 1492.  DOI : 10.3390/w16111492
 
16. Skobtsov, V. Yu., Sokolov, B. V., Zhang, W. A., and Fu M., 2024. Hybrid neural network models for monitoring time series data of complex objects. Journal of Instrument Engineering 67(2), pp. 200-204. (in Russian) DOI: 10.17586/0021-3454-2024-67-2-200-204
 
17. Taylan, E. D., 2024. An Approach for Future Droughts in Northwest Türkiye: SPI and LSTM Methods. Sustainability, 16(16), 6905. DOI :10.3390/su16166905
 
18. Vo, T. Q., Kim, S. H., Nguyen, D. H. and Bae, D. H., 2023. LSTM-CM: a hybrid approach for natural drought prediction based on deep learning and climate models. Stochastic Environmental Research and Risk Assessment. 37(6), 2035-2051. DOI: 10.1007/s00477-022-02378-w
 
19. Wang, G., Cai, W., Santoso, A., Abram, N., Ng, B., Yang, K. and Li, X., 2024. The Indian Ocean Dipole in a warming world. Nature Reviews Earth & Environment, 5(8), 588–604. DOI: 10.1038/s43017-024-00573-7
 
20. Wu, Z., Yin, H., He, H. and Li, Y., 2022. Dynamic-LSTM hybrid models to improve seasonal drought predictions over China. Journal of Hydrology, 615(1), 128706. DOI: 10.1016/j.jhydrol.2022.128706
 
21. Xu, D., Zhang, Q., Ding, Y. and Zhang, D., 2022. Application of a hybrid ARIMA-LSTM model based on the SPEI for drought forecasting. Environmental Science and Pollution, 29(3), 4128-4144.
 
22. Zhang, N., Dai, X., Ehsan, M. A. and Deksissa, T., 2020. Development of a drought prediction system based on long short-term memory networks LSTM. Springer International Publishin, 17, 142-153. DOI: 10.1007/978-3-030-64221-1_13
 

  • Receive Date 17 October 2024
  • Accept Date 09 January 2025
  • Publish Date 21 March 2025