Comprehensive Evaluation of Machine Learning Techniques for Hydrological Drought Forecasting
This article has a reply.
VIEW THE REPLYPublication: Journal of Irrigation and Drainage Engineering
Volume 147, Issue 7
Abstract
Drought is among the most hazardous climatic disasters that significantly influence various aspects of the environment and human life. Qualitative and reliable drought forecasting is important worldwide for effective planning and decision-making in disaster-prone regions. Data-driven models have been extensively used for drought forecasting, but due to the inadequacy of information on model performance, the selection of an appropriate forecasting model remains a challenge. This study concerns a comparative analysis of six machine learning (ML) techniques widely used for hydrological drought forecasting. The standardized runoff index (SRI) was calculated at a seasonal (3-month) time scale for the period 1973 to 2016 in four selected watersheds of the Han River basin in South Korea. The ML models employed were built-ins, using precipitation, temperature, and humidity as input variables and the SRI as the target variable. The results indicated that all the ML models were able to map the relationship for seasonal SRI using the applied input vectors. The decision tree (DT) technique outperformed in all the watersheds with an average mean absolute error , root mean square error , Nash-Sutcliffe efficiency , and coefficient of determination . The performances of the support vector machine (SVM) and deep learning neural network (DLNN) were similar, whereas the fuzzy rule-based system (FRBS) performed very well compared to the artificial neural network (ANN) and the adaptive neuro-fuzzy inference system (ANFIS). The overall findings of this study indicate that, considering performance criteria and computation time, the DT was the most accurate ML technique for hydrological drought forecasting in the Han River basin.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Some or all data, models, or code generated or used during the study are available from the corresponding author by request. (Data used in study, codes to generate drought index, and codes of all the machine learning techniques).
Acknowledgments
This work was supported by the Lower-Level and Core Disaster-Safety Technology Development Program funded by the Ministry of Interior and Safety (Grant No. 2020-MOIS33-006) and the Korea National Research Foundation (Grant No. 2020R1A2C1012919). The first author is extremely thankful to the Higher Education Commission (HEC) and the Government of Pakistan for the scholarship under the project “HRD Initiative-MS leading to Ph.D. program of faculty development for UESTPS, Phase-1, and Batch-V for Hanyang University, South Korea.”
References
Abrahart, R. J., L. M. See, and D. P. Solomatine. 2008. Practical hydroinformatics: Computational intelligence and technological developments in water applications. Berlin: Springer.
Alipour, Z., A. M. A. Ali, F. Radmanesh, and M. Joorabyan. 2014. “Comparison of three methods of ANN, ANFIS and time series models to predict ground water level: (Case study: North Mahyar plain).” Bull. Environ. Pharmacol. Life Sci. 3 (5): 128–134.
Belayneh, A., and J. Adamowski. 2013. “Drought forecasting using new machine learning methods.” J. Water Land Dev. 18 (9): 3–12. https://doi.org/10.2478/jwld-2013-0001.
Breiman, L., J. Friedman, R. Olshen, and C. Stone. 1984. Classification and regression trees. Boca Raton, FL: CRC Press.
Brown, M., and C. J. Harris. 1994. Neurofuzzy adaptive modelling and control. Englewood Cliffs, NJ: Prentice-Hall.
Durbach, I., B. Merven, and B. Mccall. 2017. “Expert elicitation of autocorrelated time series with application to e3 (energy-environment-economic) forecasting models.” Environ. Modell. Software 88 (Feb): 93–105. https://doi.org/10.1016/j.envsoft.2016.11.007.
Haykin, S. 1999. Neural networks, a comprehensive foundation. 2nd ed., 135–155. Englewood Cliffs, NJ: Prentice-Hall.
Heim, R. R. 2002. “A review of twentieth-century drought indices used in the United States.” Bull. Am. Meteorol. Soc. 83 (8): 1149–1166. https://doi.org/10.1175/1520-0477-83.8.1149.
Hothorn, T., K. Hornik, and A. Zeileis. 2006. “Unbiased recursive partitioning: A conditional inference framework.” J. Comput. Graphical Stat. 15 (3): 651–674. https://doi.org/10.1198/106186006X133933.
Jang, J. S. R., C. T. Sun, and E. Mizutani. 1997. Neuro-fuzzy and soft computing: A computational approach to learning and machine intelligence, 665–685. Englewood Cliffs, NJ: Prentice-Hall.
Jehanzaib, M., M. N. Sattar, J. H. Lee, and T. W. Kim. 2020a. “Investigating effect of climate change on drought propagation from meteorological to hydrological drought using multi-model ensemble projections.” Stochastic Environ. Res. Risk Assess. 34 (1): 1–15. https://doi.org/10.1007/s00477-019-01760-5.
Jehanzaib, M., S. A. Shah, J. Yoo, and T. W. Kim. 2020b. “Investigating the impacts of climate change and human activities on hydrological drought using non-stationary approaches.” J. Hydrol. 588 (Sep): 125052. https://doi.org/10.1016/j.jhydrol.2020.125052.
Keskin, M. E., Ö. Terzi, E. D. Taylan, and D. Küçükyaman. 2009. “Meteorological drought analysis using data driven models for the Lakes District, Turkey.” Hydrol. Sci. J. 54 (6): 1114–1124. https://doi.org/10.1623/hysj.54.6.1114.
Lee, J. Y., N. W. Kim, T. W. Kim, and M. Jehanzaib. 2019. “Feasible ranges of runoff curve numbers for Korean watersheds based on the interior point optimization algorithm.” KSCE J. Civ. Eng. 23 (12): 1–9. https://doi.org/10.1007/s12205-019-0901-9.
Maca, P., and P. Pech. 2016. “Forecasting SPEI and SPI drought indices using the integrated artificial neural networks.” Comput. Intell. Neurosci. 2016 (Dec): 17. https://doi.org/10.1155/2016/3868519.
Magdalena, L. 2015. Fuzzy rule-based systems. In Handbook of computational intelligence, 203–218. Berlin: Springer.
Mishra, A. K., and V. P. Singh. 2011. “Drought modeling—A review.” J. Hydrol. 403 (1–2): 157–175. https://doi.org/10.1016/j.jhydrol.2011.03.049.
Mokhtarzad, M., F. Eskandari, N. J. Vanjani, and A. Arabasadi. 2017. “Drought forecasting by ANN, ANFIS, and SVM and comparison of the models.” Environ. Earth Sci. 76 (21): 729. https://doi.org/10.1007/s12665-017-7064-0.
Nair, V., and G. E. Hinton. 2010. “Rectified linear units improve restricted Boltzmann machines.” In Proc., 27th Int. Conf. on Machine Learning, 807–814. Alexandria, VA: IBM and National Science Foundation.
Nalbantis, I., and G. Tsakiris. 2009. “Assessment of hydrological drought revisited.” Water Resour. Manage. 23 (5): 881–897. https://doi.org/10.1007/s11269-008-9305-1.
Nayak, P. C., K. Sudheer, D. Rangan, and K. Ramasastri. 2004. “A neuro-fuzzy computing technique for modeling hydrological time series.” J. Hydrol. 291 (1–2): 52–66. https://doi.org/10.1016/j.jhydrol.2003.12.010.
See, L., and S. Openshaw. 1999. “Applying soft computing approaches to river level forecasting.” Hydrol. Sci. J. 44 (5): 763–777. https://doi.org/10.1080/02626669909492272.
Shirmohammadi, B., H. Moradi, V. Moosavi, M. T. Semiromi, and A. Zeinali. 2013. “Forecasting of meteorological drought using wavelet-ANFIS hybrid model for different time steps (Case study: Southeastern part of east Azerbaijan province, Iran).” Nat. Hazards 69 (1): 389–402. https://doi.org/10.1007/s11069-013-0716-9.
Shukla, S., and A. W. Wood. 2008. “Use of a standardized runoff index for characterizing hydrologic drought.” Geophys. Res. Lett. 35 (2): 226–236. https://doi.org/10.1029/2007GL032487.
Solomatine, D. P., and A. Ostfeld. 2008. “Data-driven modelling: Some past experiences and new approaches.” J. Hydroinf. 10 (1): 3–22. https://doi.org/10.2166/hydro.2008.015.
Srivastava, N., G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. 2014. “Dropout: A simple way to prevent neural networks from overfitting.” J. Mach. Learn. Res. 15 (1): 1929–1958.
Sujay, R. N., and C. D. Paresh. 2014. “Support vector machine applications in the field of hydrology: A review.” Appl. Soft Comput. J. 19 (Jun): 372–386. https://doi.org/10.1016/j.asoc.2014.02.002.
Vapnik, V. 1999. The nature of statistical learning theory. 2nd ed. Berlin: Springer.
WAMIS (Water Resources Management Information System). 2020. “National Water Resource Management Comprehensive Information System.” Accessed July 19, 2020. http://www.wamis.go.kr/wkw/rf_dubrfobs.do.
Wang, Z., W. Yan, and T. Oates. 2017. “Time series classification from scratch with deep neural networks: A strong baseline.” In Proc., Int. Joint Conf. on Neural Networks, 1578–1585. New York: IEEE.
Zadeh, L. A. 2001. “A new direction in AI: Toward a computational theory of perceptions.” AI Mag. 22 (1): 3–20. https://doi.org/10.1609/aimag.v22i1.1545.
Zhao, J., J. Xu, X. Xie, and H. Lu. 2016. “Drought monitoring based on TIGGE and distributed hydrological model in Huaihe River basin, China.” Sci. Total Environ. 553 (May): 358–365. https://doi.org/10.1016/j.scitotenv.2016.02.115.
Zhao, L., A. Lyu, J. Wu, M. Hayes, Z. Tang, B. He, J. Liu, and M. Liu. 2014. “Impact of meteorological drought on streamflow drought in Jinghe River basin of China.” Chin. Geogr. Sci. 24 (6): 694–705. https://doi.org/10.1007/s11769-014-0726-x.
Information & Authors
Information
Published In
Copyright
© 2021 American Society of Civil Engineers.
History
Received: Jan 9, 2020
Accepted: Feb 22, 2021
Published online: Apr 20, 2021
Published in print: Jul 1, 2021
Discussion open until: Sep 20, 2021
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.
Cited by
- Mohammed Achite, Nehal Elshaboury, Muhammad Jehanzaib, Dinesh Vishwakarma, Quoc Pham, Duong Anh, Eslam Abdelkader, Ahmed Elbeltagi, Performance of Machine Learning Techniques for Meteorological Drought Forecasting in the Wadi Mina Basin, Algeria, Water, 10.3390/w15040765, 15, 4, (765), (2023).
- Tuong Quang Vo, Seon-Ho Kim, Duc Hai Nguyen, Deg-Hyo Bae, LSTM-CM: a hybrid approach for natural drought prediction based on deep learning and climate models, Stochastic Environmental Research and Risk Assessment, 10.1007/s00477-022-02378-w, (2023).
- Suman Markuna, Pankaj Kumar, Rawshan Ali, Dinesh Kumar Vishwkarma, Kuldeep Singh Kushwaha, Rohitashw Kumar, Vijay Kumar Singh, Sumit Chaudhary, Alban Kuriqi, Application of Innovative Machine Learning Techniques for Long-Term Rainfall Prediction, Pure and Applied Geophysics, 10.1007/s00024-022-03189-4, 180, 1, (335-363), (2023).
- Haowen Yue, Mekonnen Gebremichael, Vahid Nourani, Performance of the Global Forecast System's medium-range precipitation forecasts in the Niger river basin using multiple satellite-based products, Hydrology and Earth System Sciences, 10.5194/hess-26-167-2022, 26, 1, (167-181), (2022).
- Mohammed Achite, Muhammad Jehanzaib, Nehal Elshaboury, Tae-Woong Kim, Evaluation of Machine Learning Techniques for Hydrological Drought Modeling: A Case Study of the Wadi Ouahrane Basin in Algeria, Water, 10.3390/w14030431, 14, 3, (431), (2022).
- Muhammad Jehanzaib, Muhammad Ajmal, Mohammed Achite, Tae-Woong Kim, Comprehensive Review: Advancements in Rainfall-Runoff Modelling for Flood Mitigation, Climate, 10.3390/cli10100147, 10, 10, (147), (2022).
- Guo Chun Wang, Qian Zhang, Shahab S. Band, Majid Dehghani, Kwok wing Chau, Quan Thanh Tho, Senlin Zhu, Saeed Samadianfard, Amir Mosavi, Monthly and seasonal hydrological drought forecasting using multiple extreme learning machine models, Engineering Applications of Computational Fluid Mechanics, 10.1080/19942060.2022.2089732, 16, 1, (1364-1381), (2022).
- Xuan Li, Jingming Hou, Jie Chai, Ying’en Du, Hao Han, Shaoxiong Yang, Xujun Gao, Xiao Yang, An Online Data-Driven Evolutionary Algorithm–Based Optimal Design of Urban Stormwater-Drainage Systems, Journal of Irrigation and Drainage Engineering, 10.1061/(ASCE)IR.1943-4774.0001699, 148, 11, (2022).
- Muhammad Jehanzaib, Sabab Ali Shah, Ho Jun Son, Sung-Hwan Jang, Tae-Woong Kim, Predicting Hydrological Drought Alert Levels Using Supervised Machine-Learning Classifiers, KSCE Journal of Civil Engineering, 10.1007/s12205-022-1367-8, 26, 6, (3019-3030), (2022).
- Hasan Törehan Babacan, Ömer Yüksek, Fatih Saka, Investigation of Impact of Vapor Pressure on Hybrid Streamflow Prediction Modeling, KSCE Journal of Civil Engineering, 10.1007/s12205-022-0488-4, 27, 2, (890-902), (2022).
- See more