Improvement of drought forecasting by means of various machine learning algorithms and wavelet transformation

• Autorzy: Tuğrul Turker , Hinis Mehmet Ali

Identyfikatory

DOI

10.1007/s11600-024-01399-z

• Języki publikacji: EN

Abstrakty

EN

Drought, which is defined as a decrease in average rainfall amounts, is one of the most insidious natural disasters. When it starts, people may not be aware of it, which is why droughts are difficult to monitor. Scientists have long been working to predict and monitor droughts. For this purpose, they have developed many methods, such as drought indices, one of which is the Standardized Precipitation Index (SPI). In this study, SPI was used to detect droughts, and machine learning algorithms, including support vector machines (SVM), artificial neural networks, random forest, and decision tree, were used to predict droughts. In addition, 3 different statistical criteria, which are correlation coefficient (r), root mean square error (RMSE), and Nash-Sutcliffe efficiency (NSE), were used to investigate model performance values. The wavelet transform (WT) was also applied to improve model performance. One of the areas most impacted by droughts in Turkey is the Konya Closed Basin, which is geographically positioned in the center of the country and is among the top grain-producing regions in Turkey. The Apa Dam is one of the most significant water resources in the area. It provides water to many fertile fields in its vicinity and is affected by droughts which is why it was selected as a study area. Meteorological data, such as monthly precipitation, that could represent the region were obtained between 1955 and 2020 from the general directorate of state water works and the general directorate of meteorology. According to the findings, the M04 model, whose input structure was developed using SPI, various time steps, data delayed up to 5 months, and monthly precipitation data from the preceding month (time t - 1), produced the best results out of all the models examined using machine learning algorithms. Among machine learning algorithms, SVM has achieved the most successful results not only before applying WT but also after WT. The best results were obtained from M04, in which SVM with WT was used (NSE = 0.9942, RMSE = 0.0764, R = 0.9971).

Słowa kluczowe

EN

SVM; ANN; drought modeling; SPI; wavelet transform; dam management

PL

SVM; ANN; modelowanie suszy; SPI; przekształcenie falkowe; zarządzanie zaporą

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2025
• Tom: Vol. 73, no. 1
• Strony: 855--874
• Opis fizyczny: Bibliogr. 43 poz.

Twórcy

autor

Tuğrul Turker

• Graduate School of Natural and Applied Sciences Department, Civil Engineering, Aksaray University, Aksaray, Turkey
• Gazi University, Rectorate, Ankara, Turkey

• https://orcid.org/0000-0001-7547-847X

autor

Hinis Mehmet Ali

• Faculty of Engineering, Civil Engineering, Aksaray University, Aksaray, Turkey

• https://orcid.org/0000-0002-1870-3535

Bibliografia

• 1. Achite M, Katipoglu OM, Şenocak S, Elshaboury N, Bazrafshan O, Dalkilię HY (2023a) Modeling of meteorological, agricultural, and hydrological droughts in semi-arid environments with various machine learning and discrete wavelet transform. Theor Appl Climatol 154:413-451. https://doi.org/10.1007/s00704-023-04564-4
• 2. Achite M, Katipoglu OM, Jehanzaib M, Elshaboury N, Kartal V, Ali S (2023b) Hydrological drought prediction based on hybrid extreme learning machine: Wadi Mina Basin case study, Algeria. Atmosphere 14:1447
• 3. Adnan S, Ullah K, Shuanglin L, Gao S, Khan AH, Mahmood R (2018) Comparison of various drought indices to monitor drought status in Pakistan. Clim Dyn 51:1885-1899. https://doi.org/10.1007/s00382-017-3987-0
• 4. Belayneh A, Adamowski J, Khalil B, Ozga-Zielinski B (2014) Long- term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet neural network and wavelet support vector regression models. J Hydrol 508:418-429. https://doi.org/10.1016/j.jhydrol.2013.10.052
• 5. Belayneh A, Adamowski J, Khalil B (2016a) Short-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet transforms and machine learning methods. Sustain Water Resour Manag 2:87-101. https://doi.org/10.1007/s40899-015-0040-5
• 6. Belayneh A, Adamowski J, Khalil B, Quilty J (2016b) Coupling machine learning methods with wavelet transforms and the boot- strap and boosting ensemble approaches for drought prediction. Atmos Res 172:37-47. https://doi.org/10.1016/j.atmosres.2015.12.017
• 7. Berhail S, Katipoglu OM (2023) Comparison of the SPI and SPEI as drought assessment tools in a semi-arid region: case of the Wadi Mekerra basin (northwest of Algeria). Theor Appl Climatol 154:1373-1393. https://doi.org/10.1007/s00704-023-04601-2
• 8. Biau G, Scornet E (2016) A random forest guided tour. TEST 25:197- 227. https://doi.org/10.1007/s11749-016-0481-7
• 9. Breiman L (2001) Random forest. Mach Learn. https://doi.org/10.1023/A:1010933404324
• 10. Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees. Chapman and Hall/CRC, New York
• 11. Byun H-R, Wilhite DA (1999) Objective quantification of drought severity and duration. J Clim 12:2747-2756
• 12. Çoban Ö, Eşit M, Yalçın S (2023) ML-DPIE: comparative evaluation of machine learning methods for drought parameter index esti- mation: a case study of Turkiye. Nat Hazards 120(2):989-1021. https://doi.org/10.1007/s11069-023-06233-1
• 13. Dastorani MT, Afkhami H (2011) Application of artificial neural net- works on drought prediction in Yazd (Central Iran)
• 14. Demuth H, Beale M (1998) Neural network toolbox for use with MAT- LAB: user’s guide; computation, visualization, programming. Mathworks Incorporated, Natick
• 15. Deo RC, Şahin M (2015) Application of the artificial neural network model for prediction of monthly standardized precipitation and evapotranspiration index using hydrometeorological parameters and climate indices in eastern Australia. Atmos Res 161:65-81. https://doi.org/10.1016/j.atmosres.2015.03.018
• 16. Deparday V, Gevaert CM, Molinario G, Soden R, Balog-Way S (2019) Machine learning for disaster risk management
• 17. Dikshit A, Pradhan B, Alamri AM (2020) Temporal hydrological drought index forecasting for new south wales. Aust Using Mach Learn Approaches Atmos 11:585. https://doi.org/10.3390/atmos11060585
• 18. Edwards DC, McKee TB (1997) Characteristics of 20th century drought in the United States at multiple time scales, vol 97. Colo¬rado State University Fort Collins, Fort Collins
• 19. Elbeltagi A, Kumar M, Kushwaha N, Pande CB, Ditthakit P, Vishwakarma DK, Subeesh A (2023) Drought indicator analysis and forecasting using data driven models: case study in Jaisalmer, India. Stoch Environ Res Risk Assess 37(1):113-131. https://doi.org/10.1007/s00477-022-02277-0
• 20. Gunn SR (1998) Support vector machines for classification and regression. ISIS Tech Rep 14:5-16
• 21. Guttman NB (1994) On the sensitivity of sample L moments to sample size. J Clim 7(6):1026-1029
• 22. Guttman NB (1999) Accepting the standardized precipitation index: a calculation algorithm 1. JAWRA J Am Water Resour Assoc 35:311-322
• 23. Hao Z, Singh VP, Xia Y (2018) Seasonal drought prediction: advances, challenges, and future prospects. Rev Geophys 56:108-141. https://doi.org/10.1002/2016RG000549
• 24. Haykin S (1998) Neural networks: a comprehensive foundation. Pren- tice Hall PTR, Hoboken
• 25. Hinis MA, Geyikli MS (2023) Accuracy evaluation of standardized precipitation index (SPI) estimation under conventional assumption in Yeşilirmak, Kizilirmak, and Konya Closed Basins. Turk Adv Meteorol 2023:5142965. https://doi.org/10.1155/2023/5142965
• 26. Jain VK, Pandey RP, Jain MK, Byun H-R (2015) Comparison of drought indices for appraisal of drought characteristics in the Ken River Basin. Weather Clim Extrem 8:1-11. https://doi.org/10.1016/j.wace.2015.05.002
• 27. Jehanzaib M, Bilal Idrees M, Kim D, Kim T-W (2021) Comprehensive evaluation of machine learning techniques for hydrological drought forecasting. J Irrig Drain Eng 147:04021022. https://doi.org/10.1061/(ASCE)IR.1943-4774.0001575
• 28. Kao S-C, Govindaraju RS (2010) A copula-based joint deficit index for droughts. J Hydrol 380:121-134. https://doi.org/10.1016/j.jhydrol.2009.10.029
• 29. Katipoğlu OM (2023a) Implementation of hybrid wind speed prediction model based on different data mining and signal processing approaches. Environ Sci Pollut Res 30:64589-64605. https://doi.org/10.1007/s11356-023-27084-0
• 30. Katipoğlu OM (2023b) Prediction of streamflow drought index for short-term hydrological drought in the semi-arid Yesilirmak Basin using wavelet transform and artificial intelligence techniques. Sustainability 15:1109. https://doi.org/10.3390/su150 21109
• 31. Katipoğlu OM, Yeşilyurt SN, Dalkılıç HY, Akar F (2023) Application of empirical mode decomposition, particle swarm optimization, and support vector machine methods to predict stream flows. Environ Monit Assess 195:1108. https://doi.org/10.1007/s10661-023-11700-0
• 32. Khan MMH, Muhammad NS, El-Shafie A (2020) Wavelet based hybrid ANN-ARIMA models for meteorological drought fore- casting. J Hydrol 590:125380
• 33. Kim T-W, Jehanzaib M (2020) Drought risk analysis, forecasting and assessment under climate change. Water 12:1-7. https://doi.org/10.3390/w12071862
• 34. Kim T-W, Valdes JB (2003) Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. J Hydrol Eng 8:319-328. https://doi.org/10.1061/(ASCE)1084-0699(2003)8:6(319)
• 35. Kisi O (2011) Wavelet regression model as an alternative to neural networks for river stage forecasting. Water Resour Manag 25:579-600. https://doi.org/10.1007/s11269-010-9715-8
• 36. Maheswaran R, Khosa R (2012) Comparative study of different wavelets for hydrologic forecasting. Comput Geosci 46:284- 295. https://doi.org/10.1016/j.cageo.2011.12.015
• 37. Mallat SG (1989) A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Mach Intell 11:674-693
• 38. McKee TB, Doesken NJ, Kleist J (1993) The relationship of drought frequency and duration to time scales. In: Proceedings of the 8th conference on applied climatology. California
• 39. Mishra A, Singh VP (2009) Analysis of drought severity-area-frequency curves using a general circulation model and scenario uncertainty. J Geophys Res Atmos. https://doi.org/10.1029/2008JD010986-
• 40. Mishra V, Cherkauer KA, Shukla S (2010) Assessment of drought due to historic climate variability and projected future climate change in the midwestern United States. J Hydrometeorol 11:46-68. https://doi.org/10.1175/2009JHM1156.1
• 41. Mishra AK, Singh VP (2011) Drought modelling—a review. J Hydrol 403:157-175. https://doi.org/10.1016/j.jhydrol.2011.03.049
• 42. Mohammed S, Elbeltagi A, Bashir B, Alsafadi K, Alsilibe F, Alsalman A, Zeraatpisheh M, Szeles A, Harsanyi E (2022) A comparative analysis of data mining techniques for agricultural and hydrological drought prediction in the eastern Mediterranean. Comput Electron Agric 197:106925. https://doi.org/10.1016/j.compag.2022.106925
• 43. Muller KR, Mika S, Ratsch G, Tsuda K, Scholkopf B (2001) An introduction to kernel-based learning algorithms. IEEE Trans Neural Netw 12:181-201. https://doi.org/10.1109/72.914517

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).