Evaporation and precipitation prediction for future time frames via combined machine learning-climate change models: Quri Gol Wetland Case

Abstract

Evaporation is a critical component in the management of water resources. Due to the complex interactions between various meteorological variables involved in evaporation calculations, numerous nonlinear models have been developed. The applicability and performance of these models vary depending on the specific climatic conditions of each region. This study evaluates the impacts of climate change on evaporation and precipitation patterns in the Quri Gol Wetland, located in East Azerbaijan, Iran, using machine learning models and climate change projections. Evaporation values for the present period (1991-2020) were estimated using six machine learning models: Random Forest (RF), Gradient Boosted Tree (GBT), Generalized Linear Model (GLM), Support Vector Machine (SVM), Gaussian Process Regression (GPR), and deep learning (DL). Future projections (2021-2050, 2051- 2080, 2081-2100) were based on the LARS-WG and SDSM models under three climate scenarios (RCP 2.6, RCP 4.5, and RCP 8.5). The performance of the machine learning models was assessed using statistical metrics including R2, Scatter Index (SI), Mean Absolute Error (MAE), Willmott’s Index (WI), and Kling-Gupta Efficiency (KGE). The RF and DL models provided the most accurate predictions, with RF achieving an R2 of 0.821 and an MAE of 0.902, while DL reached an R2 of 0.822 and an MAE of 0.915 in the validation phase. Results from climate change projections indicated a significant increase in evaporation over the next century, with cumulative evaporation rising by up to 50.01% under the RCP 8.5 scenario by 2081-2100. In contrast, the projected increase in precipitation was much smaller, reaching a maximum of 16% in the same period. This imbalance between evaporation and precipitation highlights the potential for increasing water stress in the Quri Gol Wetland. The findings emphasize the need for adaptive water management strategies to mitigate the effects of increased evaporation and maintain ecological stability in the region.

Keywords

• Climate change
• Meteorological variables
• Evaporation
• Machine learning
• Statistical indices

References

1. Ahmadaali J, Barani G A, Qaderi K, Hessari B (2018). Analysis of the effects of water management strategies and climate change on the environmental and agricultural sustainability of Urmia Lake basin, Iran. Water 10: 160
2. Azizi G, Nazif S, Abbasi F (2017). An assessment of the influence of climate change on Urmia Lake water level reduction. Journal of Interdisciplinary Studies in the Humanities 9(4): 1-21
3. Bilali A E, Abdeslam T, Ayoub N, Lamane H, Ezzaouini M A, Elbeltagi A (2023). An interpretable machine learning approach based on DNN, SVR, Extra Tree, and XGBoost models for predicting daily pan evaporation. J. Environ. Manage. 327: 116890
4. Bengio Y (2009). Learning Deep Architectures for Artificial Intelligence. Found. Trends Mach. Learn. 2(1): 1-127
5. Breiman L (1999). Using adaptive bagging to debias regressions. Technical Report 547, Statistics Department, University of California.
6. Breiman L (2001). Random forests. Mach. Learn. 45(1): 5-32
7. Chandler R E & Wheater H S (2002). Analysis of rainfall variability using generalized linear models: a case study from the west of Ireland. Water Resour. Res. 38(10): 1-10
8. Dibike Y B & Coulibaly P (2005). Hydrologic impact of climate change in the Saguenay Watershed: Comparison of Ownscaling Methods and Hydrologic Models. J. Hydrol. 307: 145-163

9. Ghaemi A, Rezaie-Balf M, Adamowski J, Kisi O, Quilty J (2019). On the applicability of maximum overlap discrete wavelet transform integrated with MARS and M5 model tree for monthly pan evaporation prediction. Agric. For. Meteorol. 278:107647. https://doi.org/10.1016/j.agrformet.2019.107647.
10. Ghorbani M A, Deo R C, Karimi V, Yaseen Z M, Terzi O (2018). Implementation of a hybrid MLP-FFA model for water level prediction of Lake Egirdir, Turkey. Stoch. Env. Res. Risk Assess. 32(6): 1683-1697. https://doi.org/10.1007/s00477-017-1474-0.
11. Glorot X & Bengio Y (2010). Understanding the difficulty of training deep feedforward neural networks. Proceedings of Machine Learning Research 9:249-256
12. Goyal M K, Bharti B, Quilty J, Adamowski J & Pandey A (2014). Modeling of daily pan evaporation in sub tropical climates using ANN, LS- SVR, Fuzzy Logic, and ANFIS. Expert Syst. Appl. 41(11): 5267-5276
13. Goyal M K & Ojha C S P (2014). Evaluation of rule and decision tree induction algorithms for generating climate change scenarios for temperature and pan evaporation on a lake basin. J. Hydrol. Eng. 19:828-835
14. Guven A & Kisi O (2013). Monthly pan evaporation modeling using linear genetic programming. J. Hydrol. 503:178-185
15. Hamel L (2009). Knowledge Discovery with Support Vector Machines. John Wiley, Hoboken, New Jersey.
16. Hay L E, Wilby R L & Leavesley G H (2000). A comparison of delta change and downscaled GCM scenarios for three mountainous basins in the United States. J. Am. Water Resour. Assoc. 36: 387-397
17. Helfer F, Lemckert C H & Zhang H (2012). Impacts of climate change on temperature and evaporation from a large reservoir in Australia. J. Hydrol. 1-38
18. Hinton G E, Osindero Y W S (2006). A fast learning algorithm for deep belief nets. Neural Comput. 18(7): 1527-1554
19. Keshtegar B, Piri J & Kisi O (2016) A nonlinear mathematical modeling of daily pan evaporation based on conjugate gradient method. Comput. Electron. Agric. 127:120-130
20. Keyvanrad MA, Homayounpour MM (2015) Deep belief network training improvement using elite samples minimizing free energy. Int. J. Pattern Recognit. Artif. 29(5): 155-166
21. Kilsby C G, Jones P D, Burton A, Ford A C, Fowler H J, Harpham C, James P, Smith A & Wilby R L (2007). A daily weather generator for use in climate change studies. Environ. Model. Softw. 22: 1705-1719
22. Kim S, Shiri J, Kisi O (2012). Pan evaporation modeling using neural computing approach for different climatic zones. Water Resour. Manage. 26(11):3231-3249.
23. Kisi O (2015). Pan evaporation modeling using least square support vector machine, multivariate adaptive regression splines and M5 model tree. J. Hydrol. 528: 312-320
24. Kisi O & Heddam S (2019). Evaporation modelling by heuristic regression approaches using only temperature data. Hydrol. Sci. J. 64(6):653- 672
25. Kotsiantis S & Pintelas P (2004). Combining bagging and boosting. Int. J. Comput. Intell. Syst. 1(4):324-333
26. Lu X, Ju Y, Wu L, Fan J, Zhang F & Li Z (2018). Daily pan evaporation modeling from local and cross-station data using three tree-based machine learning models. J. Hydrol. 566: 668-684
27. Majhi B, Naidu D, Mishra A P & Satapathy S C (2020). Improved prediction of daily pan evaporation using Deep-LSTM model. Neural Comput. Appl. pp. 1-16
28. Malik A, Saggi M K, Rehman S, Sajjad H, Inyurt S, Bhatia A S, Farooque A A, Oudah A Y & Yaseen Z M (2022). Deep learning versus gradient boosting machine for pan evaporation prediction, Eng. Appl. Comput. Fluid Mech. 16(1): 570-587
29. Malohlava M & Candel A (2018). Gradient boosting machine with H2O. http://docs.h2o.ai/h2o/latest-stable/h2o-docs/data-science/gbm.html .Accessed 24 FEBRUARY 2020.
30. McCullagh P (1984). Generalized linear models. Eur. J. Oper. Res. 16(3): 285-292
31. Nelder J A & Baker R J (1972). Generalized Linear Models. Wiley Online Library, New Jersey.
32. Pregibon D& Hastie T J (2017). Generalized linear models. In: Statistical Models in S. Routledge.
33. Quinlan J R (1993). C4.5 programs for machine learning. Morgan Kaurmann, San Mateo, CA.
34. Rezaie-Balf M, Kisi O & Chua L H C (2019). Application of ensemble empirical mode decomposition based on machine learning methodologies in forecasting monthly pan evaporation. Hydrol. res. 50(2): 498-516
35. Schapire R (1990). The strength of weak learnability. Journal of Machine learning 5: 197-227
36. Seifi A & Soroush F (2020). Pan evaporation estimation and derivation of explicit optimized equations by novel hybrid meta-heuristic ANN based methods in different climates of Iran. Comput. Electron. Agric. 173: 105418
37. Semenov M A & Stratonovitch P (2010). Use of multi-model ensembles from global climate models for assessment of climate change impacts. Clim. Res. 41:1-14
38. Shiri J (2019). Evaluation of a neuro-fuzzy technique in estimating pan evaporation values in low-altitude locations. Meteorol. Appl. 26(2):204- 212
39. Shaker Sureh F, Sattari M T, Rostamzadeh H & Kahya E (2024). Meteorological Drought Assessment and Prediction in Association with Combination of Atmospheric Circulations and Meteorological Parameters via Rule Based Models. J Agr Sci-Tarim Bili. 30(1):61-78. doi:10.15832/ankutbd.1067486
40. Tatsumi K, Oizumi T & Yamashiki Y (2013). Introduction of daily minimum and maximum temperature change signals in the Shikoku region using the statistical downscaling method by GCMs. Hydrol. Res. Lett. 7(3): 48-53
41. Terzi O (2010). Modeling of daily pan evaporation of lake Egirdir using data-driven techniques. International symposium on innovations in Intelligent systems and Applications. Istanbul. Turkey. pp. 320-324
42. Tezel G & Buyukyildiz M (2016). Monthly evaporation forecasting using artificial neural networks and support vector machines. Theor. Appl. Climatol. 124: 69-80
43. Vapnik V (1995). The Nature of Statistical Learning Theory. Springer, New York.
44. Vapnik V (1998). Statistical Learning Theory. Wiley, New York.
45. Wang L, Kisi O, Zounemat-Kermani M & Li H (2017a). Pan evaporation modeling using six different heuristic computing methods in different climates of China. J. Hydrol. 544: 407-427
46. Wang L, Niu Z, Kisi O, Li C & Yu D (2017b). Pan evaporation modeling using four different heuristic approaches. Comput. Electron. Agric. 140: 203-213
47. Wang H, Yan H, Zeng W, Lei G, Ao C & Zha Y (2020). A novel nonlinear Arps decline model with salp swarm algorithm for predicting pan evaporation in the arid and semi-arid regions of China. J. Hydrol. 582: 124545
48. Wang H, Sun F, Liu F, Wang T, Liu W & Feng Y (2023). Reconstruction of the pan evaporation based on meteorological factors with machine learning method over China. Agric. Water Manag. 287:108416.
49. Wilby R L, Dawson C W & Barrow E M (2002). SDSM a decision support tool for the assessment of regional climate change impacts. Environ. Model. Softw. 17:147-159
50. Wilby RL, Harris I (2006). A frame work for assessing uncertainties in climate change impacts: low flow scenarios for the River Thames, UK. Water Resour. Res. https://doi.org/10.1029/2005wr004065
51. Wilby R L, Tomlinson O J, Dawson C W (2007). Multi-site simulation of precipitation by condition resampling. J. Clim. Res. 23: 183-194
52. Williams C K I, Barber D (1998). Bayesian classification with gaussian processes. IEEE Trans. Pattern Anal. Mach. Intell. 20(12): 1342-1351
53. Williams C K I, Rasmussen C E (1996). Gaussian processes for regression. In: Advances in Neural Information Processing Systems. MIT Press, pp. 514–520
54. Zarghami M, Abdi A, Babaeian I, Hassanzadeh Y İ & Kanani R (2011). Impacts of climate change on runoffs in East Azerbaijan, Iran. Glob Planet Change 78: 137-146
55. Zounemat-Kermani M, Kisi O, Piri J & Mahdavi-Meymand A (2019). Assessment of artificial intelligence–based models and metaheuristic algorithms in modeling evaporation. J. Hydrol. Eng. 24(10): 04019033. https://doi.org/10.1061/(ASCE)HE. 1943-5584.0001835