پژوهش‌های تغییرات آب و هوایی

پژوهش‌های تغییرات آب و هوایی

پایش خشکسالی بر مبنای شاخص بارش- تبخیروتعرق استاندارد شده SPEI تحت تأثیر تغییر اقلیم و الگوریتم XGBoost

نوع مقاله : مقاله پژوهشی

نویسندگان
هادی رمضانی اعتدالی 1
مژگان احمدی 2
1 استاد گروه علوم و مهندسی آب، دانشکده کشاورزی، دانشگاه بین المللی امام خمینی (ره) قزوین، قزوین، ایران
2 دانش آموخته دکتری، گروه علوم و مهندسی آب، دانشگاه بین المللی امام خمینی (ره) قزوین، قزوین، ایران
10.30488/ccr.2026.568744.1321
چکیده
در سال‌های اخیر، به‌دنبال بروز پدیده‌ی گرمایش جهانی و تغییر در الگوهای اقلیمی و پارامترهای هواشناسی، فراوانی وقوع خشکسالی در بسیاری از مناطق جهان افزایش یافته است. در این مطالعه به پایش خشکسالی با استفاده از شاخص SPEI و بررسی خصوصیات این پدیده (شدت، بزرگی، مدت) در شرایط تغییر اقلیم در ایستگاه سینوپتیک قزوین در دوره تاریخی 2014-1986 و دوره‌های آینده 2050-2026، 2075-2051 و 2100-2076 تحت سناریوهای SSP2-4.5 و SSP5-8.5 در مقیاس‌های زمانی 3، 6، 9 و 12 ماهه پرداخته شده است. به‌منظور کاهش عدم‌قطعیت مدل‌های منفرد و افزایش قابلیت اعتماد برآوردها، از یک رویکرد ترکیب چندمدلی مبتنی بر یادگیری ماشین (Multi-Model Ensemble) با استفاده از الگوریتم XGBoost جهت ترکیب غیرخطی و بهینه خروجی سه مدل اقلیمی  CMIP6شامل MIROC6،ACCESS-CM2  و CNRM-CM6-1 استفاده شد. ویژگی‌های خشکسالی بر اساس داده‌های مدل ترکیبی (Ensemble) حاصل از سه مدل اقلیمی محاسبه شدند. در سناریویSSP2-4.5، تغییرات خشکسالی نسبت به گذشته روندی افزایشی ملایم نشان داد. در دوره‌ی 2026–2050، میانگین شدت بین 03/2 تا 02/3 و بزرگی بین 91/0 تا 25/1 مشاهده شد. در سناریوی بدبینانه SSP5-8.5، روند افزایش شدت و بزرگی خشکسالی‌ها واضح‌تر بود. در نیمه‌ی اول قرن (2026–2050)، شدت بین 91/1 تا 70/3 و بزرگی بین 1/1تا 14/1 متغیر بود. به‌طور کلی، نتایج نشان داد که هر دو شاخص شدت و بزرگی خشکسالی از گذشته به آینده روندی افزایشی دارند، اما افزایش شدت چشمگیرتر است. بدین ترتیب می‌توان نتیجه گرفت که در آینده، منطقه‌ی مورد مطالعه با افزایش فراوانی، شدت و پایداری خشکسالی‌ها مواجه خواهد شد و این امر ضرورت برنامه‌ریزی سازگاری، مدیریت منابع آب و توسعه‌ی راهبردهای کاهش اثرات خشکسالی را بیش از پیش آشکار می‌سازد.
کلیدواژه‌ها
مدل گردش عمومی جو
مدل گروهی
یادگیری ماشین
سناریوهای گزارش ششم
موضوعات

عنوان مقاله English

Drought monitoring based on the Standardized Precipitation-Evaporation Index SPEI under the influence of climate change and the XGBoost algorithm

نویسندگان English

Hadi Ramezsani Etedali 1
Mojgan Ahmadi 2
1 Associate Professor, Department of Water Science and Engineering, Imam Khomeini International University, Qazvin, Iran
2 Ph.D. Graduate, Department of Water Science and Engineering, Imam Khomeini International University, Qazvin, Iran
چکیده English

In recent years, following the occurrence of global warming and changes in climate patterns and meteorological parameters, the frequency of droughts has increased in many regions of the world. In this study, drought monitoring using the SPEI index and examining the characteristics of this phenomenon (intensity, magnitude, duration) under climate change conditions at the Qazvin synoptic station in the historical period 2014-1986 and the future periods 2050-2026, 2051-2075 and 2100-2076 under SSP2-4.5 and SSP5-8.5 scenarios at time scales of 3, 6, 9 and 12 months have been studied. To reduce the uncertainty associated with individual models and enhance the reliability of the estimates, a machine learning–based Multi-Model Ensemble (MME) approach was employed. The XGBoost algorithm was used to perform a nonlinear and optimized combination of the outputs from three CMIP6 climate models: MIROC6, ACCESS-CM2, and CNRM-CM6-1. Drought characteristics were subsequently calculated based on the ensemble dataset derived from the combined outputs of these three climate models. In the SSP2-4.5 scenario, drought changes showed a slight increasing trend compared to the past. In the period 2026–2050, the average intensity was observed between 2.03 and 3.02, and the magnitude between 0.91 and 1.25. In the pessimistic scenario SSP5-8.5, the trend of increasing drought intensity and magnitude was more obvious. In the first half of the century (2026–2050), the intensity varied between 1.91 and 3.70, and the magnitude between 1.1 and 1.14. Overall, the results showed that both the intensity and magnitude indices of drought have an increasing trend from the past to the future, but the increase in intensity is more dramatic. Thus, it can be concluded that in the future, the study area will face an increase in the frequency, severity, and persistence of droughts, which further highlights the need for adaptation planning, water resource management, and the development of strategies to reduce the effects of drought

کلیدواژه‌ها English

Atmospheric general circulation model
ensemble model
machine learning
Scenarios Six Report
1.    شاهین رخسار، پ.، علیزاده، ا.، انصاری، ح.، قربانی، م. 1398. بررسی عدم قطعیت گروهی مدل های گردش عمومی جو در شبیه سازی داده های هواشناسی (مطالعه موردی ایستگاه سینوپتیک رشت). آبیاری و زهکشی ایران، 13 (6): 1909-1897.
2.    ایزدی، ن.، امیرآبادی زاده، م.، دستورانی، م. 1402. بررسی تغییرات دمای هوا در شهرستان طبس در افق آینده با استفاده از گزارش ششم تغییر اقلیم. هواشناسی و علوم جو، 6 (1): 14-1.
3.    Vicente-Serrano, S. M., Beguería, S., & López-Moreno, J. I. (2010). A multiscalar drought index sensitive to global warming: The Standardized Precipitation Evapotranspiration Index (SPEI). Journal of Climate, 23(7), 1696–1718.
https://doi.org/10.1175/2009JCLI2909.1
4.    Vicente-Serrano, S. M., Beguería, S. & López-Moreno, J. I. 2010 A multiscalar drought index sensitive to global warming: the standardized precipitation evapotranspiration index. Journal of Climate 23 (7), 1696–1718. https://doi.org/10.1175/2009JCLI2909.1.
5.    Thornthwaite, C. W. (1948). An approach toward a rational classification of climate. Geographical Review, 38(1), 55–94.
6.    Khazaei, M. R. (2025). Projected changes to drought characteristics in Tehran under CMIP6 SSP-RCP climate change scenarios. Heliyon, 11(2).doi: 10.1016/j.heliyon.2025.e41811. PMID: 39882481; PMCID: PMC11774936.
7. Maqsood, J., Wang, X., Farooque, A. A., & Nawaz, R. A. (2024). Future projections of temperature-related indices in Prince Edward Island using ensemble average of three CMIP6 models. Scientific Reports, 14(1), 12661. doi: 10.1038/s41598-024-63450-9. PMID: 38830965; PMCID: PMC11148011.
8. Jose, D.M., Vincent, A.M. & Dwarakish, G.S. Improving multiple model ensemble predictions of daily precipitation and temperature through machine learning techniques. Sci Rep 12, 4678 (2022). https://doi.org/10.1038/s41598-022-08786-w
9. Chen T and Guestrin C 2016 XGBoost: a scalable tree boosting system Proc. 22nd Proc ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining pp 785–94
10. Friedman J H 2001 Greedy function approximation: a gradient boosting machine Ann. Stat. 29 1189–232.
11. Tuong, V. Q., Kiet, B. A., & Pham, T. T. (2025). Assessment of Future Drought Characteristics Using Various Temporal Scales and Multiple Drought Indices over Mekong Basin Under Climate Changes. Water, 17(10), 1507. https://doi.org/10.3390/w17101507
12. Cook, B.I., Mankin, J.S., Marvel, K., Williams, A.P., Smerdon, J.E. & Anchukaitis, K.J. (2020) Twenty-first century drought projections in the CMIP6 forcing scenarios. Earth's Future, 8(6), e2019EF001461. Available from: https://doi.org/ 10.1029/2019ef001461
13. Li, Z. & Fang, H. (2016) Impacts of climate change on water ero sion: a review. Earth-Science Reviews, 163, 94–117. Available from: https://doi.org/10.1016/j.earscirev.2016.10.004
14. Zheng, H., Chiew, F.H.S., Charles, S. & Podger, G. (2018) Future climate and runoff projections across South Asia from CMIP5 global climate models and hydrological modelling. Journal of Hydrology: Regional Studies, 18, 92–109. Available from: https://doi.org/10.1016/j.ejrh.2018.06.004
15. Schilling, J., Hertig, E., Tramblay, Y. & Scheffran, J. (2020) Climate change vulnerability, water resources and social implications in North Africa. Regional Environmental Change, 20(1), 15. Avail able from: https://doi.org/10.1007/s10113-020-01597-7
16. Meaurio, M., Zabaleta, A., Boithias, L., Epelde, A.M., Sauvage, S., Sanchez-Pérez, J.M. et al. (2017) Assessing the hydrological response from an ensemble of CMIP5 climate projections in the transition zone of the Atlantic region (Bay of Biscay). Journal of Hydrology, 548, 46–62. Available from: https://doi.org/10.1016/ j.jhydrol.2017.02.029
17. Li, L., Krasovskaia, I., Xiong, L. & Yan, L. (2017) Analysis and pro jection of runoff variation in three Chinese rivers. Hydrology Research, 48(5), 1296–1310. Available from: https://doi.org/10. 2166/nh.2016.164
18. Wang, D. & Wang, A. (2017) Applicability assessment of GPCC and CRU precipitation products in China during 1901 to 2013. Climatic and Environmental Research, 22(4), 446–462 (in Chinese).
19. Li, Z., Li, Q., Wang, J., Feng, Y. & Shao, Q. (2020) Impacts of pro jected climate change on runoff in upper reach of Heihe River basin using climate elasticity method and GCMs. Science of the Total Environment, 716, 137072. Available from: https://doi. org/10.1016/j.scitotenv.2020.137072
20. Xiong, L., Yan, L., Li, L., Jiang, C. & Du, T. (2017) Advances in analysis of impacts of changing environments on extreme urban rainfall and drainage infrastructure. Advances in Water Science, 28(6), 930–942.
21. Eyring, V., Bony, S., Meehl, G.A., Senior, C.A., Stevens, B., Stouffer, R.J. et al. (2016) Overview of the Coupled Model Inter comparison Project Phase 6 (CMIP6) experimental design and organization. Geoscientific Model Development, 9(5), 1937–1958. Available from: https://doi.org/10.5194/gmd-9-1937-2016
22. Kim, Y., Rocheta, E., Evans, J.P. & Sharma, A. (2020) Impact of bias correction of regional climate model boundary conditions on the simulation of precipitation extremes. Climate Dynamics, 55(11–12), 3507–3526. Available from: https://doi.org/10.1007/ s00382-020-05462-5
23. O'Neill, B.C., Kriegler, E., Riahi, K., Ebi, K.L., Hallegatte, S., Carter, T.R. et al. (2013) A new scenario framework for climate change research: the concept of shared socioeconomic path ways. Climatic Change, 122(3), 387–400. Available from: https://doi.org/10.1007/s10584-013-0905-2
24. Hamed, M.M., Nashwan, M.S., Shahid, S., Ismail, T., Wang, X.J., Dewan, A. et al. (2022) Inconsistency in historical simulations and future projections of temperature and rainfall: a compari son of CMIP5 and CMIP6 models over Southeast Asia. Atmo spheric Research, 265, 105927. Available from: https://doi.org/ 10.1016/j.atmosres.2021.105927
25. Nashwan, M.S. & Shahid, S. (2022) Future precipitation changes in Egypt under the 1.5 and 2.0C global warming goals using CMIP6 multimodel ensemble. Atmospheric Research, 265, 105908. Available from: https://doi.org/10.1016/j.atmosres. 2021.105908
26. Yue, Y., Yan, D., Yue, Q., Ji, G. & Wang, Z. (2021) Future changes in precipitation and temperature over the Yangtze River Basin in China based on CMIP6 GCMs. Atmospheric Research, 264, 105828. Available from: https://doi.org/10.1016/j.atmosres.2021.105828
27. Shuaifeng, S. & Xiaodong, Y. (2022) Projected changes and uncer tainty in cold surges over northern China using the CMIP6 weighted multi-model ensemble. Atmospheric Research, 278, 106334. Available from: https://doi.org/10.1016/j.atmosres. 2022.106334
28. Chen, L. & Frauenfeld, O.W. (2014) A comprehensive evaluation of precipitation simulations over China based on CMIP5 multimo del ensemble projections. Journal of Geophysical Research Atmospheres, 119(10), 5767–5786. Available from: https://doi. org/10.1002/2013jd021190
29. Zhang, S. & Chen, J. (2021) Uncertainty in projection of climate extremes: a comparison of CMIP5 and CMIP6. Journal of Mete orological Research, 35(4), 646–662. Available from: https://doi. org/10.1007/s13351-021-1012-3
30. Wang, D. & Wang, A. (2017) Applicability assessment of GPCC and CRU precipitation products in China during 1901 to 2013. Climatic and Environmental Research, 22(4), 446–462 (in Chinese).
31. Reichler, T. & Kim, J. (2008) How well do coupled models simulate today's climate? Bulletin of the American Meteorological Society, 89(3), 303–312. Available from: https://doi.org/10.1175/bams 89-3-303
32. Friedman, J.H. (2001) Greedy function approximation: a gradient boosting machine. Annals of Statistics, 29(5), 1189–1232.
33. Guo, L.-Y., Gao, Q., Jiang, Z.-H. & Li, L. (2018) Bias correction and projection of surface air temperature in LMDZ multiple simula tion over central and eastern China. Advances in Climate Change Research, 9(1), 81–92. Available from: https://doi.org/ 10.1016/j.accre.2018.02.003
34. Patel, J., Gnanaseelan, C., Chowdary, J.S. & Parekh, A. (2021) A quantile mapping approach-based bias correction in Coupled Model Intercomparison Project Phase 5 models for decadal temperature predictions over India. International Journal of Cli matology, 42(4), 2455–2469. Available from: https://doi.org/10. 1002/joc.7376
35. Tong, Y., Gao, X., Han, Z., Xu, Y., Xu, Y. & Giorgi, F. (2020) Bias correction of temperature and precipitation over China for RCM simulations using the QM and QDM methods. Climate Dynamics, 57(5–6), 1425–1443. Available from: https://doi.org/ 10.1007/s00382-020-05447-4
36. Oh, S.-G. & Suh, M.-S. (2016) Comparison of projection skills of deterministic ensemble methods using pseudo-simulation data generated from multivariate Gaussian distribution. Theoretical and Applied Climatology, 129(1–2), 243–262. Available from: https://doi.org/10.1007/s00704-016-1782-1
37. Wang, D., Liu, J., Shao, W., Mei, C., Su, X. & Wang, H. (2021) Comparison of CMIP5 and CMIP6 multi-model ensemble for precipitation downscaling results and observational data: the case of Hanjiang River Basin. Atmosphere, 12(7), 867. Available from: https://doi.org/10.3390/atmos12070867
38. Wang, D., Liu, J., Wang, H., Shao, W., Mei, C. & Ding, X. (2022) Performance evaluations of CMIP6 and CMIP5 models for pre cipitation simulation over the Hanjiang River Basin, China. Journal of Water and Climate Change, 13(5), 2089–2106. Avail able from: https://doi.org/10.2166/wcc.2022.402
39. Yue, Y., Yan, D., Yue, Q., Ji, G. & Wang, Z. (2021) Future changes in precipitation and temperature over the Yangtze River Basin in China based on CMIP6 GCMs. Atmospheric Research, 264, 105828. Available from: https://doi.org/10.1016/j.atmosres.2021.105828
40. Yu, Y., Mao, J., Wullschleger, S.D., Chen, A., Shi, X., Wang, Y. et al. (2022) Machine learning-based observation-constrained projec tions reveal elevated global socioeconomic risks from wildfire. Nature Communications, 13(1), 1250. Available from: https:// doi.org/10.1038/s41467-022-28853-0
41. Xu, R., Chen, N., Chen, Y. & Chen, Z. (2020) Downscaling and pro jection of multi-CMIP5 precipitation using machine learning methods in the upper Han River basin. Advances in Meteorol ogy, 2020, 1–17. Available from: https://doi.org/10.1155/2020/ 8680436
42. Jose, D.M., Vincent, A.M. & Dwarakish, G.S. (2022) Improving mul tiple model ensemble predictions of daily precipitation and temperature through machine learning techniques. Scientific Reports, 12(1), 4678. Available from: https://doi.org/10.1038/ s41598-022-08786-w
43. Ahmed, K., Sachindra, D.A., Shahid, S., Iqbal, Z., Nawaz, N. & Khan, N. (2020) Multi-model ensemble predictions of precipita tion and temperature using machine learning algorithms. Atmospheric Research, 236, 104806. Available from: https://doi. org/10.1016/j.atmosres.2019.104806
44. Crawford, J., Venkataraman, K. & Booth, J. (2019) Developing cli mate model ensembles: a comparative case study. Journal of Hydrology, 568, 160–173. Available from: https://doi.org/10. 1016/j.jhydrol.2018.10.054
45. Acharya, N., Shrivastava, N.A., Panigrahi, B.K. & Mohanty, U.C. (2013) Development of an artificial neural network based multi-model ensemble to estimate the northeast monsoon rain fall over south peninsular India: an application of extreme learning machine. Climate Dynamics, 43(5–6), 1303–1310. Available from: https://doi.org/10.1007/s00382-013-1942-2
46. Wang, B., Zheng, L., Liu, D.L., Ji, F., Clark, A. & Yu, Q. (2018) Using multi-model ensembles of CMIP5 global climate models to reproduce observed monthly rainfall and temperature with machine learning methods in Australia. International Journal of Climatology, 38(13), 4891–4902. Available from: https://doi. org/10.1002/joc.5705
47. O'Neill, B. C., Tebaldi, C., van Vuuren, D. P., Eyring, V., Friedlingstein, P., Hurtt, G., Knutti, R., Kriegler, E., Lamarque, J.-F., Lowe, J., Meehl, G. A., Moss, R., Riahi, K., and Sanderson, B. M. (2016). The Scenario Model Intercomparison Project (ScenarioMIP) for CMIP6, Geosci. Model Dev., 9, 3461–3482. 
48. Meinshausen, M., Nicholls, Z. R. J., Lewis, J., Gidden, M. J., Vogel, E., Freund, M., Beyerle, U., Gessner, C., Nauels, A., Bauer, N., Canadell, J. G., Daniel, J. S., John, A., Krummel, P. B., Luderer, G., Meinshausen, N., Montzka, S. A., Rayner, P. J., Reimann, S., Smith, S. J., van den Berg, M., Velders, G. J. M., Vollmer, M. K., and Wang, R. H. J. (2020).The shared socio-economic pathway (SSP) greenhouse gas concentrations and their extensions to 2500, Geosci. Model Dev., 13, 3571–3605. 
49. Thrasher, B., Depsky, N., Taylor, M. A., and Nemani, R. (2022). NASA-NEX-GDDP-CMIP6 Dataset. NASA Earth Exchange.
50. Sellinger, C. E. (1996). Potential evapotranspiration and the water balance. Journal of the American Water Resources Association, 32(1), 49–56.
51. Alam, M. M., Begum, R. A., & Er, A. C. (2017). Spatial and temporal analysis of drought risk in Bangladesh using the Standardized Precipitation Evapotranspiration Index (SPEI). Theoretical and Applied Climatology, 128(1–2), 315–335. https://doi.org/10.1007/s00704-015-1701-2
52. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 785–794). ACM. https://doi.org/10.1145/2939672.2939785
53. Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29, 1189–1232.
54. Zhang, X., Ren, G., Yang, Y., Bing, H., Hao, Z. & Zhang, P. (2022) Extreme historical droughts and floods in the Hanjiang River Basin, China, since 1426. Climate of the Past, 18(8), 1775–1796. Available from: https://doi.org/10.5194/cp-18-1775-2022