ارائه مدل تلفیقی عددی-یادگیری ماشین Galerkin-MARS به‌منظور مدل‌سازی خشک‌سالی هواشناسی (مطالعه موردی: استان خوزستان)

نوع مقاله : مقاله پژوهشی

نویسندگان

گروه مهندسی احیاء مناطق خشک و کوهستانی، دانشکده منابع طبیعی، دانشگاه تهران، ایران.

10.22059/jwim.2025.392401.1213

چکیده

خشک‌سالی یکی از بلایای طبیعی، به‌ویژه در مناطق خشک و نیمه‌خشک به‌شمار می‌آید. تحلیل شرایط، مشخصات و وﺿﻌﻴﺖ ﺧﺸک‌سالی ﺑﻪﻋﻨﻮان یک نوع خطر ﻃﺒﻴﻌﻲ در مناطق مختلف ﺑﺎ تمرکز بر جمع‌آوری راهکارهای ﻣﻘﺎﺑﻠﻪ ﺑﺎ خشک‌سالی و ﻣﺪﻳﺮﻳﺖ مخاطرات آن دارای اهمیت بسیار بالایی می‌باشد. در پژوهش حاضر، تجزیه و تحلیل و پیش‌بینی خشک‌سالی هواشناسی در استان خوزستان با مدل‌های انفرادی Galerkin و MARS و مدل تلفیقی هوشمند Galerkin-MARS در طول دوره آماری 30 ساله (1399-1369) مورد بررسی قرار گرفت. جهت ارزیابی شرایط خشک‌سالی، از شاخص بارش استاندارد شده (SPI) ‌حاصل از داده‌های هشت ایستگاه سینوپتیک استان خوزستان استفاده شد. در گام بعدی، نتایج مدل‌سازی توسط مدل‌های ذکر شده و با استفاده از شاخص‌های نیکویی برازش با یکدیگر مقایسه شدند. نتایج بیانگر این بود که مدل تلفیقی Galerkin-MARS به‌منظور برآورد شاخص SPI در استان خوزستان از کارایی بسیار بالایی برخوردار است. هم‌چنین پنجره‌های زمانی بلندمدت SPI از دقت بالاتری نسبت به پنجره‌های زمانی کوتاه مدت در منطقة مورد مطالعه برخوردار بودند. به‌طور کلی می‌توان گفت که تلفیق مدل‌های عددی با یادگیری ماشین در استان خوزستان، افزایش دقت در مدل‌سازی نمایه SPI را به دنبال دارد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Presenting a combined numerical-machine learning model Galerkin-MARS for modeling meteorological drought (Case study: Khuzestan Province)

نویسندگان [English]

  • Sadaf Piri
  • Mohammad Ansari ghojghar
Department of Reclamation of arid and mountainous regions Engineering, Faculty of Natural Resources, University of Tehran, Iran.
چکیده [English]

Drought is one of the natural hazards, especially in arid and semi-arid regions. Analyzing the conditions, characteristics, and status of drought as a type of natural hazard in different regions with a focus on gathering solutions to cope drought and manage its risks is of great importance. In the present study, the analysis and prediction of meteorological drought in Khuzestan province was investigated with individual Galerkin and MARS models and the combined Galerkin-MARS model during a 30-year statistical period (1990-2020). To assess drought conditions, the Standardized Precipitation Index (SPI) obtained from data from eight synoptic stations was used. In the next step, the modeling results were compared with the aforementioned models using goodness-of-fit indices. The results indicated that the combined Galerkin-MARS model is highly efficient for estimating SPI in Khuzestan province. Also, long-term SPI time windows had higher accuracy than short-term time windows in the study area. In general, it can be said that combining numerical models with machine learning in Khuzestan Province leads to increased accuracy in SPI modeling.

کلیدواژه‌ها [English]

  • Forecasting models
  • Meteorological data
  • Nonlinear prediction
  • SPI
  1. Adnan, R. M., Dai, H. L., Kuriqi, A., Kisi, O., & Kermani, M. Z. (2023). Improving drought modeling    based on new heuristic machine learning methods. Ain Shams Engineering Journal, 14(2023), 1-13.
  2. Agana, N.A., & Homaifar, A. (2018). EMD-based predictive deep belief network for time series prediction: an application to drought forecasting. Hydrology, 5. https://doi. org/10.3390/hydrology5010018.
  3. Ahmed, S. M. (2020). Impacts of drought, food security policy and climate change on performance of irrigation schemes in Sub -saharan Africa: The case of Sudan. Agricultural Water Management, 232, 106064.
  4. Babaali, H,. Nohani, E., & Dehghani, R. (2024). Evaluation of the Standardized Precipitation Index with a hybrid model based on machine learning (Case study: Lorestan province). Journal of Climate Research, Accepted Manuscript Available Online from 02 December 2024. (In Persian).
  5. Bazrafshan, O., Salajegheh, A., Mahdavi, M., & Fatehi, A. (2015). A study of Efficiency of the Hybrid model Artificial Neural Network Models-stochastic in Hydrological Drought Forecasting using kappa statistics (Case study: Gamasiab Watershed Basin). Iranian Journal of Watershed Management Science, 8(27), 35-48. (In Persian).
  6. Belayneh, A., Adamowski, J., Khalil, B., & Quilty, J. (2016). Coupling machine learning methods with wavelet transforms and the bootstrap and boosting ensemble approaches for drought prediction. Atmospheric Research, 172, 37-47.
  7. Belytschko, T., Lu, Y. Y., & Gu, L. (1994). Element‐free Galerkin methods. International Journal for Numerical Methods in Engineering, 3737(22), 229229-256256.
  8. Fawzy, S., Osman, A. I., Doran, J., & Rooney, D. W. (2020). Strategies for mitigation of climate change: a review. Environmental Chemistry Letters, 18, 2069-2094.
  9. Friedman, J. H. (1991). Multivariate adaptive regression splines. Stat., 19, 1-141.
  10. Hosseini-Moghari, S. M., & Araghinejad, S. (2016). Application of Statistical, Fuzzy and Perceptron Neural Networks in Drought Forecasting (Case study: Gonbad-e Kavous Station). Water and Soil, 30(1), 247-259. (In Persian).
  11. Liu, G. R., Chen, X. L., & Reddy, J. N. (2002). Buckling of symmetrically laminated composite plates using the element-free Galerkin method. International Journal of Structural Stability and Dynamics2(03), 281-294.
  12. McKee, T. B., Doesken, N. J., & Kleist, J. (1993, January). The relationship of drought frequency and duration to time scales. In Proceedings of the 8th Conference on Applied Climatology (Vol. 17, No. 22, pp. 179-183).
  13. Negahban, S., Mokarram, M., & Moradizadeh Kermani, R. (2024). Assessing the efects of drought hazardos on rural communites surrounds Maharlu Lake, Iran. Environmental Hazards Management, 11(1), 1-13.
  14. Mohammadi, J., Vafaeinezhad, A., Behzadi, S., Aghamohammadi, H., & Hemmasi, A. (2022). Drought prediction and modeling by hybrid wavelet method and neural network algorithms. RS and GIS for Natural Resources, 4(13), 87-111. (In Persian).
  15. Moisa, M. B., Merga, B. B., & Gemeda, D.O. (2022). Multiple indices-based assessment of agricultural drought: A case study in Gilgel Gibe Sub-basin, Southern Ethiopia. Theoretical and Applied Climatology, 148(1), 455-464. doi:10.1007/s00704-022-03962-4.
  16. Raymond, C., Horton, R. M., Zscheischler, J., Martius, O., AghaKouchak, A., Balch, J., Bowen, S. G., Camargo, S. J., Hess, J., & Kornhuber, K. (2020). Understanding and managing connected extreme events. Nature climate change, 10(7), 611-621.
  17. Shamloo, N., Sattari, M. T., Valizadeh Khalil, K., & Apaydin, H. (2023). Evaluation of Combined Agricultural Drought Index (CDI), Prediction Methods Based on Satellite Images via Deep Learning and Machine Learning Approaches. Water and Soil, 37(5), 787-807. (In Persian).
  18. Wilhite, D. A., & Glantz, M. H. (1985). Understanding: the drought phenomenon: the role of definitions. Water international, 10(3), 111-120.
  19. Woli, P., Jones, J. W., Ingram, K. T., & Fraisse, C. W. (2012). Agricultural reference index for drought (ARID). Agronomy Journal, 104(2), 287-300.
  20. Yousefi, H., & Moridi, A. (2022). Multiobjective optimization of agricultural planning considering climate change impacts: Minab reservoir upstream watershed in Iran. Journal of Irrigation and Drainage Engineering, 148(4), 04022007. (In Persian).