پیوندهای مفید
اخبار و اعلانات
آمار
| تعداد نشریات | 161 |
| تعداد شماره‌ها | 6,532 |
| تعداد مقالات | 70,504 |
| تعداد مشاهده مقاله | 124,121,722 |
| تعداد دریافت فایل اصل مقاله | 97,229,070 |
معرفی یک مدل غیرخطی بر اساس هیبرید ماشین‌های یادگیری به منظور مدل‌سازی و پیشبینی بارش و مقایسه با روش SDSM (مطالعات موردی: شهرکرد، بارز و یاسوج) | ||
| تحقیقات آب و خاک ایران | ||
| مقاله 4، دوره 51، شماره 2، اردیبهشت 1399، صفحه 325-339 اصل مقاله (2.07 M) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22059/ijswr.2019.285141.668258 | ||
| نویسندگان | ||
| مهدی ولیخان انارکی1؛ سید فرهاد موسوی2؛ سعید فرزین* 3؛ حجت کرمی3 | ||
| 1دانش‌آموخته کارشناسی ارشد، گروه مهندسی و مدیریت منابع آّب، دانشکده مهندسی عمران، دانشگاه سمنان | ||
| 2گروه مهندسی آب و سازه‌های هیدرولیکی، دانشکده مهندسی عمران، دانشگاه سمنان | ||
| 3استادیار گروه مهندسی آب و سازه‌های هیدرولیکی، دانشکده مهدسی عمران، دانشگاه سمنان | ||
| چکیده | ||
| در پژوهش حاضر، مدلی هیبریدی بر مبنای روشهای غیرخطی شامل رگرسیون تطبیقی چندگانه اسپلاین (MARS)، شبکه‌عصبی مصنوعی (ANN) و K نزدیکترین همسایه (KNN) به منظور ریزمقیاسنمایی و پیشبینی بارش ایستگاه‌های شهرکرد، بارز و یاسوج تحت شرایط تغییر اقلیم معرفی شده است. مدل هیبریدی ارائه شده، مانند مدل ریزمقیاسنمایی SDSM، از دو گام طبقهبندی و رگرسیون تشکیل شده است. مدل MARS برای طبقهبندی وقوع بارش و الگوریتمهای ANN و KNN برای تعیین مقدار بارش بهکار برده شدهاند. نتایج مدل MARS برای تعیین وقوع بارش نشان میدهد که مدل مذکور نسبت به مدل SDSM از دقت بیشتری برخوردار است. با مقایسه نتایج ریزمقیاسنمایی مشاهده میشود که الگوریتم ANN نسبت به مدل SDSM و الگوریتم KNN دارای دقت بیشتری در تعیین میانگین سالانه و ماهانه بارش است. بهطوری که در ایستگاه شهرکرد مقدار معیار R برای الگوریتم ANN نسبت به مدل SDSM به اندازه 54 درصد دقیقتر است. همچنین، الگوریتمهای ANN، KNN و SDSM از نظر بیشترین دقت در سه ایستگاه بررسی شده، با در نظر گرفتن میانگین، انحراف معیار و ضریب چولگی ماهانه به ترتیب در رتبههای اول، دوم و سوم قرار داده میشوند. در نهایت، مقدار تغییرات بارش در دوره آینده نزدیک (2020-2040) و آینده دور (2070-2100) تحت سناریوهای A2 و B2 مدل HADCM3 بررسی شد. نتایج نشان داد که کمترین کاهش بارش (2 درصد) مربوط به الگوریتم ANN (در ایستگاه شهرکرد) و سناریوی A2 در دوره آینده نزدیک و بیشترین آن (54 درصد) مربوط به مدل SDSM (در ایستگاه یاسوج) و سناریوی A2 در دوره آینده دور میباشد. در نهایت می‌توان نتیجه گرفت که هیبرید ماشین‌های یادگیری نسبت به مدل SDSM، از دقت بیشتری برخوردار است و می‌توان از مدل معرفی شده به عنوان جایگزین مدل SDSM استفاده کرد. | ||
| کلیدواژه‌ها | ||
| تغییر اقلیم؛ ریزمقیاسنمایی؛ ماشین‌های یادگیری؛ بارش | ||
| عنوان مقاله [English] | ||
| Introducing a Nonlinear Model Based on Hybrid Machine Learning for Modeling and Prediction of Precipitation and Comparison with SDSM Method (Cases Studies: Shahrekord, Barez, and Yasuj) | ||
| نویسندگان [English] | ||
| Mahdi Valikhan Anaraki1؛ Sayed-Farhad Mousavi2؛ Saeed Farzin3؛ hojat karami3 | ||
| 1Graduated MSc., Department of Water Resources Engineering and Management, Faculty of Civil Engineering, Semnan University, Semnan, Iran. | ||
| 2Department of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering, Semnan University | ||
| 3Assistant Professor, Department of Water Engineering and Hydraulic Structures, Faculty of Civil Engineering, Semnan Univercity, Semnan, Iran. | ||
| چکیده [English] | ||
| In the present study, a nonlinear hybrid model, based on multivariate adaptive regression splines (MARS), artificial neural networks (ANN) and K-nearest neighbor (KNN) has been presented for downscaling the precipitation of Shahrekord, Barez, and Yasuj under climate change conditions. This model, similar to SDSM, is composed of two steps; classification and regression. The MARS model is employed for classification of precipitation occurrence and the ANN and KNN are employed for determination of the amount of precipitation. The results of MARS showed that the mentioned model is more accurate than the SDSM model. Comparing the results of downscaled precipitation showed that the ANN model is more accurate than the SDSM and KNN in prediction of average annual and monthly precipitation. So that the R value for ANN was 54% more than the one in SDSM model, in Shahrekord. Also, according to the highest accuracy, standard deviation and skewness coefficient, the ANN, KNN and SDSM model ranked first, second, and third, respectively, for prediction of monthly average precipitation in three investigated stations. Eventually, the precipitation changes in the near future (2020-2040) and far future (2070-2100) periods were investigated under the A2 and B2 scenarios of the HADCM3 model. Results revealed that the lowest precipitation reduction is corresponded to ANN (in Shahrekord) and A2 scenario in the near future period and the highest precipitation reduction is corresponded to SDSM (in Yasuj) and A2 scenario in the far future period. Finally, it can be concluded that the proposed model is more accurate than the SDSM model and can be used as an alternative to the SDSM model. | ||
| کلیدواژه‌ها [English] | ||
| climate change, Downscaling, Machine learning, precipitation | ||
| مراجع | ||
|
Ahmadi, A., Moridi, A., Lafdani, E. K. and Kianpisheh, G. (2014). Assessment of climate change impacts on rainfall using large scale climate variables and downscaling models–A case study. Journal of Earth System Science, 123(7), 1603-1618. Ahmed, K., Shahid, S., Nawaz, N. and Khan, N. (2019). Modeling climate change impacts on precipitation in arid regions of Pakistan: a non-local model output statistics downscaling approach. Theoretical and Applied Climatology, 137(1-2), 1347-1364. Al-Mukhtar, M. and Qasim, M. (2019). Future predictions of precipitation and temperature in Iraq using the statistical downscaling model. Arabian Journal of Geosciences, https://doi.org/10.1007/s12517-018-4187-x. Araghinejad, S. (2014). Data-driven modeling: Using MATLAB in Water Resources and Environmental Engineering. Springer, Water Science and Technology Library, 67. Ashofteh, S. A. and Bozorg-Haddad, O. (2013). Use of multi-conditional functions in the field of reservoir management and under climate change. Iranian Journal of Soil and Water Research, 45(4), 397-404. (In Farsi). Beheshti, M., Heidari, A. and Saghafian. (2019). Susceptibility of Hydropower Generation to Climate Change: Karun III Dam Case Study. Water, 11(5), 1025. Campozano, L., Tenelanda, D., Sanchez, E., Samaniego, E. and Feyen, J. (2016). Comparison of statistical downscaling methods for monthly total precipitation: Case study for the Paute River Basin in Southern Ecuador. Advances in Meteorology, 2016, ID: 6526341. Chaudhary, S., Agarwal, A. and Nakamura, T. (2019). Rainfall Projection in Yamuna River Basin, India, Using Statistical Downscaling. In: Rathinasamy M., Chandramouli S., Phanindra K., Mahesh U. (eds) Water Resources and Environmental Engineering II. Springer, Singapore. Chen, S. T., Yu, P. S. and Tang, Y. H. (2010). Statistical downscaling of daily precipitation using support vector machines and multivariate analysis. Journal of Hydrology, 385(1-4), 13-22. Devak, M., Dhanya, C. T. and Gosain, A. K. (2015). Dynamic coupling of support vector machine and K-nearest neighbour for downscaling daily rainfall. Journal of Hydrology, 525, 286-301. Dorji, S., Herath, S. and Mishra, B. (2017). Future climate of colombo downscaled with SDSM-neural network. Climate, 5(1), 24. Friedman, J. H. (1991). Multivariate adaptive regression splines. The Annals of Statistics, 19(1), 1-67. Ghamghami, M., Ghahreman, N. and Araghinejad, S. (2010). An evaluation of the performance of an advanced approach of the K-nearest neighbor in simulating the daily meteorological data. Iranian Journal of Soil and Water Research, 42(1), 45-54. (In Farsi). Hadi, S. J. and Tombul, M. (2018). Streamflow forecasting using four wavelet transformation combinations approaches with data-driven models: A comparative study. Water Resources Management, 32(14), 4661-4679. Haji Hosseini, R., Golian, S. and Yazdi, J. (2018). Evaluation of data-driven models to downscale rainfall parameters from global climate models outputs: The case study of Latyan watershed. Journal of Water and Climate Change, https://doi.org/10.2166/wcc.2018.191 Harpham, C. and Wilby, R. L. (2005). Multi-site downscaling of heavy daily precipitation occurrence and amounts. Journal of Hydrology, 312(1-4), 235-255. Hessami, M., Gachon, P., Ouarda, T. B. M. J. and St-Hilaire, A. (2008). Automated regression-based statistical downscaling tool. Environmental Modelling & Software,23(6), 813–834. IPCC-TGCIA. (1999). Guidelines on the Use of Scenario Data for Climate Impact and Adaptation Assessment, Version 1. Intergovernmental Panel on Climate Change, 69 p. IPCC-TGCIA. (2007). General Guidelines on the Use of Scenario Data for Climate Impact and Adaptation Assessment. Version 1, 312, Intergovernmental Panel on Climate Change, 66 p. Khashei, A., Shahidi, A., Pourrezabilondi, M., Amirabadizadeh, A. and Jafarzadeh, A. (2018). Performance assessment of ANN and SVR for downscaling of daily rainfall in dry regions. Iranian Journal of Soil and Water Research, 49(4), 781-793. (In Farsi). Lee, K. T., Hung, W. C. and Meng, C. C. (2008). Deterministic insight into ANN model performance for storm runoff simulation. Water Resources Management, 22(1), 67-82. Mekanik, F., Imteaz, M. A., Gato-Trinidad, S. and Elmahdi, A. (2013). Multiple regression and artificial neural network for long-term rainfall forecasting using large scale climate modes. Journal of Hydrology, 503, 11-21. Mesbahzadeh, T., Miglietta, M. M., Miakbari, M., Soleimani Sardoo, F. and Abdolhoseini, M. (2019). Joint Modeling of Precipitation and Temperature Using Copula Theory for Current and Future Prediction under Climate Change Scenarios in Arid Lands (Case Study, Kerman Province, Iran). Advances in Meteorology, https://doi.org/10.1155/2019/6848049. Modaresi, F. Araghinejad, S. and Ebrahimi, K. (2018). A comparative assessment of artificial neural network, generalized regression neural network, least-square support vector regression, and K-nearest neighbor regression for monthly streamflow forecasting in linear and nonlinear conditions. Water Resources Management, 32(1), 243-258. Moghadam, S. H., Ashofteh, P. S. and Loáiciga. H. A. (2019). Application of Climate Projections and Monte Carlo Approach for Assessment of Future River Flow: Khorramabad River Basin, Iran. Journal of Hydrologic Engineering, https://doi.org/10.1061/(ASCE)HE.1943-5584.0001801. Morita, T., (2001). 2.5. 1.1 IPCC Emissions Scenarios and the SRES Process. IPCC TAR WG3. Nourani, V., Baghanam, A. H. and Gokcekus, H. (2018). Data-driven ensemble model to statistically downscale rainfall using nonlinear predictor screening approach. Journal of Hydrology, 565, 538-551. Nourani, V., Razzaghzadeh, Z., Baghanam, A.H. and Molajou, A. (2019). Theoretical and Applied Climatology, 137(3-4): 1729-1746. Rezaie-Balf, M., Zahmatkesh, Z and. Kim, S. (2017). Soft computing techniques for rainfall-runoff simulation: Local non–parametric paradigm vs. model classification methods. Water Resources Management, 31(12), 3843-3865. Salajegheh, A., Rafiei Sardoii, E., Moghaddamnia, A., Malekian, A., Araghinejad, S., Khalighi Sigarodi, S. and Pourjam, A. S. (2018). Performance assessment of LARS-WG and SDSM downscaling models in simulation of precipitation and temperature. Iranian Journal of Soil and Water Research, 48(2), 253-262. (In Farsi). Sayedi, A., Taleb beydokhti, N., Najarchi, M. and Najafizadeh, M. M. (2019). Investigation into the Effects of Climatic Change on Temperature, Rainfall, and Runoff of the Doroudzan Catchment, Iran, Using the Ensemble Approach of CMIP3 Climate Models. Advances in Meteorology, https://doi.org/10.1155/2019/6357912. Singh, K. K., Pal, M. and Singh, V. P. (2010). Estimation of mean annual flood in Indian catchments using back propagation neural network and M5 model tree. Water Resources Management, 24(10), 2007-2019. Wilby, R. L., Dawson, C. W. and Barrow, E. M. (2002). SDSM- A decision support tool for the assessment of regional climate change impacts. Environmental Modelling & Software, 17(2), 145-157. Wu, C. L., Chau, K. W. and Fan, C. (2010). Prediction of rainfall time series using modular artificial neural networks coupled with data-preprocessing techniques. Journal of Hydrology, 389(1-2), 146-167.
| ||
|
آمار تعداد مشاهده مقاله: 863 تعداد دریافت فایل اصل مقاله: 497 |
||