Combining soft Computing Model Based on Machine Learning Algorithm and Principal Component Analysis for Precipitation Forecasting

Document Type : Original Article

Author

Faculty of Agriculture, Azarbaijan Shahid Madani University, Tabriz, Iran

Abstract

The effect of precipitation changes on water resources, agricultural production reveals the need for accurate methods for precipitation forecasting. In this research, one of the soft computing methods was developed in order to forecast precipitation with the data reduction approach. Input data of model was mean air temperature, dew point temperature, mean sea level pressure, mean station pressure, mean relative humidity and mean wind speed at Tabriz, Ahar and Jolfa stations. The method used in this study includes Epsilon and Nu support vector regression. In all studied stations, the use of Nu support vector regression compared to Epsilon reduced the error so that UII values ​​with Nu support vector regression in Tabriz, Ahar and Jolfa stations were decreased 19.19, 5.88 and 15.78%, respectively. The results indicate the limitation of using the data reduction approach for data with KMO factor lower than 0.5, which included Tabriz and Ahar stations. Principal component analysis in both types of support vector regression increased the performance of the model so that in Jolfa station by using principal component analysis d values ​​of Epsilon and Nu support vector regression increased by 16.6 and 17.5%. Execution of Verimax rotation in preprocessing of input data to regression was stronger than principal component analysis. In this regard, RRMSE and RMSE values ​​in Jolfa station using Epsilon support vector regression were decreased 6.66 and 6.45%. Therefore, principal component analysis is a suitable tool to improve the performance of soft computing methods by regarding the relevant constraints.

Keywords

Main Subjects

References

صلی (MLR-PCA) در پیش­بینی تبخیر - تعرق مرجع. نشریه آب و خاک،سال24 بیست و چهارم، شماره 6، ص 119-1186.
شیخ الاسلامی، ن.، قهرمان، ب.، مساعدی، ا.، داوری، ک.، و م. مهاجرپور. 1393. پیش­بینی تبخیر و تعرق گیاه مرجع (ET0) با استفاده از روش آنالیز مولفه­های اصلی (PCA) و توسعه مدل رگرسیون خطی چندگانه (MLR-PCA) (مطالعه موردی: ایستگاه مشهد). نشریه آب و خاک (علوم و صنایع کشاورزی)، سال بیست و هشتم، شماره 2، ص429-.420.
ضابط پیشخانی، ن.، سیدیان، م.، حشمت پور، ع.، و ح. روحانی. 1395. مقایسه الگو سازی بارندگی ماهانه با مدل های SVMو ANFIS (مطالعه موردی: شهر گنید کاووس). نشریه آب و خاک (علوم و صنایع کشاورزی)، سال سی، شماره 1، ص 246-236.
ناظم السادات، ج.، و ا. شیروانی. 1384. پیش بینی دمای سطح آب خلیج فارس با استفاده از رگرسیون چندگانه و تحلیل مولفه های اصلی. علوم و فنون کشاورزی و منابع طبیعی، سال نه، شماره سه، ص 1-10.
Chen, X., and S. Zhu. 2013. Improved hybrid model based on support vector regression machine for monthly precipitation forecasting. Journal of computers, 8(1): 232-239.
Du, J., Y. Liu, Y. Yu and W. Yan.2017. A Prediction of Precipitation Data Based on Support Vector Machine and Particle Swarm Optimization (PSO-SVM) Algorithms. Algorithms, 10(57): 1-15.
Hamidi, O., J. Poorolajal, M.  Sadeghifar, H. Abbasi, Z. Maryanaji, H.R.  Faridi and L.Tapak.2015. A comparative study of support vector machines and artificial neural networks for predicting precipitation in Iran. Theor Appl Climatol, 119: 723–731.
Hasan, N., N.Chandra Nath and R. Islam Rasel.2015. A support vector regression model for forecasting rainfall. Proceedings of International Conference on Electrical Information and Communication Technology, 554-559.
Ingsrisawang, L., S. Ingsriswang, S.Somchit, P. Aungsuratana and W. Khantiyanan. 2008. Machine learning techniques for short-term rain forecasting system in the northeastern part of Thailand. International Journal of Computer, Electrical, Automation, Control and Information Engineering, 2(5): 1422-1427.
Jiajia, H., CH. Kai, CH. Jinsong, X. Wenwen, T. Li andL.Jun.2017.A multi-time scale SVM method for local short-term rainfall prediction. Meteorology, 43(4): 402–412.
Langhammer, J. and J. Cˇ esák.2016. Applicability of a nu-support vector regression model for the completion of missing data in hydrological time series. Water, 8(560): 1-25.
Moon, S. andY.Kim.2020. An improved forecast of precipitation type using correlation-based feature selection and multinomial logistic regression. Atmospheric Research, 240: 1-14.
Ortiz-Garcı, E.G., S. Salcedo-Sanz and C. Casanova-Mateo. 2014. Accurateprecipitation prediction with support vector classifiers: a studyincluding novel predictive variables and observational data. Atmospheric Research, 139: 128–136.
Papacharalampous, G., H. TyralisandD. Koutsoyiannis.2018.Univariate Time Series Forecasting of Temperature and Precipitation with a Focus on Machine Learning Algorithms: a Multiple-Case Study from Greece. Water Resources Management, 32: 5207–5239.
Pannkkong, W., V.H. Pham and V.N.Huynh. 2016. A hybrid model of ARIMA, ANNs and k-means clustering for time series forecasting. Lecture Notes in Computer Science, 8(4): 30-53.
Samui, P., V.Ravibabu Mandla, A.Krishnaand T. Teja.2011. Prediction of Rainfall Using Support Vector Machine and Relevance Vector Machine, Earth Science India, 4: 188-200.
Sehad, M., M. Lazri andS.Ameur.2017. Novel SVM-based technique to improve rainfall estimation over the Mediterranean region (north of Algeria) using the multisperctral MSG SEVIRI imagery. Advances in Space Research, 59: 1381-1394.
 Shenify, M., A.S. Danesh, M. Gocić, R.S. Taher, A.W. Abdul Wahab, A.Gani, SH. Shamshirband and D. Petković.2016. Precipitation Estimation Using Support Vector Machine with Discrete Wavelet Transform. Water Resource Management, 30: 641–652.
 
Soares dos Santos, T., D. Mendes and R Rodrigues Torres. 2016. Artificial neural networks and multiple linear regression model using principle components to estimate rainfall over South America. Nonlinear Processes Geophysics, 23: 13-20.
UlSaufie, A.Z., A.S. Yahya and N.A. Ramli. 2011. Improving multiple linear regression model using principal componentanalysis for predicting PM10 concentration in Seberang Prai, PulauPinang. International Journal of Environmental Sciences, 2(2): 403-410.
Zaynoddin, M., H. Bonakdari, A.Azari, I.Ebtehaj, B.Gharabaghi and H.Riahi Madavar. 2018. Novel hybrid linear stochastic with non-linear extreme learning machine methods for forecasting monthly rainfall a tropical climate. Journal of Environmental Management, 222: 190-206.
Zhang, CH., H.Wang, J.Zeng, L.MA and L. Guan.2020. Short-term dynamic radar quantitative precipitation estimation based on wavelet transform and support vector machine. Journal of Meteorological Research, 34: 413-426.
 

Files

Share

How to cite

Statistics