Comparison of BP, PSO-BP and statistical models for predicting daily global solar radiation in arid Northwest China

Abstract Accurate prediction of global solar radiation (Rs) is important for understanding meteorological and hydrological processes, as well as the utilization of solar energy and development of clean production. In order to improve the accuracy and universality of daily Rs prediction in arid Northwest China, back-propagation neural network (BP) and BP optimized by the particle swarm optimization algorithm (PSO-BP) along with six statistical models (Angstrom-Prescott, Bristow-Campbell, Swartman-Ogunlade, Sebaii, Chen and Abdalla) were adopted and compared with measured Rs data from eight representative meteorological stations across four sub-climatic zones, including the temperate continental arid zone, temperate continental high temperature-arid zone, plateau continental semi-arid zone and temperate monsoon semi-arid zone. The results showed that PSO-BP models (coefficient of determination, R2, 0.7649–0.9678) were more accurate than BP models (R2, 0.7215–0.9632) and statistical models (R2, 0.5630–0.9445) for the daily Rs prediction in the four sub-zones of arid Northwest China. The PSO-BP1 and BP1 models (with sunshine duration, maximum and minimum temperature, relative humidity and extraterrestrial radiation as inputs), PSO-BP2 and BP2 (with sunshine duration, maximum and minimum temperature and extraterrestrial radiation as inputs) performed better than the other models, with R2, mean absolute error, root mean square error, relative root mean square error and Nash-Sutcliffe coefficient ranging 0.9228–0.9678, 1.5546–1.6309 MJ·m−2·d−1, 2.0054–1.7579 MJ·m−2·d−1, 0.1517–0.1329 and 0.9017–0.9604, respectively, among which the PSO-BP1 model provided the most accurate results. Sunshine-based models (R2, 0.7533–0.9678) were generally superior to temperature-based models (R2, 0.5630–0.8492), which indicated that sunshine duration was more influential for daily Rs prediction than temperature in this area. Overall, the PSO-BP model exhibits the best generalization capability and is recommended for more accurate daily Rs prediction in arid Northwest China.

[1]  O. Behar,et al.  Comparison of solar radiation models and their validation under Algerian climate - The case of direct irradiance , 2015 .

[2]  Jiafa Huang,et al.  Application of Improved PSO - BP Neural Network in Customer Churn Warning , 2018 .

[3]  F. Besharat,et al.  Empirical models for estimating global solar radiation: A review and case study , 2013 .

[4]  Hatice Citakoglu,et al.  Comparison of artificial intelligence techniques via empirical equations for prediction of solar radiation , 2015, Comput. Electron. Agric..

[5]  J. N. Black,et al.  The distribution of solar radiation over the Earth's surface , 1956 .

[6]  Shaohong Wu,et al.  Estimating the daily global solar radiation spatial distribution from diurnal temperature ranges over the Tibetan Plateau in China , 2013 .

[7]  Xurong Mei,et al.  Evaluation of temperature-based global solar radiation models in China , 2009 .

[8]  Ningbo Cui,et al.  Improvement of Makkink model for reference evapotranspiration estimation using temperature data in Northwest China , 2018, Journal of Hydrology.

[9]  A. Angstroem.  Solar and terrestrial radiation , 1924 .

[10]  Zhongjie Huan,et al.  Evaluation of global solar radiation using multiple weather parameters as predictors for South Africa provinces , 2014 .

[11]  Majid Jamil,et al.  Empirical correlation of estimating global solar radiation using meteorological parameters , 2015 .

[12]  Basharat Jamil,et al.  Statistical analysis of sunshine based global solar radiation (GSR) models for tropical wet and dry climatic Region in Nagpur, India: A case study , 2018 .

[13]  Yue Jia,et al.  National-scale assessment of pan evaporation models across different climatic zones of China , 2018, Journal of Hydrology.

[14]  S. Deng,et al.  A critical review of the models used to estimate solar radiation , 2017 .

[15]  Yousef A.G. Abdalla,et al.  New Correlations of Global Solar Radiation with Meteorological Parameters for Bahrain , 1994 .

[16]  David B. Ampratwum,et al.  Estimation of solar radiation from the number of sunshine hours , 1999 .

[17]  Laurel Saito,et al.  Empirical models for estimating daily global solar radiation in Yucatán Peninsula, Mexico , 2016 .

[18]  Ling Zou,et al.  Prediction and comparison of solar radiation using improved empirical models and Adaptive Neuro-Fuzzy Inference Systems , 2017 .

[19]  Nwokolo Samuel Chukwujindu.  A comprehensive review of empirical models for estimating global solar radiation in Africa , 2017 .

[20]  S. Kaseb,et al.  Potential of four different machine-learning algorithms in modeling daily global solar radiation , 2017 .

[21]  André St-Hilaire,et al.  A guideline to select an estimation model of daily global solar radiation between geostatistical interpolation and stochastic simulation approaches , 2017 .

[22]  O. Kisi,et al.  Solar radiation prediction using different techniques: model evaluation and comparison , 2016 .

[23]  Jia Yue,et al.  Calibration of Hargreaves model for reference evapotranspiration estimation in Sichuan basin of southwest China , 2017 .

[24]  Nadir Ahmed Elagib,et al.  New approaches for estimating global solar radiation across Sudan , 2000 .

[25]  Xin Ma,et al.  Evaluation and development of empirical models for estimating daily and monthly mean daily diffuse horizontal solar radiation for different climatic regions of China , 2019, Renewable and Sustainable Energy Reviews.

[26]  Ningbo Cui,et al.  Evaluation of random forests and generalized regression neural networks for daily reference evapotranspiration modelling. , 2017 .

[27]  K. K. Gopinathan,et al.  A general formula for computing the coefficients of the correlation connecting global solar radiation to sunshine duration , 1988 .

[28]  Wenzhi Zhao,et al.  Validation of five global radiation models with measured daily data in China , 2004 .

[29]  Lifeng Wu,et al.  Potential of kernel-based nonlinear extension of Arps decline model and gradient boosting with categorical features support for predicting daily global solar radiation in humid regions , 2019, Energy Conversion and Management.

[30]  Sara Saeidi Ramiyani,et al.  A hybrid computational approach to estimate solar global radiation: An empirical evidence from Iran , 2013 .

[31]  Xiaofan Zeng,et al.  Study of solar radiation prediction and modeling of relationships between solar radiation and meteorological variables , 2015 .

[32]  E. Taşdemiroǧlu,et al.  A new method for estimating solar radiation from bright sunshine data , 1984 .

[33]  V. Bahel,et al.  A correlation for estimation of global solar radiation , 1987 .

[34]  R. Swartman,et al.  Solar radiation estimates from common parameters , 1967 .

[35]  Ningbo Cui,et al.  Estimation of soil temperature from meteorological data using different machine learning models , 2019, Geoderma.

[36]  Jesús Polo,et al.  A new statistical approach for deriving global solar radiation from satellite images , 2009 .

[37]  Lifeng Wu,et al.  New combined models for estimating daily global solar radiation based on sunshine duration in humid regions: A case study in South China , 2018 .

[38]  Michael J. Savage,et al.  Comparison of estimates of daily solar radiation from air temperature range for application in crop simulations , 2008 .

[39]  Kasra Mohammadi,et al.  A statistical comparative study to demonstrate the merit of day of the year-based models for estimation of horizontal global solar radiation , 2014 .

[40]  Saad Mekhilef,et al.  Adaptive neuro-fuzzy approach for solar radiation prediction in Nigeria , 2015 .

[41]  A. A. El-Sebaii,et al.  Estimation of global solar radiation on horizontal surfaces in Jeddah, Saudi Arabia , 2009 .

[42]  Ali Rahimikhoob,et al.  Estimating global solar radiation using artificial neural network and air temperature data in a semi-arid environment , 2010 .

[43]  Lifeng Wu,et al.  Empirical and machine learning models for predicting daily global solar radiation from sunshine duration: A review and case study in China , 2019, Renewable and Sustainable Energy Reviews.

[44]  Adel Mellit,et al.  Prediction of daily and mean monthly global solar radiation using support vector machine in an arid climate , 2016 .

[45]  Milan Despotovic,et al.  Data mining with various optimization methods , 2014, Expert Syst. Appl..

[46]  Lifeng Wu,et al.  Evaluation and development of temperature-based empirical models for estimating daily global solar radiation in humid regions , 2018 .

[47]  Milan Despotovic,et al.  Review and statistical analysis of different global solar radiation sunshine models , 2015 .

[48]  Abbas Rohani,et al.  A novel soft computing model (Gaussian process regression with K-fold cross validation) for daily and monthly solar radiation forecasting (Part: I) , 2018 .

[49]  Shahaboddin Shamshirband,et al.  A comparative evaluation for identifying the suitability of extreme learning machine to predict horizontal global solar radiation , 2015 .

[50]  Cristina Alonso-Tristán,et al.  Mathematical interpolation methods for spatial estimation of global horizontal irradiation in Castilla-León, Spain: A case study , 2017 .

[51]  Youcef Messlem,et al.  Estimation of the daily global solar radiation based on Box–Jenkins and ANN models: A combined approach , 2016 .

[52]  G. Campbell,et al.  On the relationship between incoming solar radiation and daily maximum and minimum temperature , 1984 .

[53]  Soteris A. Kalogirou,et al.  An adaptive wavelet-network model for forecasting daily total solar-radiation , 2006 .

[54]  Ozgur Kisi,et al.  Modeling solar radiation of Mediterranean region in Turkey by using fuzzy genetic approach , 2014 .

[55]  John Boland,et al.  Preliminary survey on site-adaptation techniques for satellite-derived and reanalysis solar radiation datasets , 2016 .

[56]  Por Lip Yee,et al.  Estimating the diffuse solar radiation using a coupled support vector machine–wavelet transform model , 2016 .

[57]  Ningbo Cui,et al.  Development of data-driven models for prediction of daily global horizontal irradiance in Northwest China , 2019, Journal of Cleaner Production.

[58]  Z. Samani,et al.  Estimating Potential Evapotranspiration , 1982 .

[59]  Kada Bouchouicha,et al.  Estimating the global solar irradiation and optimizing the error estimates under Algerian desert climate , 2019, Renewable Energy.

[60]  Jalal Shiri,et al.  Artificial neural networks vs. Gene Expression Programming for estimating outlet dissolved oxygen in micro-irrigation sand filters fed with effluents , 2013 .

[61]  Dalibor Petković,et al.  Potential of adaptive neuro-fuzzy system for prediction of daily global solar radiation by day of the year , 2015 .

[62]  Yingni Jiang,et al.  Computation of monthly mean daily global solar radiation in China using artificial neural networks and comparison with other empirical models , 2009 .

[63]  Hamid Barati,et al.  Application of Fully Recurrent (FRNN) and Radial Basis Function (RBFNN) Neural Networks for Simulating Solar Radiation , 2014 .

[64]  H. Cai,et al.  Evaluation of SVM, ELM and four tree-based ensemble models for predicting daily reference evapotranspiration using limited meteorological data in different climates of China , 2018, Agricultural and Forest Meteorology.

[65]  Richard G. Allen,et al.  Self-Calibrating Method for Estimating Solar Radiation from Air Temperature , 1997 .