干旱区生态环境知识资源中心(Arid): Comparison of BP, PSO-BP and statistical models for predicting daily global solar radiation in arid Northwest China

Arid

DOI	10.1016/j.compag.2019.104905
	Comparison of BP, PSO-BP and statistical models for predicting daily global solar radiation in arid Northwest China
	Zhang, Yixuan 1,2; Cui, Ningbo 1,2,3; Feng, Yu 1,2,4; Gong, Daozhi 4; Hu, Xiaotao 3
通讯作者	Cui, Ningbo
来源期刊	COMPUTERS AND ELECTRONICS IN AGRICULTURE
ISSN	0168-1699
EISSN	1872-7107
出版年	2019
卷号	164
英文摘要	Accurate prediction of global solar radiation (R-s) 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 R-s 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 ngstrom-Prescott, Bristow-Campbell, Swartman-Ogunlade, Sebaii, Chen and Abdalla) were adopted and compared with measured R-s 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, R-2, 0.7649-0.9678) were more accurate than BP models (R-2, 0.7215-0.9632) and statistical models (R-2, 0.5630-0.9445) for the daily R-s 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 R-2, 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 (R-2, 0.7533-0.9678) were generally superior to temperature-based models (R-2, 0.5630-0.8492), which indicated that sunshine duration was more influential for daily R-s prediction than temperature in this area. Overall, the PSO-BP model exhibits the best generalization capability and is recommended for more accurate daily R-s prediction in arid Northwest China.
英文关键词	Global solar radiation Back-propagation neural network Particle swarm optimization angstrom ngstrom-Prescott model Bristow-Campbell model
类型	Article
语种	英语
国家	Peoples R China
收录类别	SCI-E
WOS记录号	WOS:000483910100024
WOS关键词	SUPPORT VECTOR MACHINE ; EMPIRICAL-MODELS ; SUNSHINE DURATION ; NEURAL-NETWORKS ; METEOROLOGICAL DATA ; TEMPERATURE DATA ; INTERPOLATION ; IRRADIATION ; VALIDATION ; REGIONS
WOS类目	Agriculture, Multidisciplinary ; Computer Science, Interdisciplinary Applications
WOS研究方向	Agriculture ; Computer Science
来源机构	西北农林科技大学
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/214966
作者单位	1.Sichuan Univ, State Key Lab Hydraul & Mt River Engn, Chengdu, Sichuan, Peoples R China; 2.Sichuan Univ, Coll Water Resource & Hydropower, Chengdu 610065, Sichuan, Peoples R China; 3.Northwest A&F Univ, Key Lab Agr Soil & Water Engn Arid & Semiarid Are, Minist Educ, Yangling, Shaanxi, Peoples R China; 4.Chinese Acad Agr Sci, State Engn Lab Efficient Water Use Crops & Disast, Key Lab Dryland Agr, Inst Environm & Sustainable Dev Agr, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Yixuan,Cui, Ningbo,Feng, Yu,et al. Comparison of BP, PSO-BP and statistical models for predicting daily global solar radiation in arid Northwest China[J]. 西北农林科技大学,2019,164.
APA	Zhang, Yixuan,Cui, Ningbo,Feng, Yu,Gong, Daozhi,&Hu, Xiaotao.(2019).Comparison of BP, PSO-BP and statistical models for predicting daily global solar radiation in arid Northwest China.COMPUTERS AND ELECTRONICS IN AGRICULTURE,164.
MLA	Zhang, Yixuan,et al."Comparison of BP, PSO-BP and statistical models for predicting daily global solar radiation in arid Northwest China".COMPUTERS AND ELECTRONICS IN AGRICULTURE 164(2019).