基于LM-BP神经网络的西北地区太阳辐射时空变化研究

doi:10.13249/j.cnki.sgs.2016.05.017

摘要/Abstract

摘要：

定量模拟太阳辐射对认识西北地区气候变化至关重要,但西北地区辐射站点稀少,而气象站点较多,利用众多的气象站点观测值模拟太阳辐射是获得太阳辐射数据很好的方法之一。利用LM (Levenberg-Marquardt) 算法对普通的BP神经网络进行优化（优化后的BP神经网络简称LM-BP神经网络）模拟太阳辐射,通过与传统气候模型模拟的太阳辐射结果对比发现,LM-BP神经网络模型的模拟精度最高,模拟值与实测值的拟合程度明显优于H-S模型和A-P模型。由此利用西北地区159个气象站点的气象数据和LM-BP神经网络模型模拟了1990~2012年这些气象站点的太阳总辐射月总量,将LM-BP神经网络模拟的气象站点的太阳辐射和25个辐射观测站的实测太阳辐射数据相结合,通过空间插值得到了西北地区太阳总辐射的空间分布,并分析了其时空分布及变化特征。研究结果发现西北地区1990~2012年的年均总辐射月总量变化为262~643 βMJ/m²,呈现“中间高,两端低”的空间分布特征。LM-BP神经网络模型的模拟精度高,是一种很有发展前景的辐射模拟方法,可将其应用在无辐射观测地区的太阳辐射模拟中。

关键词: LM-BP神经网络, 太阳辐射, 时空变化, 西北地区

Abstract:

Solar radiation data can be used to simulate surface dynamic and thermal process. Solar radiation data is the important input parameter of the models in ecology, hydrology, crop, solar radiation transmission, global circulation and so on. Quantitative simulation of solar radiation is important for understanding climate change in Northwest China. However, the solar radiation stations are sparse in Northwest China, so using small amount of radiation site data interpolating or extrapolating is difficult to obtain the spatial distribution of solar radiation data. There are more many weather stations in Northwest China, so it is one of the best methods to simulate the solar radiation by using a large number of meteorological observations. In this article, the LM (Levenberg-Marquardt) algorithm is used to optimize the BP neural network (LM-BP neural network is abbreviation of BP neural network for the optimization). This article simulates solar radiation using LM-BP neural network, H-S and A-P climate models at Urumqi, Kashi, Hami, Xining and Guyuan radiation stations and uses MPE, MBE and RMSE indexes of accuracy assessment to test the three models. The results indicate that LM-BP neural network has the highest accuracy in model simulations, showing satisfactory performance compared with the simulation results of traditional two climate models, simulated and observed values of fitting degree model is superior to H-S and A-P climate models. So we selects the LM-BP neural network model to simulate solar radiation in Northwest China. Basing on the meteorological data from 159 weather stations in Northwest, we apply the BP neural network optimized LM (Levenberg - Marquardt) algorithm to simulate the total month solar radiation during 1990-2012 in these meteorological observation stations. Then the solar radiation value of the 159 weather stations and the measured radiation data of the 25 radiation observation station to obtain the spatial-temporal distribution of annual average solar radiation by interpolation, and analyzes. These results indicate that average annual total radiation in 1990-2012 in Northwestern ranges from 262 MJ/m²to 643 MJ/m², presenting the distribution pattern of high in the middle, low on both end. LM neural network is a promising method for solar radiation simulation, which can be used in the simulation of solar radiation in the area of no radiation observation.

Key words: LM-BP neural network, solar radiation, spatial and temporal changes, Northwest China

中图分类号:

P422.1

李净, 冯姣姣, 王卫东, 张福存. 基于LM-BP神经网络的西北地区太阳辐射时空变化研究[J]. 地理科学, 2016, 36(5): 780-786.

Jing Li, Jiaojiao Feng, Weidong Wang, Fucun Zhang. Spatial and Temporal Changes in Solar Radiation of Northwest China Based LM-BP Neural Network[J]. SCIENTIA GEOGRAPHICA SINICA, 2016, 36(5): 780-786.

图/表 5

图1

图2

表1

图3

图4

参考文献 21

[1]	施国萍, 邱新法, 曾燕. 中国三种太阳辐射起始数据分布式模拟[J]. 地理科学, 2013, 33(4): 385-392.
	、[Shi Guoping, Qiu Xinfa, Zeng Yan. Distributed Modeling of Three Kinds of Initial Data for Global Solar Radiation Simulation in China. Scientia Geographica Sinica, 2013, 33(4): 385-392.]
[2]	查良松. 我国地面太阳辐射量的时空变化研究[J]. 地理科学, 1996, 16(3): 41-46.
	、[Zha Liangsong. A Study on Spatial and Temporal Variation of Solar Radiation in China. Scientia Geographica Sinica, 1996, 16(3): 41-46.]
[3]	周晋, 吴业正, 晏刚, 等. 利用神经网络估算太阳辐射[J]. 太阳能学报, 2005, 26(4): 509-512.
	、[Zhou Jin, Wu Yezheng, Yan Ganget al. Solar radiation estimation using artificial neural networks. Acta Energiae Solaris Sinica, 2005, 26(4): 509-512.]
[4]	曹双华, 曹家枞, 刘凤强. 小波分析在太阳辐射神经网络预测中的应用研究[J]. 东华大学学报:自然科学版, 2004, 30(6): 18-22.
	、[Cao Shuanghua, Cao Jiacong, Liu Fengqiang. Study of Application of Wavelet Analysis to Neural Networks for the Forecast of Solar Irradiance. Journal of Donghua University(Natural Science Edition), 2004, 30(6): 18-22.]
[5]	林星春, 曹双华, 曹家枞. 太阳散射辐射逐日预测模型研究[J]. 建筑热能通风空调, 2006, 25(6): 76-79.
	、 [Lin Xingchun, Cao Shuanghua, Cao Jiacong. Study on Daily Solar Diffuse Radiation Forecasting Model.、 [Lin Xingchun, Cao Shuanghua, Cao Jiacong. Study on Daily Solar Diffuse Radiation Forecasting Model. Building Energy & Environment, 2006, 25(6): 76-79.]
[6]	Jiang Yingni.Prediction of Monthly Mean Daily Diffuse Solar Radiation Using Artificial Neural Networks and Comparison With Other Empirical Models[J]. Energy Policy, 2008, 36(10): 3833-3837.
[7]	Wan K K, Tang H L, Liu Y et al. An Analysis of Thermal and Solar zone Radiation Models Using an Angstrom-Prescott Equation and Artificial Neural Networks[J]. Energy, 2008, 33(7): 1115-1127.
[8]	Mubiru J, Banda E.Estimation of Monthly Average Daily Global Solar Irradiation Using Artificial Neural Networks[J]. Solar Energy, 2008, 82(2): 181-187.
[9]	Rehman S, Mohandes M.Artificial Neural Network Estimation of Global Solar Radiation Using Air Temperature and Relative Humidity[J]. Energy Policy, 2008, 36(2): 571-576.
[10]	Benghanem M, Mellit A, Alamri S N.ANN-based Modelling and Estimation of Daily Global Solar Radiation Data: a Case Study[J]. Energy Conversion and Management, 2009, 50(7): 1644-1655.
[11]	Fadare D A.Modelling of Solar Energy Potential in Nigeria Using an Artificial Neural Network Model[J]. Applied Energy, 2009, 86(9): 1410-1422.
[12]	Behrang M A, Assareh E, Ghanbarzadeh A et al. The Potential of Different Artificial Neural Network (ANN) Techniques in Daily Global Solar Radiation Modeling Based on Meteorological Data[J]. Solar Energy, 2010, 84(8): 1468-1480.
[13]	Ozgoren M, Bilgili M, Sahin B.Estimation of Global Solar Radiation Using ANN Over Turkey[J]. Expert Systems With Applications, 2012, 39(5): 5043-5051.
[14]	Kaushika N D, Tomar R K, Kaushik S C.Artificial Neural Network Model Based on Interrelationship of Direct, Diffuse and Global Solar Radiations[J]. Solar Energy, 2014, 10: 327-342.
[15]	谢金南, 周嘉陵. 西北地区中、东部降水趋势的初步研究[J]. 高原气象, 2001, 20(4): 362-367.
	、[Xie Jinna, Zhou Jialing. A Preliminary Study on Trends and Interannual Variaration of Precipitation in Central and Western Portions of Northwest Region of China. Plateau Meteorology, 2001, 20(4): 362-367.]
[16]	赵玲玲, 翁苏明, 曾华军, 等. 模式分析的核方法[M] . 北京: 机械工业出版社, 2006 .
	、 [Zhao Lingling, Weng Suming, Zeng Huajunet al. Kernel Methods for Pattern Analysis. Beijing: China Machine Press, 2006.]
[17]	Duffie J A, Beckman W A.Solar engineering of thermal processes[M]. New York:John Wiley and Sons, 1980.
[18]	高蓓, 范建忠, 李化龙, 等. 陕西黄土高原近50年日照时数的变化[J]. 安徽农业科学, 2012, 40(4): 2246-2250.
	、 [Gao Bei, Fan Jianzhong, Li Hualonget al. Variation of Sunshine Hours over Loess Plateau of Shaanxi in Recent 50 Years. Journal of Anhui Agricultural Sciences, 2012, 40(4): 2246-2250.]
[19]	杨勤, 梁旭, 赵光平, 等. 宁夏太阳辐射逐日、月、年总量的变化特征[J]. 干旱区研究, 2009, 26(3): 413-423.
	、[Yang Qin, Liang Xu, Zhao Guangpinget al. Change Characteristics of Daily, Monthly and Annual Solar Radiation in Ningxia Hui Autonomous Region. Arid Zone Research, 2009, 26(3): 413-423.]
[20]	曹雯, 申双和, 段春锋. 西北地区生长季参考作物蒸散变化成因的定量分析[J]. 地理学报, 2011, 66(3): 407-415.
	、 [Cao Wen, Shen Shuanghe, Duan Chunfeng. Quantification of the Causes for Reference Crop Eapotranspiration Changes in Growing Season in Northwest China.、 [Cao Wen, Shen Shuanghe, Duan Chunfeng. Quantification of the Causes for Reference Crop Eapotranspiration Changes in Growing Season in Northwest China. Acta Geographica Sinica, 2011, 66(3): 407-415.]
[21]	许建明, 何金海, 阎凤霞. 1961~2007年西北地区地面太阳辐射长期变化特征研究[J]. 气候与环境研究, 2010, 15(1): 89-96.
	、[Xu Jianming, He Jinhai, Yan Fengxia. Research on Secular Variation of Solar Radiation over Northwest China from 1961 to 2007. Climatic and Environmental Research, 2010, 15(1): 89-96.]

模型	统计指标	台站
模型	统计指标	乌鲁木齐	喀什	哈密	西宁	固原
A-P模型	MPE(%)	31	15	31	21	17
	MBE(MJ/m²)	94	61	132	92	76
	RMSE(MJ/m²)	123	75	145	103	95
	R	0.87	0.94	0.96	0.66	0.72
H-S模型	MPE(%)	37	32	39	28	25
	MBE(MJ/m²)	127	150	147	122	113
	RMSE(MJ/m²)	165	189	164	134	126
	R	0.63	0.52	0.56	0.08	0.36
LM-BP模型	MPE(%)	18	8	20	14	13
	MBE(MJ/m²)	60	35	94	66	58
	RMSE(MJ/m²)	93	43	111	77	70
	R	0.94	0.99	0.96	0.96	0.94