Please wait a minute...
img

官方微信

遥感技术与应用  2018, Vol. 33 Issue (5): 881-889    DOI: 10.11873/j.issn.1004-0323.2018.5.0881
模型与反演     
基于BP神经网络的华东地区太阳辐射模拟及时空变化分析
冯姣姣1,2,王维真1,李净3,刘雯雯4
(1.中国科学院西北生态环境资源研究院,中国科学院黑河遥感实验研究站,
甘肃省遥感重点实验站,甘肃 兰州730000;2.中国科学院大学,北京100049;
3.西北师范大学地理与环境科学学院,甘肃 兰州730070;
4.甘肃测绘产品质量监督检验站,甘肃 兰州730000)
Simulation of Solar Radiation based on BP Neural Network andIts Spatio-temporal Change Analysis in East China
 Feng Jiaojiao1,2,Wang Weizhen1,Li Jing3,Liuwenwen4
(1.Key Laboratory of Remote Sensing of Gansu Province,Heihe Remote Sensing Experimental 
Research Station,Northwest Institute of Eco\|Environment and Resources,Chinese Academy of 
Sciences,Lanzhou,730000,China;2.University of Chinese Academy of Sciences,Beijing,100049,China;
3.The College of Geographical and Environmental Science,Northwest Normal University,
Lanzhou,730070,China;4.Surveying and Mapping Product Quality Supervision and Inspection Stationin Gansu Province,Lanzhou,730000,China)
 全文: PDF 
摘要:
太阳辐射数据是农作物模型、水文模型及气候变化模型等的重要参数,但是,全国范围内太阳辐射站点的分布有限,太阳辐射数据的缺乏制约着相关模型的发展,而神经网络对太阳辐射的估算精度较高,现有的神经网络模拟太阳辐射的模型很少考虑气溶胶、云、水汽对太阳辐射的影响,基于MODIS提供的气溶胶、云、水汽高空大气遥感产品和常规气象站点资料,输入LM\|BP神经网络模型模拟了华东地区90个常规气象站点2001~2014年的太阳辐射月均值。验证结果表明:该模型的拟合优度达到0.95,均方根误差基本控制在2 MJ·m-2以内,平均偏离误差基本在-1 MJ·m-2至1 MJ·m-2之间。最后,利用模型的模拟值,结合13个辐射站点的实测值,通过空间插值得到华东地区2001~2014年年均太阳辐射的精细化空间分布图。

 
关键词: 太阳辐射神经网络MODIS气溶胶水汽时空变化    
Abstract: Solar radiation data are important parameters of crop model,hydrological model and climate change model,however,the distribution of solar radiation sites is scarce and uneven throughout the country,and it is difficult to obtain spatial continuous solar radiation by using only rare radia.Therefore,the lack of solar radiation data restricts the development of the relevant model,and the neural network on the solar radiation has a good predictability,many Artificial Neural Network ensemble models were developed to estimate solar radiation using routinely measured meteorolological variables,but it did not consider cloud,aerosol,and precipitable water vapor influence on solar radiation.In this paper,we used cloud,aerosols,atmospheric precipitable water vapor from MODIS atmosphere remote sensing products and conventional meteorological data including air pressure,temperature,sunshine duration and latitude and elevation,based on the LM\|BP neural network model to simulate the 90 conventional weather stations in Eastern China from 2001 to 2014.The results show that the model has a good fit of 0.95,and the root mean square error is controlled within 2 MJ·m-2.The average deviation error is between -1 MJ·m-2 and 1 MJ·m-2.Finally,using the simulated values of the model and the measured values of 13 radiation sites,the spatial distribution of the annual solar radiation in the East China region from 2001 to 2014 is obtained by spatial interpolation and the spatial variation trend is analyzed. 
Key words:      Solar radiation;Neural network;MODIS;Cloud;Aerosol;Water vapor;Spatio-temporal change
收稿日期: 2017-11-18
:  P422.1  
基金资助: 国家自然科学基金项目(41671373、41301363)资助,中国科学院战略重点研究计划项目(XDA19040500)。
作者简介: 冯姣姣(1990-),女,甘肃陇南人,博士研究生,主要从事地表辐射与蒸散发的遥感估算。Email:fengjiao@lzb.ac.cn。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
冯姣姣
王维真
李净
刘雯雯

引用本文:

冯姣姣,王维真,李净,刘雯雯. 基于BP神经网络的华东地区太阳辐射模拟及时空变化分析[J]. 遥感技术与应用, 2018, 33(5): 881-889.

Feng Jiaojiao,Wang Weizhen,Li Jing,Liuwenwen. Simulation of Solar Radiation based on BP Neural Network andIts Spatio-temporal Change Analysis in East China. Remote Sensing Technology and Application, 2018, 33(5): 881-889.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2018.5.0881        http://www.rsta.ac.cn/CN/Y2018/V33/I5/881

[1] 汪子豪, 秦其明, 孙元亨.

基于BP神经网络的地表温度空间降尺度方法 [J]. 遥感技术与应用, 2018, 33(5): 793-802.

[2] 金点点,宫兆宁. 基于Landsat 系列数据地表温度反演算法对比分析—以齐齐哈尔市辖区为例[J]. 遥感技术与应用, 2018, 33(5): 830-841.
[3] 刘军建, 师春香, 韩帅, 姜志伟, 张涛. 多源地面短波辐射数据融合与评估[J]. 遥感技术与应用, 2018, 33(5): 850-856.
[4] 谢旭,陈芸芝. 基于PSO-RBF神经网络模型反演闽江下游水体悬浮物浓度[J]. 遥感技术与应用, 2018, 33(5): 900-907.
[5] 刘畅,李震,张平,田帮森,周建民. 基于Google Earth Engine评估新疆西南部MODIS积雪产品[J]. 遥感技术与应用, 2018, 33(4): 584-592.
[6] 郝斌飞,韩旭军,马明国,刘一韬,李世卫. Google Earth Engine在地球科学与环境科学中的应用研究进展[J]. 遥感技术与应用, 2018, 33(4): 600-611.
[7] 范锦龙,张晔萍,李昌宝,许文波,刘少杰,薛飞,覃志豪. 风云卫星中分辨率遥感数据几何定位误差分析[J]. 遥感技术与应用, 2018, 33(4): 621-627.
[8] 汪航,师茁. 基于MODIS时间序列数据的春尺蠖虫害遥感监测方法研究—以新疆巴楚胡杨为例[J]. 遥感技术与应用, 2018, 33(4): 686-695.
[9] 林利斌,鲍艳松,左泉,房世波. 基于Sentinel-1与FY-3C数据反演植被覆盖地表土壤水分[J]. 遥感技术与应用, 2018, 33(4): 750-758.
[10] 郭俊杰,姚志刚. TG-2多角度偏振成像仪云相态识别机载验证试验[J]. 遥感技术与应用, 2018, 33(3): 439-448.
[11] 拉巴卓玛,次珍. 2002~2015年西藏雅鲁藏布江流域积雪变化及影响因子分析研究[J]. 遥感技术与应用, 2018, 33(3): 508-519.
[12] 侯海艳,侯金,黄春林,王昀琛. 基于人工神经网络和AMSR2多频微波亮温的北疆地区雪深反演[J]. 遥感技术与应用, 2018, 33(2): 241-251.
[13] 杨朦朦,汪汇兵,欧阳斯达,范奎奎,戚凯丽. 基于双树复小波分解的BP神经网络遥感影像分类[J]. 遥感技术与应用, 2018, 33(2): 313-320.
[14] 汤玉明,邓孺孺,刘永明,熊龙海. 大气气溶胶遥感反演研究综述[J]. 遥感技术与应用, 2018, 33(1): 25-34.
[15] 张帅,师春香,梁晓,贾炳浩,吴捷. 风云三号积雪覆盖产品评估[J]. 遥感技术与应用, 2018, 33(1): 35-46.