[1]朱伟仁,孙红福,朱琳,等.基于共轭梯度法和BP神经网络的火山灰云顶高度反演研究[J].自然灾害学报,2019,28(06):028-36.[doi:10.13577/j.jnd.2019.0604]
 ZHU Weiren,SUN Hongfu,ZHU Lin,et al.Inversion of volcanic ash cloud top height based on conjugate gradient method and BP neural network[J].,2019,28(06):028-36.[doi:10.13577/j.jnd.2019.0604]
点击复制

基于共轭梯度法和BP神经网络的火山灰云顶高度反演研究
分享到:

《自然灾害学报》[ISSN:/CN:23-1324/X]

卷:
28
期数:
2019年06期
页码:
028-36
栏目:
出版日期:
2019-12-28

文章信息/Info

Title:
Inversion of volcanic ash cloud top height based on conjugate gradient method and BP neural network
作者:
朱伟仁1 孙红福1 朱琳2 褚闪闪1
1. 中国矿业大学(北京) 地球科学与测绘工程学院, 北京 100083;
2. 中国气象局 国家卫星气象中心, 北京 100081
Author(s):
ZHU Weiren1 SUN Hongfu1 ZHU Lin2 CHU Shanshan1
1. College of Geoscience and Surveying Engineering, China University of Mining & Technology, Beijing 100083, China;
2. National Satellite Meteorological Center of China, China Meteorological Administration, Beijing 100081, China
关键词:
MSG SEVIRI火山灰云顶高度BP神经网络共轭梯度法L-M算法拟合精度波段敏感性
Keywords:
MSG SEVIRIvolcanic ash cloudBP Neural networkconjugate gradient algorithmL-M algorithmfitting accuracyband sensitivity
分类号:
TP79;X43;X9
DOI:
10.13577/j.jnd.2019.0604
摘要:
对于火山灰云顶高度的反演问题本质上是一个不确定性反演问题,不论是一维变分的方法还是线性统计回归方法,在复杂气象条件下无法获得高精度解。为了减少对热红外辐射传输模式、物理反演方法以及辅助气象数据的依赖,提出了一种基于BP神经网络的火山灰云高度遥感反演方法。以2010年5月8日发生在冰岛的艾雅法拉火山爆发为例,利用覆盖研究区域的Meteosat-8卫星的SEVIRI仪器数据资料和美国NOAA开发的GOES-R火山灰云顶高度算法反演的火山灰云高度作为训练样本,建立了基于共轭梯度法和L-M法两种训练方法的优化神经网络反演方法体系。研究结果表明:在迭代次数相同的条件下,利用共轭梯度法的反演结果均方误差要优于L-M算法。我国新一代静止气象卫星风云四号成像仪具有与SEVIRI仪器相似的红外通道设置,本研究对建立基于我国新一代静止气象卫星FY-4数据的火山灰云顶高度定量反演模型也具有重要的借鉴意义。
Abstract:
The inversion of the height of the volcanic ash cloud top is essentially an uncertain inversion problem. No matter the one-dimensional variation method or the linear statistical regression method, the high-precision solution can not be obtained under the complex meteorological conditions. In order to reduce the dependence on thermal infrared radiation transfer mode, physical inversion method and auxiliary meteorological data, a remote sensing inversion method of volcanic ash cloud height based on BP neural network is proposed. Taking the Eyjafjallajokull eruption in Iceland on May 8, 2010 as an example, an optimized neural network inversion method system based on conjugate gradient method and L-M method was established by using the Seviri instrument data of Meteosat-8 satellite covering the research area and the height of ash cloud retrieved by goes-r algorithm developed by NOAA as training sample. The results show that the mean square error of the inversion results of the conjugate gradient method is better than that of the L-M algorithm under the same number of iterations. China’s new generation of geostationary meteorological satellite fengyun-4 imager has similar infrared channel settings with seviri instruments. This study is also of great significance for the establishment of quantitative inversion model of volcanic ash cloud top height based on FY-4 data of China’s new generation of geostationary meteorological satellite.

参考文献/References:

[1] 张程远,席道瑛,刘小燕,等. 火山喷发沉降物扩散理论模型[J]. 自然灾害学报,2003, 12(1):109-115. ZHANG Chengyuan, XI Daoying, LIU Xiaoyan, et al. A theoretical model for diffusion of volcanic eruptive sediment[J]. Journal of Natural Disasters, 2003, 12(1):109-115. (in Chinese)
[2] Webley P, Mastin L. Improved prediction and tracking of volcanic ash clouds[J]. Journal of Volcanology & Geothermal Research, 2009, 186(1-2):1-9.
[3] 韩振海,任锦章,陈洪洲. 火山灾害及其监测预防[J]. 自然灾害学报,1993, 2(4):85-97. HAN Zhenhai, REN Jinzhang, CHEN Hongzhou. Volcanic disaster and its monitoring and prevention[J]. Journal of Natural Disasters, 1993, 2(4):85-97. (in Chinese)
[4] 张学霞,薄立群,张树文. 基于RS和GIS的长白山火山灾害风险评估研究[J]. 自然灾害学报, 2003, 12(1):47-55. ZHANG Xuexia, BO Liqun, ZHANG Shuwen. Risk assessment of volcanic hazards in Changbai Mountain region based on RS and GIS[J]. Journal of Natural Disasters, 2003, 12(1):47-55. (in Chinese)
[5] Wen, Shiming, Rose, William I. Retrieval of sizes and total masses of particles in volcanic clouds using AVHRR bands 4 and 5[J]. Journal of Geophysical Research, 1994, 99(D3):5421.
[6] Pavolonis M J, Heidinger A K, Sieglaff J. Automated retrievals of volcanic ash and dust cloud properties from upwelling infrared measurements[J]. Journal of Geophysical Research Atmospheres, 2013, 118(3):1436-1458.
[7] Zhu L, Li J, Zhao Y, et al. Retrieval of volcanic ash height from satellite-based infrared measurements[J]. Journal of Geophysical Research:Atmospheres, 2017, 122(10):5364-5379.
[8] Oppenheimer C. Volcanological applications of meteorological satellites[J]. International Journal of Remote Sensing, 1998, 19(15):2829-2864.
[9] Nelson D L, Garay M J, Kahn R A, et al. Stereoscopic height and wind retrievals for aerosol plumes with the MISR INteractive explorer (MINX)[J]. Remote Sensing, 2013, 5(9):4593-4628.
[10] Tupper A, Carn S, Davey J, et al. An evaluation of volcanic cloud detection techniques during recent significant eruptions in the western ‘Ring of Fire’[J]. Remote Sensing of Environment, 2004, 91(1):27-46.
[11] Prata A J. Infrared radiative transfer calculations for volcanic ash clouds[J]. Geophysical Research Letters, 1989, 16(11):1293-1296.
[12] Piscini A, Picchiani M, Chini M, et al. A neural network approach for the simultaneous retrieval of volcanic ash parameters and SO2 using MODIS data[J]. Atmospheric Measurement Techniques, 2014, 7(12):4023.
[13] Posselt R, Mueller R, Trentmann J, et al. A surface radiation climatology across two Meteosat satellite generations[J]. Remote Sensing of Environment, 2014, 142:103-110.
[14] 张宏,马岩,李勇,等. 基于遗传BP神经网络的核桃破裂功预测模型[J]. 农业工程学报, 2014, 30(18):78-84. ZHANG Hong, MA Yan, LI Yong, et al. Rupture energy prediction model for walnut shell breaking based on genetic BP neural network[J]. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(18):78-84. (in Chinese)
[15] 卢文喜,杨忠平,李平,等. 基于改进BP算法的地下水动态预测模型[J]. 水资源保护, 2007, 23(3):5-8. LU Weixi, YANG ZhongPing, LI Ping, et al. Dynamic prediction model of groundwater based on improved BP algorithm[J]. Water Resources Protection, 2007, 23(3):5-8. (in Chinese)
[16] 周建华. 共轭梯度法在BP网络中的应用[J]. 计算机工程与应用, 1999, 35(3):17-18. ZHOU Jianhua. Application of conjugate gradient method in BP Networks[J]. CEA, 1999, 35(3):17-18. (in Chinese)
[17] Céspedes L F, Chang R, Velasco A. IS-LM-BP in the pampas[J]. IMF Staff Papers, 2003, 50(1):143-156.
[18] 项文强,张华,王姮,等. 基于L-M算法的BP网络在变压器故障诊断中的应用[J]. 电力系统保护与控制, 2011, 39(8):100-103,111. XIANG Wenqiang, ZHANG Hua, WANG Heng, et al. Application of BP neural network with L-M algorithm in power transformer fault diagnosis[J]. Power System Protection and Control, 2011, 39(8):100-103,111. (in Chinese)
[19] 盛仲飙,同晓荣. BP神经网络在曲线拟合中的应用[J]. 科学技术与工程, 2011, 11(28):6998-7000. SHENG Zhongbiao, TONG Xiaorong. The application of BP neural networks in curve fitting[J]. Science Technology and Engineering, 2011,11(28):6998-7000. (in Chinese)
[20] 金龙,况雪源,黄海洪,等. 人工神经网络预报模型的过拟合研究[J]. 气象学报, 2004, 62(1):62-70. JIN Long, KUANG Xueyuan, HUANG Haihong, et al. Study on the overfitting of the artificial neural network forecasting model[J]. Acta Meteorologica Sinica, 2004, 62(1):62-70. (in Chinese)

备注/Memo

备注/Memo:
收稿日期:2019-04-16;改回日期:2019-07-01。
基金项目:国家重点研发计划(2018YFA0605502);国家自然科学基金项目(41871263)
作者简介:朱伟仁(1995-),男,硕士研究生,主要从事领域为遥感技术与应用研究.E-mail:wangwangyamiedie@163.com
通讯作者:朱琳(1978-),女,研究员,主要从事定量遥感建模及应用研究.E-mail:zhulin@cma.gov.cn
更新日期/Last Update: 1900-01-01