Retrieving of salt lake mineral ions salinity from hyper-spectral data based on BP neural network
ZHOU Yamin1, ZHANG Rongqun1, MA Hongyuan1, ZHANG Jian2, ZHANG Xiaoshuan1
1. College of Information & Electrical Engineering, China Agriculture University, Beijing 100083, China;
2. College of Economic and Management, Beijing Information Science & Technology University, Beijing 100192, China
高光谱遥感数据能够提供比多光谱遥感数据更为丰富的光谱信息,从而更精确地刻画地物的光谱特征。在水体遥感原理基础上,采用自适应波段选择(adaptive band selection,ABS)方法对HJ-1A卫星高光谱数据的波段相关性和信息量进行分析,结合BP神经网络技术确定最优波段组合并构建盐湖矿物离子含量的反演模型,对柴达木盆地西台吉乃尔湖的K+,Mg2+,Na+,Cl-和SO42-离子含量进行定量反演,获得盐湖矿物离子含量的空间分布情况。研究结果表明,BP神经网络反演模型的盐湖矿物离子含量反演精度在85%以上,反演得到的矿物离子含量的分布情况与实地调查结果基本一致。因此,利用高光谱数据和BP神经网络可以对盐湖矿物资源进行大范围动态监测,为盐湖资源的合理开发和高效利用提供科学依据。
Hyper-spectral remote sensing data can provide more spectral information and describe the spectral signature of salt lake more accurately than multi-spectral remote sensing data. Based on the theory of remote sensing on water, the authors analyzed the band correlation and information of HJ-1A satellite hyper-spectrum image by using adaptive band selection(ABS) method. Combined with BP neural network techniques, the authors determined the optimal band combination, established the retrieval models for mineral ions salinity of salt lake, quantitatively determined the salinities of K+, Mg2+, Na+, Cl-, SO42- ions of west Taijinar Salt Lake in Qaidam Basin, and acquired the spatial distribution siuation of mineral ions salinity. The results show that the forecast accuracy of BP neural network models are exclusively higher than 85%, the spatial distribution of mineral ions content of salt lake is consistent with the result of field survey. The research confirms that the correlation of BP neural network and domestic hyper-spectral remote sensing data can be used to monitor the mineral resource of salt lake dynamically, thus providing the scientific foundation for the reasonable development and efficient utilization.
周亚敏, 张荣群, 马鸿元, 张健, 张小栓. 基于BP神经网络的盐湖矿物离子含量高光谱反演[J]. 国土资源遥感, 2016, 28(2): 34-40.
ZHOU Yamin, ZHANG Rongqun, MA Hongyuan, ZHANG Jian, ZHANG Xiaoshuan. Retrieving of salt lake mineral ions salinity from hyper-spectral data based on BP neural network. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(2): 34-40.
[1] 程芳琴,张亚宁,常慧敏,等.紫外分光光度法测定盐湖卤水中钙镁离子含量[J].无机盐工业,2006,38(4):54-56. Cheng F Q,Zhang Y N,Chang H M,et al.UV spectrophotometric determination of magnesium and calcium in brine from salt lake[J].Inorganic Chemicals Industry,2006,38(4):54-56.[2] 杨英桂,黄梓平.察尔汗盐湖晶间卤水中氯离子含量测定方法探讨[J].青海大学学报:自然科学版,2003,21(5):36-37. Yang Y G,Huang Z P.Measuring on chlorine ion content in bittern of Carerhan salt lake[J].Journal of Qinghai University,2003,21(5):36-37.[3] 王腾,韩凤清,马茹莹,等.青海察尔汗盐湖别勒滩区段晶间卤水全氮地球化学分布特征[J].盐湖研究,2014,22(2):33-38. Wang T,Han F Q,Ma R Y,et al.Total nitrogen distribution geochemical characteristics of intercrystal brine in bieletan section of Qarhan salt lake[J].Journal of Salt Lake Research,2014,22(2):33-38.[4] 张燕霞,韩凤清,马茹莹,等.内蒙古西部地区盐湖水化学特征[J].盐湖研究,2013,21(3):17-24. Zhang Y X,Han F Q,Ma R Y,et al.Hydrochemical characteristics of salt lakes in western region of inner Mongolia,China[J].Journal of Salt Lake Research,2013,21(3):17-24.[5] 张博,张柏,洪梅,等.湖泊水质遥感研究进展[J].水科学进展,2007,18(2):301-310. Zhang B,Zhang B,Hong M,et al.Advance in remote sensing of lake water quality[J].Advances in Water Science,2007,18(2):301-310.[6] 张大林,田淑芳,栾学文.西藏扎布耶盐湖氧化硼含量空间分布遥感研究[J].国土资源遥感,2007,19(1):32-35.doi:10.6046/gtzyyg.2007.01.06. Zhang D L,Tian S F,Luan X W.Remote sensing research on the spatial distribution of Boric anhydride in the Zhabuye salt lake of Tibet[J].Remote Sensing for Land and Resources,2007,19(1):32-35.doi:10.6046/gtzyyg.2007.01.06.[7] 田淑芳,秦绪文,郑绵平,等.西藏扎布耶盐湖总盐含量遥感定量分析[J].现代地质,2005,19(4):596-602. Tian S F,Qin X W,Zheng M P,et al.Quantitative analysis of remote sensing on the total salinity of Zhabuye salt lake in Tibet[J].Geoscience,2005,19(4):596-602.[8] 杨雪,张廷斌,徐志忠,等.现代盐湖型钾盐成矿遥感预测——以扎布耶盐湖为例[J].盐湖研究,2014,22(2):14-19. Yang X,Zhang Y B,Xu Z Z,et al.Potassium metallogenic prediction of modern saline lake based on remote sensing:Focus on Zabuye saline lake[J].Journal of Salt Lake Research,2014,22(2):14-19.[9] 张焜,马世斌,刘丽萍.基于SPOT5数据的盐湖矿产开发及矿山环境遥感监测[J].国土资源遥感,2012,24(3):146-153.doi:10.6046/gtzyyg.2012.03.26. Zhang K,Ma S B,Liu L P.Remote sensing monitoring of the mineral resources exploration and mining environment of the salt lake based on SPOT5 data[J].Remote Sensing for Land and Resources,2012,24(3):146-153.doi:10.6046/gtzyyg.2012.03.26.[10] 王跃峰,白朝军.西藏盐湖矿产资源遥感定量预测方法研究[J].盐湖研究,2012,20(2):11-17,43. Wang Y F,Bai C J.Remote sensing assessment of salt lake mineral resources in Tibet,China[J].Journal of Salt Lake Research,2012,20(2):11-17,43.[11] Hung M C,Wu Y H.Mapping and visualizing the Great Salt Lake landscape dynamics using multi-temporal satellite images,1972-1996[J].International Journal of Remote Sensing,2005,26(9):1815-1834.[12] Roshier D A,Rumbachs R M.Broad-scale mapping of temporary wetlands in arid Australia[J].Journal of Arid Environments,2004,56(2):249-263.[13] Castaneda C,Herrero J,Casterad M A.Landsat monitoring of Playa-lakes in the Spanish Monegros desert[J].Journal of Arid Environments,2005,63(3):497-516.[14] French R H,Miller J J,Dettling C,et al.Use of remotely sensed data to estimate the flow of water to a playa lake[J].Journal of Hydrology,2006,325(1/4):67-81.[15] 袁迎辉,林子瑜.高光谱遥感技术综述[J].中国水运,2007,7(8):155-157. Yuan Y H,Lin Z Y.High spectrum remote sensing technology summary[J].China Water Transport,2007,7(8):155-157.[16] 周立国,冯学智,肖鹏峰,等.盐湖遥感研究的进展与展望[J].地球科学进展,2009,24(2):141-149. Zhou L G,Feng X Z,Xiao P F,et al.Advance and prospection of remote sensing application to salt lakes[J].Advances in Earth Science,2009,24(2):141-149.[17] 吕恒,李新国,曹凯.基于BP神经网络模型的太湖悬浮物浓度遥感定量提取研究[J].武汉大学学报:信息科学版,2006,31(8):683-686,735. Lyu H,Li X G,Cao K.Quantitative retrieval of suspended solid concentration in lake Taihu based on BP neural net[J].Geomatics and Information Science of Wuhan University,2006,31(8):683-686,735.[18] 郑喜玉,张明刚,徐昶,等.中国盐湖志[M].北京:科学出版社,2002:163-164. Zheng X Y,Zhang M G,Xu C,et al.Journal of China Salt Lake[M].Beijing:Science Press,2002:163-164.[19] 高海亮,顾行发,余涛,等.基于参考波段的去除HJ-1A星HSI图像中条带噪声的方法[J].红外,2013,34(3):7-11. Gao H L,Gu X F,Yu T,et al.A refrence-band-based method for removing stripe noise from HJ-1A HSI images[J].Infrared,2013,34(3):7-11.[20] 赵春晖,陈万海,杨雷.高光谱遥感图像最优波段选择方法的研究进展与分析[J].黑龙江大学自然科学学报,2007,24(5):592-602. Zhao C H,Chen W H,Yang L.Research advances and analysis of hyperspectral remote sensing image band selection[J].Journal of Natural Science of Heilongjiang University,2007,24(5):592-602.[21] 刘春红,赵春晖,张凌雁.一种新的高光谱遥感图像降维方法[J].中国图象图形学报,2005,10(2):218-222. Liu C H,Zhao C H,Zhang L Y.A new method of hyperspectral remote sensing image dimensional reduction[J].Journal of Image and Graphics,2005,10(2):218-222.[22] 樊彦国,侯春玲,朱浩,等.基于BP神经网络的盐渍土盐分遥感反演模型研究[J].地理与地理信息科学,2010,26(6):24-27. Fan Y G,Hou C L,Zhu H,et al.Research on salinity inversion from remote sensing of saline soil based on BP neural network[J].Geography and Geo-Information Science,2010,26(6):24-27.[23] 朱继文,刘丹丹.基于高光谱数据的土壤含盐量BP神经网络模型研究[J].东北农业大学学报,2009,40(10):115-118. Zhu J W,Liu D D.Research on the BP neural network model of soil salt contents by using hyperspectral data[J].Journal of Northeast Agricultural University,2009,40(10):115-118.[24] 张娟娟,余华,乔红波,等.基于高光谱特征的土壤有机质含量估测研究[J].中国生态农业学报,2012,20(5):566-572. Zhang J J,Yu H,Qiao H B,et al.Soil organic matter content estimation based on hyperspectral properties[J].Chinese Journal of Eco-Agriculture,2012,20(5):566-572.[25] 杨婷,张慧,王桥,等.基于HJ-1A卫星超光谱数据的太湖叶绿素a浓度及悬浮物浓度反演[J].环境科学,2011,32(11):3207-3214. Yang T,Zhang H, Wang Q,et al.Study of retrieving for chlorophyll- a concentration and suspended substance concentration based on HJ-1A HIS image[J].Environmental Science,2011,32(11):3207-3214.[26] 张西营,马海州,高东林,等.柴达木盆地西台吉乃尔盐湖矿区卤水水化学特征[J].盐湖研究,2007,15(2):12-20. Zhang X Y,Ma H Z,Gao D L,et al.Hydrochemical characteristics of brines in the mining area of west Taijinar salt lake in Qaidam basin[J].Journal of Salt Lake Research,2007,15(2):12-20.
2016, Vol. 28 
