Urban vegetation system has great ecological value to social-economic-natural ecosystem,but it was often submitted to different stresses caused by air pollution, water pollution, "heat island" problem, etc., which debases its ecological service functions, so it is important to develop methods to monitor urban vegetation stress level. Using the Hyperion hyper-spectral data, which has advantage in monitoring vegetation physiological characters on large scale, an urban vegetation stress level monitoring method was developed based on vegetation stress feature selection and RBFNN (Radial Basis Function Neural Network). Firstly, 14 hyperspectral vegetation indices were extracted from reflectance image of Hyperion and a feature selection based on correlation analysis was conducted to reduce the redundancies. Then an urban vegetation stress level classifier based on RBFNN was trained on the selected features and vegetation stress level was classified and mapped. Finally, the spatial distribution characteristics of vegetation stress in urban and some reasons were analyzed. The result shows that the RBFNN vegetation stress level classifier is able to identify vegetation stress level quickly and accurately. Vegetation stress level is correlated largely with urban traffic pollution and human disturbance, and vegetation in commercial and residential areas of urban center are apparently experiencing higher stress than vegetation in suburban regions; the stress level shows a ringy distribution around large greenbelts.
WANG Fang, ZHUO Li, LI Xia, XIA Li-Hua
. Urban Vegetation Stress Level Monitoring Based on Hyperspectral Feature Selection and RBF Neural Network[J]. SCIENTIA GEOGRAPHICA SINICA, 2008
, 28(1)
: 77
-82
.
DOI: 10.13249/j.cnki.sgs.2008.01.77
[1] 曾 辉,夏 洁,张 磊. 城市景观生态研究的现状与发展趋势[J].地理科学, 2003,23 (4):484~492.
[2] 李 锋,王如松. 城市绿色空间生态服务功能研究进展[J]. 应用生态学报,2004,15 (3):527~531.
[3] Li L, Ustin S L, Lay M. Application of AVIRIS data in detection of oil-induced vegetation stress and cover change at Jornada, New Mexico [J]. Remote Sensing of Environment, 2005,94(1): 1-16.
[4] Vidal A, Devaux Ros C. Evaluating forest fire hazard with a landsat TM derived water stress index [J]. Agricultural and Forest Meteorology, 1995,(77): 207- 224.
[5] Moran M S, Clarke T R, Inoue Y, et al. Estimating crop water deficit using the relation between surface air temperature and spectral vegetation index [J]. Remote Sensing of Environment, 1994,(49): 246-263.
[6] Zhao D H, Li J L, Qi J G. Identification of red and NIR spectral regions and vegetative indices for discrimination of cotton nitrogen stress and growth stage[J]. Computers and Electronics in Agriculture, 2005,(48):155-169.
[7] 张仁华.以红外辐射信息为基础的估算作物缺水状况的新模式[J].中国科学(B辑),1986,7:776~784.
[8] Chen D Y, Huang J F, Jackson T J. Vegetation water content estimation for corn and soybeans using spectral indices derived from MODIS near- and short-wave infrared bands[J]. Remote Sensing of Environment, 2005,(98): 225-236.
[9] Andras J, Peter K, Laszlo T. Detection of urban effect on vegetation in a less built-up Hungarian city by hyperspectral remote sensing[J]. Physics and Chemistry of the Earth, 2005,(30):255-259.
[10] 刘殿伟,宋开山,张 柏.行道树叶绿素变化的高光谱神经网络模型[J].生态学杂志,2006,25(3):238~242.
[11] 王 娟,慈林林,姚康泽.特征选择方法综述[J].计算机工程与科学,2005,27(12):68~71.
[12] 苏红军, 杜培军.高光谱数据特征选择与特征提取研究[J].遥感技术与应用,2006,21(4)288~293.
[13] 赵福庚,何龙飞,罗庆云.植被逆境生理生态学[M]. 北京:化学工业出版社,2004.
[14] 赵云升,杜 嘉,宋开山,等.基于卫星遥感的夏季长春市城区热场分析[J].地理科学,2006,26(4):70~74.
[15] 臧淑英,智瑞芝.基于生态足迹模型的资源型城市可持续发展定量评估——以黑龙江省石油城市大庆市为例[J].地理科学,2006,26(4):420~425.
[16] 吕 恒,江 南,罗潋葱.基于TM数据的太湖叶绿素A浓度定量反演[J].地理科学,2006,26(4):472~476.
[17] 吴宏安,蒋建军,周 杰,等.基于影象融合的干旱区城镇居民地信息提取研究[J].地理科学,2006,26(4): 477~482.
[18] 夏丽华,王 芳,王德辉.基于MODIS数据的城市光化学污染预警系统及预警等级研究[J].地理科学,2006,26(6): 712~716.
[19] 闻建光,肖 青,柳钦火,等.基于混合光谱理论的太湖水体叶绿素a浓度提取[J].地理科学,2007,27(1):92~97
[20] Hall R J, Crown P H, Titus S J, et al. Evaluation of Landsat thematic mapper data for mapping top kill caused by jack pine budworm defoliation[J]. Canadian Journal of Remote Sensing, 1995,21(4): 388-399.
[21] Sims D A, Gamon J A. Relationships Between Leaf Pigment Content and Spectral Reflectance Across a Wide Range of Species, Leaf Structures and Developmental Stages[J]. Remote Sensing of Environment, 2002, (81):337-354.
[22] Serrano L, Penuelas J, Ustin S L. Remote Sensing of Nitrogen and Lignin in Mediterranean Vegetation from AVIRIS Data: Decomposing Biochemical from Structural Signals[J]. Remote Sensing of Environment, 2002(81):355-364.
[23] Bisun D T, Mcvicar R, Tom G V N, et al. Preprocessing EO-1 Hyperion Hyperspectral Data to support the application of agricultural indexes[J]. IEEE Transaction on Geoscience and Remote Sensing, 2003,41 (6) :1246-1259.
[24] Gao B C. Normalized Difference Water Index for Remote Sensing of Vegetation Liquid Water from Space[J]. Proceedings of SPIE, 1995,(2480): 225-236.
[25] 利容于,王建波.植被抗逆细胞及生理学[M].武汉:武汉大学出版社,2002.
[26] Jacobson J S, Hill AC. Recognition of air pollution injury to vegetation: as pictorial atlas [M]. Pitt. Pennsylvania: Air Pollution Control Association, 1970.
[27] Flagler R B. Recognition of Air Pollution Injury to Vegetation: A Pictorial Atlas[M]. Pittsburgh, PA: Air and Waste Management Association,1998.
[28] 骆剑承,周成虎,杨 艳,等. 基于径向基函数(RBF)映射理论的遥感影像分类模型研究[J]. 中国图形图象学报, 2000, 5(2):94~99.
[29] 周开利,康耀红.神经网络模型及其MATLAB 仿真程序设计[M].北京:清华大学出版社,2005.
[30] Gordoon A B. Urban Forestry Landscapes: Integrating Multidisciplinary Perspectives [M]. Seattle: University of Washington Press, 1995.
