Impact of Wenchuan earthquake on the giant panda habitat in Wolong National Nature Reserve, China

被引:4
作者
Kou, Cheng [1 ,2 ]
Xu, Yu-Yue [1 ,2 ]
Ke, Chang-Qing [1 ,2 ]
He, Yu-Ting [3 ]
机构
[1] Nanjing Univ, Jiangsu Prov Key Lab Geog Informat Sci & Technol, Nanjing 210023, Jiangsu, Peoples R China
[2] Nanjing Univ, Key Lab Satellite Mapping Technol & Applicat, State Adm Surveying Mapping & Geoinformat China, Nanjing 210023, Jiangsu, Peoples R China
[3] Penn State Univ, Dept Meteorol, University Pk, PA 16802 USA
基金
中国国家自然科学基金;
关键词
Wenchuan earthquake; giant panda habitat; land cover change; support vector machines; habitat suitability index; weighted usable area; SUPPORT VECTOR MACHINES; SUITABILITY INDEX; CLASSIFICATION; MODEL;
D O I
10.1117/1.JRS.8.083507
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Monitoring the change of the giant panda habitat is essential to protect this endangered species. The Wolong National Nature Reserve (WNNR) of China, the giant panda habitat, was struck by the Wenchuan earthquake (M = 8.0) on May 12, 2008, and was seriously damaged. Landsat images covering the WNNR on four dates, one before and three after the earthquake, are classified using support vector machines to generate land cover maps (with an overall accuracy of similar to 90% and Kappa coefficients of similar to 0.86). The habitat suitability index and weighted usable area (WUA) are calculated to evaluate the changes of the habitat suitability of the WNNR. The results indicate that the forest area dropped by similar to 10% due to the earthquake. The forest located in the east of Wolong town, the home of numerous giant pandas, suffered the most. The WUA decreased significantly after the earthquake, and was showing improvement in 2013, although still not fully recovered to the level of priori earthquake. The habitat between 1200 and 1300 m above sea level (m a.s.l.) was particularly vulnerable and was slowly recovering. Further effective management is necessary to restore and protect the giant panda habitat. (C) 2014 Society of Photo-Optical Instrumentation Engineers (SPIE)
引用
收藏
页数:16
相关论文
共 52 条
[11]   SUPPORT-VECTOR NETWORKS [J].
CORTES, C ;
VAPNIK, V .
MACHINE LEARNING, 1995, 20 (03) :273-297
[12]   The Wenchuan Earthquake (May 12, 2008), Sichuan Province, China, and resulting geohazards [J].
Cui, Peng ;
Chen, Xiao-Qing ;
Zhu, Ying-Yan ;
Su, Feng-Huan ;
Wei, Fang-Qiang ;
Han, Yong-Shun ;
Liu, Hong-Jiang ;
Zhuang, Jian-Qi .
NATURAL HAZARDS, 2011, 56 (01) :19-36
[13]  
Di B., 2010, REMOTE SENS ENVIRON, V114, P761
[14]   Multispectral landuse classification using neural networks and support vector machines: one or the other, or both? [J].
Dixon, B. ;
Candade, N. .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2008, 29 (04) :1185-1206
[15]  
ENVI, 2012, ATM CORR MOD QUAC FL
[16]   Entangling the complexity of protected area management: The case of Wolong Biosphere Reserve, southwestern China [J].
Fu, BJ ;
Wang, KL ;
Lu, YH ;
Liu, SL ;
Ma, KM ;
Chen, LD ;
Liu, GH .
ENVIRONMENTAL MANAGEMENT, 2004, 33 (06) :788-798
[17]  
Haykin S., 2009, Neural Networks and Learning Machines, VThird
[18]  
Hu Jinchu, 2011, Acta Theriologica Sinica, V31, P10
[19]   An assessment of support vector machines for land cover classification [J].
Huang, C ;
Davis, LS ;
Townshend, JRG .
INTERNATIONAL JOURNAL OF REMOTE SENSING, 2002, 23 (04) :725-749
[20]  
Huang JinYan Huang JinYan, 2007, Scientia Silvae Sinicae, V43, P73