Extraction of remote sensing information for lake salinity level based on SVM: A case from Badain Jaran desert in Inner Mongolia
DIAO Shujuan1, LIU Chunling2, ZHANG Tao2, HE Peng2, GUO Zhaocheng2, TU Jienan2
1. National Geological Library of China, Beijing 100083, China;
2. China Aero Geophysical Survey and Remote Sensing Center for Land and Resources, Beijing 100083, China
According to the problems of remote sensing information extraction in lake salinity level of Badain Jaran desert, the authors put forward a method based on support vector machine (SVM). In this paper, the authors adopted Landsat8 OLI remote sensing image as the data source, completed the image preprocessing such as geometric correction, image registration and mosaicking. With the help of the RS and GIS technology, the authors successfully extracted the information of lake salinity levels of the Badain Jaran desert. The results show that the proposed method can effectively solve the problems of less samples and the information extraction of lake salinity levels when the spectral information is confused, and hence has the reference value and can be promoted to other similar situations.
刁淑娟, 刘春玲, 张涛, 贺鹏, 郭兆成, 涂杰楠. 基于SVM的湖泊咸度等级遥感信息提取方法——以内蒙古巴丹吉林沙漠为例[J]. 国土资源遥感, 2016, 28(4): 114-118.
DIAO Shujuan, LIU Chunling, ZHANG Tao, HE Peng, GUO Zhaocheng, TU Jienan. Extraction of remote sensing information for lake salinity level based on SVM: A case from Badain Jaran desert in Inner Mongolia. REMOTE SENSING FOR LAND & RESOURCES, 2016, 28(4): 114-118.
[1] 梁永平,赵春红,唐春雷,等.北方岩溶区水文地质环境调查进展——以北京西山岩溶区为例[J].中国地质调查,2015,2(8):1-8. Liang Y P,Zhao C H,Tang C L,et al.Progress of hydrogeology and environmental geology survey in Karst Area of northern China:An example from karst area in western hills of Beijing[J].Geology Survey of China,2015,2(8):1-8.
[2] 苏春田,潘晓东,李兆林,等.云南广南岩溶区水文地质环境地质调查进展[J].中国地质调查,2015,2(8):9-16. Su C T,Pan X D,Li Z L,et al.Progress of hydrogeology and environment geology survey in Guangnan karst area,Yunnan province[J].Geology Survey of China,2015,2(8):9-16.
[3] Vapnik V N.The Nature of Statistical Learning Theory[M].New York:Springer-Verlag,1995.
[4] Pal M,Mather P M.Support vector machines for classification in remote sensing[J].International Journal of Remote Sensing,2005,26(5):1007-1011.
[5] Pal M.Support vector machine-based feature selection for land cover classification:A case study with DAIS hyperspectral data[J].International Journal of Remote Sensing,2006,27(14):2877-2894.
[6] Carrão H,Gonçalves P,Caetano M.Contribution of multispectral and multitemporal information from MODIS images to land cover classification[J].Remote Sensing of Environment,2008,112(3):986-997.
[7] Nemmour H,Chibani Y.Fuzzy neural network architecture for change detection in remotely sensed imagery[J].International Journal of Remote Sensing,2006,27(4):705-717.
[8] 王朔琛.基于半监督支持向量机的图像分类方法研究[D].西安:陕西师范大学,2015. Wang S C.Research on Image Classification Based on Semi Supervise Support Vector Machine[D].Xi'an:Shaanxi Normal University,2015.
[9] 李驰.基于支持向量机的超分辨率图像重建[J].激光杂志,2016,37(1):138-141. Li C.Super resolution image reconstruction based on support vector machine[J].Laser Journal,2016,37(1):138-141.
[10] 吴正.风沙地貌与治沙工程学[M].北京:科学出版社,2003. Wu Z.Control Engineering of Sand Physiognomy[M].Beijing:Science Press,2003.
[11] 丁宏伟,王贵玲.巴丹吉林沙漠湖泊形成的机理分析[J].干旱区研究,2007,24(1):1-7. Ding H W,Wang G L.Study on the formation mechanism of the lakes in the Badain Juran desert[J].Arid Zone Research,2007,24(1):1-7.
2016, Vol. 28 
