漳江口湿地变化的遥感监测
|
摘要
以漳江口红树林国家级自然保护区(以下简称保护区)为研究对象,2000、2005、2010和2016年的Landsat TM/OLI影像为数据源,通过面向对象随机森林分类法对保护区湿地进行分类,分类结果总体精度达到94.45%,Kappa系数为0.931 2,表明该方法在湿地分类方面具有较大应用潜力。应用遥感技术研究保护区湿地分布及其变化,结果表明:2000—2016年,养殖池分布面积最大,大部分分布在漳江的南北两侧;护花米草主要分布在漳江南部,少量生长在漳江北部;红树林主要分布在漳江南侧,互花米草的东部,漳江北部的养殖池边缘也有少量分布;滩涂与养殖池、互花米草、红树林接壤,分布在漳江两侧。2000—2005年,保护区内的大量天然湿地向人工湿地转化,主要是滩涂湿地及其他类型转换为养殖池,变化发生在保护区南部以及中部,另有部分互花米草转换为养殖池,发生在保护区北部; 2005—2016年,互花米草面积迅速增加,主要发生在漳江南部。引起变化的主要原因是人类活动、气候因素及海平面上升。
Taking the Zhangjiangkou National Mangrove Nature Reserve as the research object,using Landsat TM/OLI images in2000,2005,2010 and 2016 as data sources,the reserve was classified by object-oriented random forest classification and the overall accuracy of the classification results reached 94.45%,and the Kappa coefficient was 0.931 2,indicating that the method has great application potential in wetland classification. In addition,remote sensing technology were introduced to study the distribution and change of wetland in protected area,the results showed that the distribution area of the culture ponds was the largest during2000—2016,most of them were distributed on the north and south of Zhangjiang River. The Spartina alterniflora were mainly distributed in the south of Zhangjiang River and partly of S. alterniflora growing in the north of Zhangjiang River. Mangroves were mainly distributed in the south of Zhangjiang River and in the east part of S. alterniflora,and there is also a small amount of distribution at the edge of culture ponds in the northern Zhangjiang River; the tidal flats were bordered by the breeding ponds,S. alterniflora and mangroves,distributed along the both sides of Zhangjiang River. During 2000—2005,a large number of natural wetlands including tidal flats or the other wetlands in the protected area were converted to culture ponds. The change occurred in the southern and central part of the protected area,and some of the S. alterniflora were converted into breeding ponds. S. alterniflora area increased rapidly from 2005 to 2016,mainly in the south part of Zhangjiang River. The main causes of change include human activities,climatic factors and rising sea levels.
Taking the Zhangjiangkou National Mangrove Nature Reserve as the research object,using Landsat TM/OLI images in2000,2005,2010 and 2016 as data sources,the reserve was classified by object-oriented random forest classification and the overall accuracy of the classification results reached 94.45%,and the Kappa coefficient was 0.931 2,indicating that the method has great application potential in wetland classification. In addition,remote sensing technology were introduced to study the distribution and change of wetland in protected area,the results showed that the distribution area of the culture ponds was the largest during2000—2016,most of them were distributed on the north and south of Zhangjiang River. The Spartina alterniflora were mainly distributed in the south of Zhangjiang River and partly of S. alterniflora growing in the north of Zhangjiang River. Mangroves were mainly distributed in the south of Zhangjiang River and in the east part of S. alterniflora,and there is also a small amount of distribution at the edge of culture ponds in the northern Zhangjiang River; the tidal flats were bordered by the breeding ponds,S. alterniflora and mangroves,distributed along the both sides of Zhangjiang River. During 2000—2005,a large number of natural wetlands including tidal flats or the other wetlands in the protected area were converted to culture ponds. The change occurred in the southern and central part of the protected area,and some of the S. alterniflora were converted into breeding ponds. S. alterniflora area increased rapidly from 2005 to 2016,mainly in the south part of Zhangjiang River. The main causes of change include human activities,climatic factors and rising sea levels.
引文
[1]黄颖,周云轩,吴稳,等.基于决策树模型的上海城市湿地遥感提取与分类[J].吉林大学学报(地球科学版),2009,39(6):1 156-1 162.
[2]张策,臧淑英,金竺,等.基于支持向量机的扎龙湿地遥感分类研究[J].湿地科学,2011,9(3):263-269.
[3]谢静,王宗明,毛德华,等.基于面向对象方法和多时相HJ-1影像的湿地遥感分类:以完达山以北三江平原为例[J].湿地科学,2012,10(4):429-438.
[4]李玉凤,刘红玉.湿地分类和湿地景观分类研究进展[J].湿地科学,2014,12(1):102-108.
[5]孙永光,赵冬至,郭文永,等.红树林生态系统遥感监测研究进展[J].生态学报,2013,33(15):4 523-4 538.
[6] PIJANOWSKI C B,BROWN G D,SHELLITO A B,et al. Using neural networks and GIS to forecast land use changes:a land transformation model[J]. Computers,Environment and Urban Systems,2002,26(6):553-575.
[7] OTUKEI J R,BLASCHKE T. Land cover change assessment using decision trees,support vector machines and maximum likelihood classification algorithms[J]. International Journal of Applied Earth Observation and Geoinformation,2010,12(S1):S27-S31.
[8]张雪红.基于决策树方法的Landsat8 OLI影像红树林信息自动提取[J].国土资源遥感,2016,28(2):182-187.
[9]徐永明,刘勇洪,魏鸣,等.基于MODIS数据的长江三角洲地区土地覆盖分类[J].地理学报,2007,62(6):640-648.
[10]肖锦成,欧维新,符海月.基于BP神经网络与ETM+遥感数据的盐城滨海自然湿地覆被分类[J].生态学报,2013,33(23):7 496-7 504.
[11]王娟,廖静娟,沈国状,等.基于面向对象技术的鄱阳湖湿地地物分类研究[J].遥感技术与应用,2016,31(3):543-550.
[12]郭亚鸽,于信芳,江东,等.面向对象的森林植被图像识别分类方法[J].地球信息科学学报,2012,14(4):514-522.
[13]白晓燕,陈晓宏,王兆礼.基于面向对象分类的土地利用信息提取及其时空变化研究[J].遥感技术与应用,2015,30(4):798-809.
[14]肖艳,姜琦刚,王斌,等.基于Relief F和PSO混合特征选择的面向对象土地利用分类[J].农业工程学报,2016,32(4):211-216.
[15] BREIMAN L. Random forests[J]. Machine Learning,2001,45(1):5-32.
[16] MAHDIANPARI M,SALEHI B,MOHAMMADIMANESH F,et al. Random forest wetland classification using ALOS-2L-band,RADARSAT-2 C-band,and Terra SAR-X imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2017,130:13-31.
[17] VAN BEIJMA S,COMBER A,LAMB A. Random forest classification of salt marsh vegetation habitats using quad-polarimetric airborne SAR,elevation and optical RS data[J]. Remote Sensing of Environment,2014,149:118-129.
[18]陈虹,刘金福,吴彩婷,等.漳江口红树林生态服务功能估算[J].森林与环境学报,2016,36(1):62-66.
[19]赵峰,张怀清,刘华,等.福建漳江口红树林湿地保护区遥感监测及保护分析[J].西北林学院学报,2011,26(1):160-165.
[20]路春燕,王宗明,贾明明,等.基于ENVISAT ASAR、Landsat TM与DEM的泥炭沼泽信息提取方法[J].武汉大学学报(信息科学版),2017,42(2):185-192.
[21]贾明明,王宗明,张柏,等.综合环境卫星与MODIS数据的面向对象土地覆盖分类方法[J].武汉大学学报(信息科学版),2014,39(3):305-310.
[22]黄慧萍.面向对象影像分析中的尺度问题研究[D].北京:中国科学院研究生院(遥感应用研究所),2003.
[23]周梦遥,何东进,覃德华,等. 1995—2015年厦门市土地利用变化对植被覆盖度的影响[J].森林与环境学报,2017,37(4):440-445.
[24] GAO B C. NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space[J]. Remote Sensing of Environment,1996,58(3):257-266.
[25]刘舒,姜琦刚,马玥,等.基于多目标遗传随机森林特征选择的面向对象湿地分类[J].农业机械学报,2017,48(1):119-127.
[26]马玥,姜琦刚,孟治国,等.基于随机森林算法的农耕区土地利用分类研究[J].农业机械学报,2016,47(1):297-303.
[2]张策,臧淑英,金竺,等.基于支持向量机的扎龙湿地遥感分类研究[J].湿地科学,2011,9(3):263-269.
[3]谢静,王宗明,毛德华,等.基于面向对象方法和多时相HJ-1影像的湿地遥感分类:以完达山以北三江平原为例[J].湿地科学,2012,10(4):429-438.
[4]李玉凤,刘红玉.湿地分类和湿地景观分类研究进展[J].湿地科学,2014,12(1):102-108.
[5]孙永光,赵冬至,郭文永,等.红树林生态系统遥感监测研究进展[J].生态学报,2013,33(15):4 523-4 538.
[6] PIJANOWSKI C B,BROWN G D,SHELLITO A B,et al. Using neural networks and GIS to forecast land use changes:a land transformation model[J]. Computers,Environment and Urban Systems,2002,26(6):553-575.
[7] OTUKEI J R,BLASCHKE T. Land cover change assessment using decision trees,support vector machines and maximum likelihood classification algorithms[J]. International Journal of Applied Earth Observation and Geoinformation,2010,12(S1):S27-S31.
[8]张雪红.基于决策树方法的Landsat8 OLI影像红树林信息自动提取[J].国土资源遥感,2016,28(2):182-187.
[9]徐永明,刘勇洪,魏鸣,等.基于MODIS数据的长江三角洲地区土地覆盖分类[J].地理学报,2007,62(6):640-648.
[10]肖锦成,欧维新,符海月.基于BP神经网络与ETM+遥感数据的盐城滨海自然湿地覆被分类[J].生态学报,2013,33(23):7 496-7 504.
[11]王娟,廖静娟,沈国状,等.基于面向对象技术的鄱阳湖湿地地物分类研究[J].遥感技术与应用,2016,31(3):543-550.
[12]郭亚鸽,于信芳,江东,等.面向对象的森林植被图像识别分类方法[J].地球信息科学学报,2012,14(4):514-522.
[13]白晓燕,陈晓宏,王兆礼.基于面向对象分类的土地利用信息提取及其时空变化研究[J].遥感技术与应用,2015,30(4):798-809.
[14]肖艳,姜琦刚,王斌,等.基于Relief F和PSO混合特征选择的面向对象土地利用分类[J].农业工程学报,2016,32(4):211-216.
[15] BREIMAN L. Random forests[J]. Machine Learning,2001,45(1):5-32.
[16] MAHDIANPARI M,SALEHI B,MOHAMMADIMANESH F,et al. Random forest wetland classification using ALOS-2L-band,RADARSAT-2 C-band,and Terra SAR-X imagery[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2017,130:13-31.
[17] VAN BEIJMA S,COMBER A,LAMB A. Random forest classification of salt marsh vegetation habitats using quad-polarimetric airborne SAR,elevation and optical RS data[J]. Remote Sensing of Environment,2014,149:118-129.
[18]陈虹,刘金福,吴彩婷,等.漳江口红树林生态服务功能估算[J].森林与环境学报,2016,36(1):62-66.
[19]赵峰,张怀清,刘华,等.福建漳江口红树林湿地保护区遥感监测及保护分析[J].西北林学院学报,2011,26(1):160-165.
[20]路春燕,王宗明,贾明明,等.基于ENVISAT ASAR、Landsat TM与DEM的泥炭沼泽信息提取方法[J].武汉大学学报(信息科学版),2017,42(2):185-192.
[21]贾明明,王宗明,张柏,等.综合环境卫星与MODIS数据的面向对象土地覆盖分类方法[J].武汉大学学报(信息科学版),2014,39(3):305-310.
[22]黄慧萍.面向对象影像分析中的尺度问题研究[D].北京:中国科学院研究生院(遥感应用研究所),2003.
[23]周梦遥,何东进,覃德华,等. 1995—2015年厦门市土地利用变化对植被覆盖度的影响[J].森林与环境学报,2017,37(4):440-445.
[24] GAO B C. NDWI-A normalized difference water index for remote sensing of vegetation liquid water from space[J]. Remote Sensing of Environment,1996,58(3):257-266.
[25]刘舒,姜琦刚,马玥,等.基于多目标遗传随机森林特征选择的面向对象湿地分类[J].农业机械学报,2017,48(1):119-127.
[26]马玥,姜琦刚,孟治国,等.基于随机森林算法的农耕区土地利用分类研究[J].农业机械学报,2016,47(1):297-303.