基于植被指数选择算法和决策树的生态系统识别
|
摘要
植被指数是对绿色植被的特定表达,在不同环境下的效果不同。植被指数的选择需要结合研究区域的环境特征。本研究将植被指数间的相关系数集成到基于马氏距离的植被指数选择算法中,根据所选样本确定最适宜的植被指数,构建决策树模型,以江西省永丰县为例,开展区域生态系统类型的识别研究。该方法首先确定提取对象,明确对象类别与对象间的隶属关系,然后逐层逐项地提取湿地、森林、草地、农田等生态系统信息。结果表明,所提出的植被指数选择算法具有较好的适用性;生态系统识别的总体精度达89. 11%,构建的决策树模型的分类精度高于传统方法,可为区域生态系统信息提取和生态系统管理提供研究方法。
Vegetation indices can reflect the spectral characteristics of different ecosystems and render remote sensing images easier to interpret,which are widely used to identify the ecosystem distribution patterns. A vegetation index is a specific expression for describing green vegetation,and its effects are inconsistent in different environments. The selection of a vegetation index needs to be combined with the characteristics of the application environment. Currently,selection of vegetation index is mainly based on the physical meaning of a vegetation index,which disregards its adaptability in the study area and leads to inconsistent research results. The correlation coefficients between vegetation indices were integrated into the vegetation indices selection algorithm based on Mahalanobis distance,and then a decision tree model was constructed based on the most suitable vegetation indices of the research area which were determined according to the selected samples. Taking Yongfeng County of Jiangxi Province as an example,it was attempted to identity the distribution pattern of ecosystems. Using this method,the ecosystems needed to be extracted were firstly determined and the relationship between ecosystems and decision tree nodes was established. Then,six different surface features,including wetlands,forests,grasslands,farmlands,urban and bare land,were classified. The overall accuracy of identification by the method was 89. 11%,which was higher than that of the traditional methods. Taking wetlands as an example,the classification accuracy of vegetation indices determined by the vegetation selection algorithm was 91. 62%,which was higher than the common vegetation indices that had an accuracy of 87. 60%. The results indicated that the vegetation indices selection algorithm developed was applicable and effective. The method was a valuable and applicable tool for the extraction of regional ecosystem types and ecosystem management.
Vegetation indices can reflect the spectral characteristics of different ecosystems and render remote sensing images easier to interpret,which are widely used to identify the ecosystem distribution patterns. A vegetation index is a specific expression for describing green vegetation,and its effects are inconsistent in different environments. The selection of a vegetation index needs to be combined with the characteristics of the application environment. Currently,selection of vegetation index is mainly based on the physical meaning of a vegetation index,which disregards its adaptability in the study area and leads to inconsistent research results. The correlation coefficients between vegetation indices were integrated into the vegetation indices selection algorithm based on Mahalanobis distance,and then a decision tree model was constructed based on the most suitable vegetation indices of the research area which were determined according to the selected samples. Taking Yongfeng County of Jiangxi Province as an example,it was attempted to identity the distribution pattern of ecosystems. Using this method,the ecosystems needed to be extracted were firstly determined and the relationship between ecosystems and decision tree nodes was established. Then,six different surface features,including wetlands,forests,grasslands,farmlands,urban and bare land,were classified. The overall accuracy of identification by the method was 89. 11%,which was higher than that of the traditional methods. Taking wetlands as an example,the classification accuracy of vegetation indices determined by the vegetation selection algorithm was 91. 62%,which was higher than the common vegetation indices that had an accuracy of 87. 60%. The results indicated that the vegetation indices selection algorithm developed was applicable and effective. The method was a valuable and applicable tool for the extraction of regional ecosystem types and ecosystem management.
引文
[1] LEVY P E,FRIEND A D,WHITE A,et al. The influence of land use change on global-scale fluxes of carbon from terrestrial ecosystems[J]. Climatic Change,2004,67(2-3):185-209.
[2] YE Y,BRYAN B A,ZHANG J,et al. Changes in land-use and ecosystem services in the Guangzhou-Foshan Metropolitan Area,China from 1990 to 2010:implications for sustainability under rapid urbanization[J]. Ecological Indicators,2018,93:930-941.
[3]王宇航,于强,岳德鹏,等.基于BRT_DC_Pd模型的土地利用模拟研究[J/OL].农业机械学报,2018,49(3):225-234.WANG Yuhang,YU Qiang,YUE Depeng,et al. Simulation of landuse based on BRT_DC_Pd model[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2018,49(3):225-234. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract.aspx? file_no=20180327&flag=1. DOI:10. 6041/j. issn. 1000-1298. 2018. 03. 027.(in Chinese)
[4] DUTTA S,JHALA Y. Planning agriculture based on landuse responses of threatened semiarid grassland species in India[J].Biological Conservation,2014,175:129-139.
[5]龙花楼.论土地利用转型与土地资源管理[J].地理研究,2015,34(9):1607-1618.LONG Hualou. Land use transition and land management[J]. Geographical Research,2015,34(9):1607-1618.(in Chinese)
[6]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.XU Yongming,LIU Yonghong,WEI Ming,et al. Land cover classification of the Yangtze River Delta using MODIS data[J]. Acta Geographica Sinica,2007,62(6):640-648.(in Chinese)
[7]穆少杰,李建龙,陈奕兆,等. 2001—2010年内蒙古植被覆盖度时空变化特征[J].地理学报,2012,67(9):1255-1268.MU Shaojie,LI Jianlong,CHEN Yizhao,et al. Spatial differences of variations of vegetation coverage in Inner Mongolia during2001—2010[J]. Acta Geographica Sinica,2012,67(9):1255-1268.(in Chinese)
[8] FOERSTER S,KADEN K,FOERSTER M,et al. Crop type mapping using spectral-temporal profiles and phenological information[J]. Computers and Electronics in Agriculture,2012,89:30-40.
[9] QI Z,YEH G O,LI X. A crop phenology knowledge-based approach for monthly monitoring of construction land expansion using polarimetric synthetic aperture radar imagery[J]. ISPRS Journal of Photogrammetry&Remote Sensing,2017,133:1-17.
[10] FERENC K. Assessment of regional variations in biomass production using satellite image analysis between 1992 and 2004[J].Transactions in GIS,2007,11(6):911-926.
[11]陈嘉,赵祥,唐荣云,等.基于定量遥感产品的土地覆盖分类方法研究[J].北京师范大学学报(自然科学版),2018,54(3):405-411.CHEN Jia,ZHAO Xiang,TANG Rongyun,et al. Land cover classification by quantitative remote sensing products[J]. Journal of Beijing Normal University(Natural Science),2018,54(3):405-411.(in Chinese)
[12]王正兴,刘闯,HUETE A,等.植被指数研究进展:从AVHRR-NDVI到MODIS-EVI[J].生态学报,2003,23(5):979-987.WANG Zhengxing,LIU Chuang,HUETE A,et al. From AVHRR-NDVI to MODIS-EVI:advances in vegetation index research[J]. Acta Ecologica Sinica,2003,23(5):979-987.(in Chinese)
[13]田庆久,闵祥军.植被指数研究进展[J].地球科学进展,1998,13(4):327-333.TIAN Qingjiu,MIN Xiangjun. Advances in study on vegetation indices[J]. Advance in Earth Sciences,1998,13(4):327-333.(in Chinese)
[14]李行,毛定山,张连蓬.高光谱遥感影像波段选择算法评价方法研究[J].地理与地理信息科学,2006,22(6):34-37.LI Xing,MAO Dingshan,ZHANG Lianpeng. Evaluation method for band selection algorithm of hyperspectral image[J].Geopraphy and Geo-Information Science,2006,22(6):34-37.(in Chinese)
[15]康顺,相诗尧.基于马氏距离的多高斯Voronoi图生成方法[J].地理与地理信息科学,2016,32(3):49-52.KANG Shun,XIANG Shiyao. A generation method of multi-Gaussian Voronoi diagram based on Mahalanobis distance[J].Geography and Geo-Information Science,2016,32(3):49-52.(in Chinese)
[16]许明明,张良培,杜博,等.基于类别可分性的高光谱图像波段选择[J].计算机科学,2015,42(4):274-275.XU Mingming,ZHANG Liangpei,DU Bo,et al. Supervised band selection based on class separability for hyperspectral image[J]. Computer Science,2015,42(4):274-275.(in Chinese)
[17] TEILLET P M,GUINDON B,GOODENOUGH D G. On the slope-aspect correction of multispectral scanner data[J]. Canadian Journal of Remote Sensing,1982,8(2):84-106.
[18]穆悦,曹晓阳,冯益明,等.地形复杂山区常用植被指数的地形校正对比[J].地球信息科学学报,2016,18(7):951-961.MU Yue,CAO Xiaoyang,FENG Yiming,et al. Comparison of topographic correction on commonly used vegetation indices in rugged terrain area[J]. Journal of Geo-information Science,2016,18(7):951-961.(in Chinese)
[19]王宏,李晓兵,余弘婧.基于NOAA/AVHRR NDVI监测中国北方典型草原的生长季及变化[J].植物生态学报,2006,30(3):365-374.WANG Hong,LI Xiaobing,YU Hongjing. Monitoring growing season of typical steppe in northern China based on NOAA/AVHRR NDVI data[J]. Acta Phytoecologica Sinica,2006,30(3):365-374.(in Chinese)
[20]汪西莉,焦李成.一种基于马氏距离的支持向量快速提取算法[J].西安电子科技大学学报(自然科学版),2004,31(4):639-643.WANG Xili,JIAO Licheng. A fast algorithm for extracting the support vector on the Mahalanobis distance[J]. Journal of Xidian University(Natural Science),2004,31(4):639-643.(in Chinese)
[21]陈元鹏,郧文聚,周旭,等.基于MESMA和RF的山丘区土地利用信息分类提取[J/OL].农业机械学报,2017,48(7):141-149.CHEN Yuanpeng,YUN Wenju,ZHOU Xu,et al. Classification and extraction of land use information in hilly area based on MESMA and RF classifier[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2017,48(7):141-149.http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? file_no=20170717&flag=1. DOI:10. 6041/j. issn. 1000-1298. 2017. 07. 017.(in Chinese)
[22]林川,宫兆宁,赵文吉.基于中分辨率TM数据的湿地水生植被提取[J].生态学报,2010,30(23):6460-6469.LIN Chuan,GONG Zhaoning,ZHAO Wenji. The extraction of wetland hydrophytes types based on medium resolution TM data[J]. Acta Ecologica Sinica,2010,30(23):6460-6469.(in Chinese)
[23] GONG P,PU R,BIGING G S,et al. Estimation of forest leaf area index using vegetation indices derived from Hyperion hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing,2003,41(6):1355-1362.
[24]赵虎,杨正伟,李霖,等.作物长势遥感监测指标的改进与比较分析[J].农业工程学报,2011,27(1):243-249.ZHAO Hu,YANG Zhengwei,LI Lin,et al. Improvement and comparative analysis of indices of crop growth condition monitoring by remote sensing[J]. Transactions of the CSAE,2011,27(1):243-249.(in Chinese)
[25] AYANLADE A,HOWARD M T. Understanding changes in a Tropical Delta:a multi-method narrative of landuse/landcover change in the Niger Delta[J]. Ecological Modelling,2017,364:53-65.
[26]王蕊,姚治君,刘兆飞.西北干旱区气候和土地利用变化对水沙运移的影响——以小南川流域为例[J].应用生态学报,2018,29(9):2879-2889.WANG Rui,YAO Zhijun,LIU Zhaofei. Impacts of climate and land use change on water and sediment load in the Northwest arid region,China:with Xiaonanchuan River Basin as a case[J]. Chinese Journal of Applied Ecology,2018,29(9):2879-2889.(in Chinese)
[27]左玉珊,王卫,郝彦莉,等.基于MODIS影像的土地覆被分类研究——以京津冀地区为例[J].地理科学进展,2014,33(11):1556-1565.ZUO Yushan,WANG Wei,HAO Yanli,et al. Land cover classification based on MODIS images:taking the Beijing-TianjinHebei region as an example[J]. Progress in Geography,2014,33(11):1556-1565.(in Chinese)
[28] BARRERA F H,ENRIQUEZ C. Vegetation cover change in growing urban agglomerations in Chile[J]. Ecological Indicators,2017,81:265-273.
[29]王李娟,牛铮,赵德刚,等.基于ETM遥感影像的海岸线提取与验证研究[J].遥感技术与应用,2010,25(2):235-239.WANG Lijuan,NIU Zheng,ZHAO Degang,et al. The study of coastline extraction and validation using ETM remote sensing image[J]. Remote Sensing Technology and Application,2010,25(2):235-239.(in Chinese)
[30] GHOSH M K,KUMAR L,ROY C. Monitoring the coastline change of Hatiya Island in Bangladesh using remote sensing techniques[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2015,101:137-144.
[2] YE Y,BRYAN B A,ZHANG J,et al. Changes in land-use and ecosystem services in the Guangzhou-Foshan Metropolitan Area,China from 1990 to 2010:implications for sustainability under rapid urbanization[J]. Ecological Indicators,2018,93:930-941.
[3]王宇航,于强,岳德鹏,等.基于BRT_DC_Pd模型的土地利用模拟研究[J/OL].农业机械学报,2018,49(3):225-234.WANG Yuhang,YU Qiang,YUE Depeng,et al. Simulation of landuse based on BRT_DC_Pd model[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2018,49(3):225-234. http:∥www. j-csam. org/jcsam/ch/reader/view_abstract.aspx? file_no=20180327&flag=1. DOI:10. 6041/j. issn. 1000-1298. 2018. 03. 027.(in Chinese)
[4] DUTTA S,JHALA Y. Planning agriculture based on landuse responses of threatened semiarid grassland species in India[J].Biological Conservation,2014,175:129-139.
[5]龙花楼.论土地利用转型与土地资源管理[J].地理研究,2015,34(9):1607-1618.LONG Hualou. Land use transition and land management[J]. Geographical Research,2015,34(9):1607-1618.(in Chinese)
[6]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.XU Yongming,LIU Yonghong,WEI Ming,et al. Land cover classification of the Yangtze River Delta using MODIS data[J]. Acta Geographica Sinica,2007,62(6):640-648.(in Chinese)
[7]穆少杰,李建龙,陈奕兆,等. 2001—2010年内蒙古植被覆盖度时空变化特征[J].地理学报,2012,67(9):1255-1268.MU Shaojie,LI Jianlong,CHEN Yizhao,et al. Spatial differences of variations of vegetation coverage in Inner Mongolia during2001—2010[J]. Acta Geographica Sinica,2012,67(9):1255-1268.(in Chinese)
[8] FOERSTER S,KADEN K,FOERSTER M,et al. Crop type mapping using spectral-temporal profiles and phenological information[J]. Computers and Electronics in Agriculture,2012,89:30-40.
[9] QI Z,YEH G O,LI X. A crop phenology knowledge-based approach for monthly monitoring of construction land expansion using polarimetric synthetic aperture radar imagery[J]. ISPRS Journal of Photogrammetry&Remote Sensing,2017,133:1-17.
[10] FERENC K. Assessment of regional variations in biomass production using satellite image analysis between 1992 and 2004[J].Transactions in GIS,2007,11(6):911-926.
[11]陈嘉,赵祥,唐荣云,等.基于定量遥感产品的土地覆盖分类方法研究[J].北京师范大学学报(自然科学版),2018,54(3):405-411.CHEN Jia,ZHAO Xiang,TANG Rongyun,et al. Land cover classification by quantitative remote sensing products[J]. Journal of Beijing Normal University(Natural Science),2018,54(3):405-411.(in Chinese)
[12]王正兴,刘闯,HUETE A,等.植被指数研究进展:从AVHRR-NDVI到MODIS-EVI[J].生态学报,2003,23(5):979-987.WANG Zhengxing,LIU Chuang,HUETE A,et al. From AVHRR-NDVI to MODIS-EVI:advances in vegetation index research[J]. Acta Ecologica Sinica,2003,23(5):979-987.(in Chinese)
[13]田庆久,闵祥军.植被指数研究进展[J].地球科学进展,1998,13(4):327-333.TIAN Qingjiu,MIN Xiangjun. Advances in study on vegetation indices[J]. Advance in Earth Sciences,1998,13(4):327-333.(in Chinese)
[14]李行,毛定山,张连蓬.高光谱遥感影像波段选择算法评价方法研究[J].地理与地理信息科学,2006,22(6):34-37.LI Xing,MAO Dingshan,ZHANG Lianpeng. Evaluation method for band selection algorithm of hyperspectral image[J].Geopraphy and Geo-Information Science,2006,22(6):34-37.(in Chinese)
[15]康顺,相诗尧.基于马氏距离的多高斯Voronoi图生成方法[J].地理与地理信息科学,2016,32(3):49-52.KANG Shun,XIANG Shiyao. A generation method of multi-Gaussian Voronoi diagram based on Mahalanobis distance[J].Geography and Geo-Information Science,2016,32(3):49-52.(in Chinese)
[16]许明明,张良培,杜博,等.基于类别可分性的高光谱图像波段选择[J].计算机科学,2015,42(4):274-275.XU Mingming,ZHANG Liangpei,DU Bo,et al. Supervised band selection based on class separability for hyperspectral image[J]. Computer Science,2015,42(4):274-275.(in Chinese)
[17] TEILLET P M,GUINDON B,GOODENOUGH D G. On the slope-aspect correction of multispectral scanner data[J]. Canadian Journal of Remote Sensing,1982,8(2):84-106.
[18]穆悦,曹晓阳,冯益明,等.地形复杂山区常用植被指数的地形校正对比[J].地球信息科学学报,2016,18(7):951-961.MU Yue,CAO Xiaoyang,FENG Yiming,et al. Comparison of topographic correction on commonly used vegetation indices in rugged terrain area[J]. Journal of Geo-information Science,2016,18(7):951-961.(in Chinese)
[19]王宏,李晓兵,余弘婧.基于NOAA/AVHRR NDVI监测中国北方典型草原的生长季及变化[J].植物生态学报,2006,30(3):365-374.WANG Hong,LI Xiaobing,YU Hongjing. Monitoring growing season of typical steppe in northern China based on NOAA/AVHRR NDVI data[J]. Acta Phytoecologica Sinica,2006,30(3):365-374.(in Chinese)
[20]汪西莉,焦李成.一种基于马氏距离的支持向量快速提取算法[J].西安电子科技大学学报(自然科学版),2004,31(4):639-643.WANG Xili,JIAO Licheng. A fast algorithm for extracting the support vector on the Mahalanobis distance[J]. Journal of Xidian University(Natural Science),2004,31(4):639-643.(in Chinese)
[21]陈元鹏,郧文聚,周旭,等.基于MESMA和RF的山丘区土地利用信息分类提取[J/OL].农业机械学报,2017,48(7):141-149.CHEN Yuanpeng,YUN Wenju,ZHOU Xu,et al. Classification and extraction of land use information in hilly area based on MESMA and RF classifier[J/OL]. Transactions of the Chinese Society for Agricultural Machinery,2017,48(7):141-149.http:∥www. j-csam. org/jcsam/ch/reader/view_abstract. aspx? file_no=20170717&flag=1. DOI:10. 6041/j. issn. 1000-1298. 2017. 07. 017.(in Chinese)
[22]林川,宫兆宁,赵文吉.基于中分辨率TM数据的湿地水生植被提取[J].生态学报,2010,30(23):6460-6469.LIN Chuan,GONG Zhaoning,ZHAO Wenji. The extraction of wetland hydrophytes types based on medium resolution TM data[J]. Acta Ecologica Sinica,2010,30(23):6460-6469.(in Chinese)
[23] GONG P,PU R,BIGING G S,et al. Estimation of forest leaf area index using vegetation indices derived from Hyperion hyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing,2003,41(6):1355-1362.
[24]赵虎,杨正伟,李霖,等.作物长势遥感监测指标的改进与比较分析[J].农业工程学报,2011,27(1):243-249.ZHAO Hu,YANG Zhengwei,LI Lin,et al. Improvement and comparative analysis of indices of crop growth condition monitoring by remote sensing[J]. Transactions of the CSAE,2011,27(1):243-249.(in Chinese)
[25] AYANLADE A,HOWARD M T. Understanding changes in a Tropical Delta:a multi-method narrative of landuse/landcover change in the Niger Delta[J]. Ecological Modelling,2017,364:53-65.
[26]王蕊,姚治君,刘兆飞.西北干旱区气候和土地利用变化对水沙运移的影响——以小南川流域为例[J].应用生态学报,2018,29(9):2879-2889.WANG Rui,YAO Zhijun,LIU Zhaofei. Impacts of climate and land use change on water and sediment load in the Northwest arid region,China:with Xiaonanchuan River Basin as a case[J]. Chinese Journal of Applied Ecology,2018,29(9):2879-2889.(in Chinese)
[27]左玉珊,王卫,郝彦莉,等.基于MODIS影像的土地覆被分类研究——以京津冀地区为例[J].地理科学进展,2014,33(11):1556-1565.ZUO Yushan,WANG Wei,HAO Yanli,et al. Land cover classification based on MODIS images:taking the Beijing-TianjinHebei region as an example[J]. Progress in Geography,2014,33(11):1556-1565.(in Chinese)
[28] BARRERA F H,ENRIQUEZ C. Vegetation cover change in growing urban agglomerations in Chile[J]. Ecological Indicators,2017,81:265-273.
[29]王李娟,牛铮,赵德刚,等.基于ETM遥感影像的海岸线提取与验证研究[J].遥感技术与应用,2010,25(2):235-239.WANG Lijuan,NIU Zheng,ZHAO Degang,et al. The study of coastline extraction and validation using ETM remote sensing image[J]. Remote Sensing Technology and Application,2010,25(2):235-239.(in Chinese)
[30] GHOSH M K,KUMAR L,ROY C. Monitoring the coastline change of Hatiya Island in Bangladesh using remote sensing techniques[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2015,101:137-144.