Landscape analysis of wetland plant functional types: The effects of image segmentation scale, vegetation classes and classification methods

文献类型： 外文期刊

第一作者： Dronova, Iryna

作者： Dronova, Iryna;Gong, Peng;Gong, Peng;Wang, Lin;Fu, Wei;Gong, Peng;Wang, Lin;Fu, Wei;Gong, Peng;Clinton, Nicholas E.;Wang, Lin;Qi, Shuhua;Liu, Ying

作者机构：

关键词： Accuracy;Classification;Heterogeneity;Landsat;Landscape;Machine-learning;OBIA;Object-based;Plant functional types;Poyang Lake;China;Remote sensing;Texture;Uncertainty;Vegetation;Wetland

期刊名称：REMOTE SENSING OF ENVIRONMENT （ 影响因子：10.164； 五年影响因子：11.057 ）

ISSN：

年卷期：

页码：

收录情况： SCI

摘要： Remote sensing-based analyses of vegetation function such as photosynthesis and productivity are challenging in wetlands with complex cover and difficult field access. Recent advances in object-based image analysis (OBIA) and machine-learning algorithms offer new image classification tools; however, few comparisons of different approaches have been discussed to date. We applied OBIA to delineate wetland plant functional types (PFTs) for Poyang Lake, the largest freshwater lake in China and Ramsar wetland conservation site, from a spring 2008 Landsat TM image. We targeted major PFTs that represent dominant vegetation groups along wetland inundation gradients and affect ecosystem biogeochemical cycles and ecological habitats. Classification results were compared among: a) several "small" object segmentation scales (with average object sizes 1350-9000m 2); b) algorithms from six families of statistical machine-learning classifiers (Bayesian, Logistic, Neural Network, Decision Trees, K-Nearest Neighbors and Support Vector Machines) and c) two hierarchical levels of vegetation classification, a generalized 3-class set and a more specific 6-class set. We also examined the response of classification accuracy to four basic object-level texture metrics. The highest accuracies (>85-90%) and best agreement among algorithms occurred at coarser object scales rather than close-to-pixel scales. No single machine-learning algorithm was consistently superior at all scales, although support vector machine, k-nearest neighbor and artificial neural network most frequently provided the highest overall and PFT-specific accuracies. Including texture metrics had both positive and negative low-magnitude effects on classification accuracy that were not consistent among scale values, algorithms or PFT classes. Individual PFTs differed in scales at which they were best discriminated from others, reflecting their unique landscape positions, ecology of dominant species and disturbance agents. There was a 29-35% disagreement between mapped areas of generalized PFTs and their respective subclasses, suggesting potential mismatches between the ecological classification scheme and PFT landscape patch structure, and raising concern on error propagation in multi-scale classifications. We conclude that OBIA with machine-learning classifiers is useful for landscape vegetation analyses, however, considerations of spatial scale and image segmentation outcomes are critical in mapping PFTs and should be more thoroughly investigated in future work.

分类号： X83

  • 相关文献

[1]A new time series vegetation-water index of phenological-hydrological trait across species and functional types for Poyang Lake wetland ecosystem. Wang, Lin,Gong, Peng,Wang, Lin,Gong, Peng,Wang, Lin,Yang, Wenbo,Li, Yingren,Liu, Qing,Wang, Lin,Dronova, Iryna,Gong, Peng,Gong, Peng.

[2]Exploring the Use of Google Earth Imagery and Object-Based Methods in Land Use/Cover Mapping. Hu, Qiong,Wu, Wenbin,Xia, Tian,Yu, Qiangyi,Yang, Peng,Li, Zhengguo,Song, Qian,Hu, Qiong,Wu, Wenbin,Xia, Tian,Yu, Qiangyi,Yang, Peng,Li, Zhengguo,Song, Qian. 2013

[3]Monitoring Thermal Pollution in Rivers Downstream of Dams with Landsat ETM plus Thermal Infrared Images. Ling, Feng,Ban, Xuan,Li, Xiaodong,Zhang, Yihang,Du, Yun,Foody, Giles M.,Du, Hao. 2017

[4]A Review of Wetland Remote Sensing. Guo, Meng,Xu, Jiawei,Li, Jing,Sheng, Chunlei,Wu, Li. 2017

[5]Relationships between soil respiration and photosynthesis-related spectral vegetation indices in two cropland ecosystems. Huang, Ni,Niu, Zheng,Zhan, Yulin,Xu, Shiguang,Wu, Chaoyang,Gao, Shuai,Hou, Xuehui,Cai, Dewen,Huang, Ni,Xu, Shiguang,Hou, Xuehui,Cai, Dewen,Tappert, Michelle C.,Huang, Wenjiang.

[6]Spatio-Temporal Dynamics of Land-Use and Land-Cover in the Mu Us Sandy Land, China, Using the Change Vector Analysis Technique. Karnieli, Arnon,Panov, Natalya,Qin, Zhihao,Wu, Bo,Yan, Feng. 2014

[7]An Enhanced IT2FCM*Algorithm Integrating Spectral Indices and Spatial Information for Multi-Spectral Remote Sensing Image Clustering. Guo, Jifa,Huo, Hongyuan. 2017

[8]Nematode Diversity in Phaeozem Agroecosystems of Northeast China. Li Qi,Jiang Yong,Liang Wen-Ju,Jiang Si-Wei,Liang Wen-Ju,Wang He.

[9]An infectious cDNA clone of a highly pathogenic porcine reproductive and respiratory syndrome virus variant associated with porcine high fever syndrome. Lv, Jian,Zhan, Jianwu,Sun, Zhi,Yuan, Shishan,Lv, Jian,Liu, Weiquan.

[10]FRACTAL ANALYSIS APPLIED TO SPATIAL STRUCTURE OF CHINA'S VEGETATION. Yang Xiu-chun,Zuo Wei,Patel Nilanchal,Zhu Xiao-hua.

[11]Regional yield estimation for winter wheat with MODIS-NDVI data in Shandong, China. Ren, Jianqiang,Chen, Zhongxin,Zhou, Qingbo,Tang, Huajun,Ren, Jianqiang,Chen, Zhongxin,Zhou, Qingbo,Tang, Huajun. 2008

[12]Valuation of rangeland ecosystem degradation with remote sensing technology in China. Wang, Ruijie,Qin, Zhihao,Jiang, Lipeng,Ye, Ke,Qin, Zhihao. 2006

[13]Long-Term Water Temperature Variations in Daya Bay, China Using Satellite and In Situ Observations. Yu, Jing,Chen, Pimao,Jia, Xiaoping,Li, Chunhou,Yu, Jing,Chen, Pimao,Jia, Xiaoping,Li, Chunhou,Yu, Jing,Chen, Pimao,Jia, Xiaoping,Li, Chunhou,Yu, Jing,Tang, Danling,Yao, Lijun. 2010

[14]Ecological effects of artificial reefs in Daya Bay of China observed from satellite and in situ measurements. Yu, Jing,Chen, Pimao,Qin, Chuanxin,Yu, Jing,Chen, Pimao,Qin, Chuanxin,Yu, Jing,Chen, Pimao,Qin, Chuanxin,Tang, Danling.

[15]Assessment of grassland degradation in Guinan county, Qinghai Province, China, in the past 30 years. Feng, Y.,Lu, Q.,Wang, X.,Tokola, T.,Liu, H..

[16]Land surface phenology of China's temperate ecosystems over 1999-2013: Spatial-temporal patterns, interaction effects, covariation with climate and implications for productivity. Wu, Chaoyang,Peng, Dailiang,Xu, Shiguang,Hou, Xuehui,Gonsamo, Alemu,Gonsamo, Alemu.

[17]Effects of meteorological factors on different grades of winter wheat growth in the Huang-Huai-Hai Plain, China. Huang Qing,Wang Li-min,Chen Zhong-xin,Liu Hang. 2016

[18]Identification of potential areas for biomass production in China: Discussion of a recent approach and future challenges. Schweers, Wilko,Zhihao, Qin,Cai, Dianxiong,Jin, Yunxiang,Bai, Zhanguo,Campbell, Elliott,Hennenberg, Klaus,Fritsche, Uwe,Mang, Heinz-Peter,Lucas, Mario,Li, Zifu,Scanlon, Andrew,Chen, Haoran,Zhihao, Qin,Zhang, Jun,Tu, Lili,Gemmer, Marco,Jiang, Tong,Zhang, Nannan. 2011

[19]Assessing the effect of desertification controlling projects and policies in northern Shaanxi Province, China by integrating remote sensing and farmer investigation data. Xu, Duanyang,Song, Alin,Song, Xiao. 2017

[20]Impact of plant roots on the resistance of soils to erosion by water: a review. Gyssels, G,Poesen, J,Bochet, E,Li, Y.

作者其他论文 更多>>

微信小程序