文献类型：期刊文献

英文题名：Integrating vegetation phenological characteristics and polarization features with object-oriented techniques for grassland type identification

作者：Sun, Bin[1,2] Qin, Pengyao[1,2] Li, Changlong[3] Gao, Zhihai[1,2] Grainger, Alan[4] Li, Xiaosong[5] Wang, Yan[6] Yue, Wei[1,2]

第一作者：孙斌;Sun, Bin

通信作者：Gao, ZH[1];Gao, ZH[2]

机构：[1]Chinese Acad Forestry, Inst Forest Resource Informat Tech, Beijing, Peoples R China;[2]NFGA, Key Lab Forestry Remote Sensing & Informat Syst, Beijing, Peoples R China;[3]Guangzhou Coll Commerce, Sch Informat Technol & Engn, Guangzhou, Peoples R China;[4]Univ Leeds, Sch Geog, Leeds, England;[5]Chinese Acad Sci, Aerosp Informat Res Inst, Beijing, Peoples R China;[6]Shandong Geog Inst Land Spatial Data & Remote Sens, Jinan, Peoples R China

年份：2023

外文期刊名：GEO-SPATIAL INFORMATION SCIENCE

收录：;EI(收录号：20234114850085);Scopus(收录号：2-s2.0-85173964532);WOS:【SCI-EXPANDED(收录号:WOS:001073874700001)】；

基金：This work was supported by the National Natural Science Foundation of China [grant number 42001386; 42271407] and within the ESA-MOST China Dragon 5 Cooperation (ID:59313).

语种：英文

外文关键词：Grassland types; vegetation phenological characteristics; polarization feature; integrated active and passive remote sensing; object-oriented classification

摘要：Due to the small size, variety, and high degree of mixing of herbaceous vegetation, remote sensing-based identification of grassland types primarily focuses on extracting major grassland categories, lacking detailed depiction. This limitation significantly hampers the development of effective evaluation and fine supervision for the rational utilization of grassland resources. To address this issue, this study concentrates on the representative grassland of Zhenglan Banner in Inner Mongolia as the study area. It integrates the strengths of Sentinel-1 and Sentinel-2 active-passive synergistic observations and introduces innovative object-oriented techniques for grassland type classification, thereby enhancing the accuracy and refinement of grassland classification. The results demonstrate the following: (1) To meet the supervision requirements of grassland resources, we propose a grassland type classification system based on remote sensing and the vegetation-habitat classification method, specifically applicable to natural grasslands in northern China. (2) By utilizing the high-spatial-resolution Normalized Difference Vegetation Index (NDVI) synthesized through the Spatial and Temporal Non-Local Filter-based Fusion Model (STNLFFM), we are able to capture the NDVI time profiles of grassland types, accurately extract vegetation phenological information within the year, and further enhance the temporal resolution. (3) The integration of multi-seasonal spectral, polarization, and phenological characteristics significantly improves the classification accuracy of grassland types. The overall accuracy reaches 82.61%, with a kappa coefficient of 0.79. Compared to using only multi-seasonal spectral features, the accuracy and kappa coefficient have improved by 15.94% and 0.19, respectively. Notably, the accuracy improvement of the gently sloping steppe is the highest, exceeding 38%. (4) Sandy grassland is the most widespread in the study area, and the growth season of grassland vegetation mainly occurs from May to September. The sandy meadow exhibits a longer growing season compared with typical grassland and meadow, and the distinct differences in phenological characteristics contribute to the accurate identification of various grassland types.