文献类型： 外文期刊

作者： Hu, Tianyu ¹ ; Cao, Mengqi ¹ ; Zhao, Xiaoxia ¹ ; Liu, Xiaoqiang ¹ ; Liu, Zhonghua ¹ ; Liu, Liangyun ⁴ ; Huang, Zhengying ¹ ; Tao, Shengli ⁵ ; Tang, Zhiyao ⁵ ; Guo, Yanpei ⁵ ; Ji, Chengjun ⁵ ; Zheng, Chengyang ⁵ ; Wang, Guoyan ⁸ ; Hu, Xiaokang ⁹ ; Zhou, Luhong ¹⁰ ; Cheng, Yunxiang ¹¹ ; Ma, Wenhong ¹¹ ; Wang, Yonghui ¹¹ ; Zhang, Pujin ¹³ ; Fan, Yuejun ¹⁴ ; Yu, Feihai ¹⁵ ; Wang, Zhong ¹⁶ ; Qiao, Xiujuan ¹⁷ ; Cheng, Xiaoli ¹⁸ ; Yin, Chunying ¹⁹ ; Ma, Hongyuan ²¹ ; Li, Liping ⁴ ; Yang, Yan ²² ; Luo, Wanyin ²³ ; Gong, Yanming ²⁴ ; Wang, Lei ²⁴ ; Chen, Leiyi ¹ ; Liu, Guofang ¹ ; Song, Chuangye ¹ ; Yang, Xuejun ¹ ; Ye, Xuehua ¹ ; Zhang, Shuren ² ; Zhu, Xiangyun ²⁵ ; Wang, Qinggang ²⁶ ; Li, Shijin ²⁷ ; Yang, Yongchuan ²⁸ ; Liu, Lingli ¹ ; Kelly, Maggi ²⁹ ; Fang, Jingyun ⁵ ; Su, Yanjun ¹ ;

作者机构： 1.Chinese Acad Sci, State Key Lab Vegetat & Environm Change, Inst Bot, Beijing 100093, Peoples R China

2.China Natl Bot Garden, Beijing 100093, Peoples R China

3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China

4.Aerosp Informat Res Inst, Key Lab Digital Earth Sci, Beijing 100094, Peoples R China

5.Peking Univ, Inst Ecol, Coll Urban & Environm Sci, Beijing 100871, Peoples R China

6.Peking Univ, Key Lab Earth Surface Proc, Minist Educ, Beijing 100871, Peoples R China

7.Beijing Forestry Univ, Sch Soil & Water Conservat, Yanchi Res Stn, Beijing 100083, Peoples R China

8.Chengdu Univ Technol, State Key Lab Geohazard Prevent & Geoenvironm Prot, Chengdu 610059, Peoples R China

9.Dali Univ, Coll Agr & Biol Sci, Coinnovat Ctr Cangshan Mt & Erhai Lake Integrated, Dali 671003, Peoples R China

10.Fujian Normal Univ, Sch Geog Sci, Key Lab Humid Subtrop Ecogeog Proc, Minist Educ, Fuzhou 350007, Peoples R China

11.Inner Mongolia Univ, Sch Ecol & Environm, Minist Educ, Key Lab Ecol & Resource Use Mongolian Plateau & In, Hohhot 010021, Peoples R China

12.Inner Mongolia Univ, Sch Ecol & Environm, Inner Mongolia Key Lab Grassland Ecol, Hohhot 010021, Peoples R China

13.Inner Mongolia Acad Agr & Anim Husb Sci, Inst Grassland Res, Hohhot 010031, Peoples R China

14.Qinghai Agrianim Husb Vocat Coll, Xining 812100, Peoples R China

15.Taizhou Univ, Inst Wetland Ecol & Clone Ecol, Zhejiang Prov Key Lab Evolutionary Ecol & Conserva, Taizhou 318000, Peoples R China

16.Wuhan Univ, Coll Life Sci, Dept Ecol, Wuhan 430072, Peoples R China

17.Chinese Acad Sci, State Key Lab Plant Divers & Specialty Crops, Wuhan Bot Garden, Wuhan 430074, Peoples R China

18.Yunnan Univ, Sch Ecol & Environm Sci, Yunnan Key Lab Soil Eros Prevent & Green Dev, Kunming 650091, Peoples R China

19.Chinese Acad Sci, Chengdu Inst Biol, CAS Key Lab Mt Ecol Restorat & Bioresource Utiliza, Chengdu 610041, Peoples R China

20.Chinese Acad Sci, Chengdu Inst Biol, Ecol Restorat & Biodivers Conservat Key Lab Sichua, Chengdu 610041, Peoples R China

21.Chinese Acad Sci, Northeast Inst Geog & Agroecol, Changchun 130102, Peoples R China

22.Chinese Acad Sci, Inst Mt Hazards & Environm, Chengdu 610041, Peoples R China

23.Chinese Acad Sci, Key Lab Desert & Desertificat, Northwest Inst Ecoenvironm & Resources, Lanzhou 730000, Peoples R China

24.Chinese Acad Sci, Xinjiang Inst Ecol & Geog, Urumqi 830011, Peoples R China

25.Chinese Acad Sci, State Key Lab Systemat & Evolutionary Bot, Inst Bot, Beijing 100093, Peoples R China

26.China Agr Univ, Coll Resources & Environm Sci, Beijing 100083, Peoples R China

27.Chinese Acad Sci, Key Lab Plant Resources Conservat & Sustainable Ut, South China Bot Garden, Guangzhou 510650, Peoples R China

28.Chongqing Univ, Coll Environm & Ecol, Chongqing 400045, Peoples R China

29.Univ Calif Berkeley, Dept Environm Sci Policy & Management, Berkeley, CA 94720 USA

30.Univ Calif Berkeley, Div Agr & Nat Resources, Berkeley, CA 94720 USA

关键词： Grassland; Canopy cover; Drone imagery; Machine learning; Scale mismatch

期刊名称：ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING （ 影响因子：12.2； 五年影响因子：13.7 ）

ISSN： 0924-2716

年卷期： 2024 年 218 卷

页码：

收录情况： SCI

摘要： Canopy cover is a crucial indicator for assessing grassland health and ecosystem services. However, achieving accurate high-resolution estimates of grassland canopy cover at a large spatial scale remains challenging due to the limited spatial coverage of field measurements and the scale mismatch between field measurements and satellite imagery. In this study, we addressed these challenges by proposing a regression-based approach to estimate large-scale grassland canopy cover, leveraging the integration of drone imagery and multisource remote sensing data. Specifically, over 90,000 10 x 10 m drone image tiles were collected at 1,255 sites across China. All drone image tiles were classified into grass and non-grass pixels to generate ground-truth canopy cover estimates. These estimates were then temporally aligned with satellite imagery-derived features to build a random forest regression model to map the grassland canopy cover distribution of China. Our results revealed that a single classification model can effectively distinguish between grass and non-grass pixels in drone images collected across diverse grassland types and large spatial scales, with multilayer perceptron demonstrating superior classification accuracy compared to Canopeo, support vector machine, random forest, and pyramid scene parsing network. The integration of extensive drone imagery successfully addressed the scale-mismatch issue between traditional ground measurements and satellite imagery, contributing significantly to enhancing mapping accuracy. The national canopy cover map of China generated for the year 2021 exhibited a spatial pattern of increasing canopy cover from northwest to southeast, with an average value of 56 % and a standard deviation of 26 %. Moreover, it demonstrated high accuracy, with a coefficient of determination of 0.89 and a root-mean- squared error of 12.38 %. The resulting high-resolution canopy cover map of China holds great potential in advancing our comprehension of grassland ecosystem processes and advocating for the sustainable management of grassland resources.