草业学报 ›› 2023, Vol. 32 ›› Issue (9): 1-16.DOI: 10.11686/cyxb2022405
• 研究论文 •
杨志贵1(), 张建国1, 李锦荣2, 于红妍3, 常丽4, 宜树华1, 吕燕燕1, 张玉琢1, 孟宝平1()
收稿日期:
2022-10-10
修回日期:
2022-11-28
出版日期:
2023-09-20
发布日期:
2023-07-12
通讯作者:
孟宝平
作者简介:
E-mail: mengbp09@lzu.edu.cn基金资助:
Zhi-gui YANG1(), Jian-guo ZHANG1, Jin-rong LI2, Hong-yan YU3, Li CHANG4, Shu-hua YI1, Yan-yan LYU1, Yu-zhuo ZHANG1, Bao-ping MENG1()
Received:
2022-10-10
Revised:
2022-11-28
Online:
2023-09-20
Published:
2023-07-12
Contact:
Bao-ping MENG
摘要:
草地类型是人类科学开发、合理利用和有效保护草地资源的重要依据,同时还是维持草地生态系统可持续发展的重要依据。目前,国内外有关土地利用类型时空变化的研究已有丰硕成果,但区域尺度草地类型时空动态变化的研究鲜有报道。因此,以内蒙古温性草原为研究对象,基于遥感植被指数、气象、土壤、地形和无人机航拍资料,结合机器学习算法构建了内蒙古草地类型分类算法,并以此为依据,分析草地类型时空动态变化特征。结果表明:1)所有遥感分类特征指标中,降水、归一化植被指数(NDVI)对研究区草地类型分类的重要性值高于其他指标,前18个分类指标(按重要性值排)的累计贡献率达85%以上;2)随机森林(RF)模型对内蒙古温性草原草地类型的分类精度最高,总体分类精度(OA)为82.16%,卡帕系数(Kappa)为0.76;3)过去20年来内蒙古地区草地类型之间的转换比较剧烈,多发生在典型草原、荒漠化草原和荒漠之间。相较于20世纪80年代草地类型,2000-2009年草地类型多由湿润类型向干旱类型转变,然而2010-2019年的草地类型则由干旱类型向湿润类型转变。本研究结果可为全球气候变化和人类活动下内蒙古草地类型的变化研究提供科学依据,同时也可为内蒙古地区草地可持续发展提供理论依据和技术支撑。
杨志贵, 张建国, 李锦荣, 于红妍, 常丽, 宜树华, 吕燕燕, 张玉琢, 孟宝平. 内蒙古温性草原草地类型近20年时空动态变化研究[J]. 草业学报, 2023, 32(9): 1-16.
Zhi-gui YANG, Jian-guo ZHANG, Jin-rong LI, Hong-yan YU, Li CHANG, Shu-hua YI, Yan-yan LYU, Yu-zhuo ZHANG, Bao-ping MENG. Spatiotemporal dynamic variation of temperate grassland classes in Inner Mongolia in the last 20 years[J]. Acta Prataculturae Sinica, 2023, 32(9): 1-16.
图1 研究区概况19世纪80年代草地类型图;该图基于审图号为GS(2019)1822号的标准地图制作,底图无修改。Grassland classes (in the 1980s); The map was based on the standard map with the drawing review No. GS(2019)1822, and the base map was not modified.
Fig.1 Overview of the study area
图2 野外工作点设置a为工作点航线设置;b和c分别为御2变焦版和精灵系列无人机。a is the strategy of observation site; b and c are Phantom 3 professional and Mavic 2 zoom Quad-Rotor intelligent unmanned aerial vehicle (UAV), respectively.
Fig.2 Strategy of field observation and data collection
图3 内蒙古不同草地类型分类依据MS、TS、DS、SD、D分别表示草甸草原、典型草原、荒漠化草原、草原化荒漠和荒漠,下同。a~e为20 m航高垂直航拍照片;f~j为20 m航高倾斜45°航拍照片;k~o为2 m航高2倍焦距航拍照片;a、f、k为草甸草原;b、g、l为典型草原;c、h、m为荒漠化草原;d、i、n为草原化荒漠;e、j、o为荒漠。MS, TS, DS, SD and D were represented meadow steppe, typical steppe, desert steppe, steppe desert and desert, the same below. a-e were taken vertically downward at the height of 20 m; f-j were taken tilted with 45° at the height of 20 m; k-o were aerial photographs taken at the height of 2 m by Mavic 2, acquired with 2× wide-angle zoom lenses; a, f, k were meadow steppe; b, g, l were typical steppe; c, h, m were desert steppe; d, i, n were steppe desert; e, j, o were deserts.
Fig.3 Classification criteria for aerial photographs of temperate steppe classes
草地类型 Grassland classes | 生活型 Vegetation life form | 优势种 Dominant grass species | 草地盖度 Coverage (%) |
---|---|---|---|
荒漠 Desert | 超旱生小灌木、小半灌木Extremely xerophytic short shrubs, short semishrubs | 珍珠、松叶猪毛菜、红砂、盐爪爪、沙蒿、沙竹Lyonia ovalifolia, Salsola laricifolia,Reaumuria songarica, Kalidium foliatum,Artemisia desertorum, Psammochloa villosa | 0~20 |
草原化荒漠 Steppe desert | 强旱生半灌木和灌木、旱生草本Super xerophytic semishrubs, shrubs, and xerophytic grasses | 纤细绢蒿、白茎绢蒿、博洛塔绢蒿、合头草、琵琶柴、短叶假木贼、沙生针茅Seriphidium gracilescens, Seriphidium terrae-albae,Seriphidium borotalense, Sympegma regelii,Reaumuria soongorica, Anabasis brevifolia,Stipa glareosa | 20~30 |
荒漠化草原 Desert steppe | 强旱生多年生草本植物、旱生小半灌木Super xerophytic perennial grasses, xerophytic short semishrubs | 石生针茅、戈壁针茅、短花针茅、无芒隐子草、冷蒿、多茎葱、蒙古葱Stipa tianschanica var. klemenzii, Stipa tianschanica var. gobica, Stipa breviflora, Cleistogenessongorica, Artemisia frigida, Allium mongolicum,Allium aflatunense | 30~40 |
典型草原 Typical steppe | 旱生多年生丛生禾草、旱生小灌木Xerophytic perennial tufted grasses, xerophytic short shrubs | 大针茅、克氏针茅、本氏针茅、糙隐子草、冰草、冷蒿、锦鸡儿Stipa grandis, Stipa krylovii, Stipa bungeana,Cleistogenes squarrosa, Agropyron cristatum,A. frigida, Caragana sinica | 60~70 |
草甸草原 Meadow steppe | 中旱生多年生丛生禾草及根茎禾草Mesoxerophytic perennial tufted grasses and root grasses | 贝加尔针茅、羊草、线叶菊Stipa baicalensis, Leymus chinensis,Filifolium sibiricum | 70~90 |
表1 不同草地类型植被特征
Table 1 Characteristics of different grassland classes in temperate steppe
草地类型 Grassland classes | 生活型 Vegetation life form | 优势种 Dominant grass species | 草地盖度 Coverage (%) |
---|---|---|---|
荒漠 Desert | 超旱生小灌木、小半灌木Extremely xerophytic short shrubs, short semishrubs | 珍珠、松叶猪毛菜、红砂、盐爪爪、沙蒿、沙竹Lyonia ovalifolia, Salsola laricifolia,Reaumuria songarica, Kalidium foliatum,Artemisia desertorum, Psammochloa villosa | 0~20 |
草原化荒漠 Steppe desert | 强旱生半灌木和灌木、旱生草本Super xerophytic semishrubs, shrubs, and xerophytic grasses | 纤细绢蒿、白茎绢蒿、博洛塔绢蒿、合头草、琵琶柴、短叶假木贼、沙生针茅Seriphidium gracilescens, Seriphidium terrae-albae,Seriphidium borotalense, Sympegma regelii,Reaumuria soongorica, Anabasis brevifolia,Stipa glareosa | 20~30 |
荒漠化草原 Desert steppe | 强旱生多年生草本植物、旱生小半灌木Super xerophytic perennial grasses, xerophytic short semishrubs | 石生针茅、戈壁针茅、短花针茅、无芒隐子草、冷蒿、多茎葱、蒙古葱Stipa tianschanica var. klemenzii, Stipa tianschanica var. gobica, Stipa breviflora, Cleistogenessongorica, Artemisia frigida, Allium mongolicum,Allium aflatunense | 30~40 |
典型草原 Typical steppe | 旱生多年生丛生禾草、旱生小灌木Xerophytic perennial tufted grasses, xerophytic short shrubs | 大针茅、克氏针茅、本氏针茅、糙隐子草、冰草、冷蒿、锦鸡儿Stipa grandis, Stipa krylovii, Stipa bungeana,Cleistogenes squarrosa, Agropyron cristatum,A. frigida, Caragana sinica | 60~70 |
草甸草原 Meadow steppe | 中旱生多年生丛生禾草及根茎禾草Mesoxerophytic perennial tufted grasses and root grasses | 贝加尔针茅、羊草、线叶菊Stipa baicalensis, Leymus chinensis,Filifolium sibiricum | 70~90 |
土地覆盖 Land cover | MCD12Q1产品类型 Types of MCD12Q1 |
---|---|
草地Grassland | 稠密灌丛Dense shrub (6)、稀疏灌丛Sparse shrubs (7)、草地Grassland (10)、永久湿地Permanent wetland (11)、稀疏植被Sparse vegetation (16) |
林地Forest | 常绿针叶林Evergreen coniferous forest (1)、常绿阔叶林Broad-leaved evergreen forest (2)、落叶针叶林Deciduous needle-leaf forest (3)、落叶阔叶林Deciduous broadleaved forest (4)、混交林Mixed forest (5)、木本热带稀树草原Woody tropical savanna (8)、热带稀树草原Tropical savanna (9) |
水体Water bodies | 水Water (17) |
永久冰雪Permanent snow and ice | 雪和冰Snow and ice (15) |
其他Others | 农用地Agricultural land (12)、城市和建筑区Cities and building areas (13)、农用地和自然植被Agricultural land and natural vegetation (14) |
表2 土地覆盖类型重分类方案
Table 2 Scheme of land cover types reclassification
土地覆盖 Land cover | MCD12Q1产品类型 Types of MCD12Q1 |
---|---|
草地Grassland | 稠密灌丛Dense shrub (6)、稀疏灌丛Sparse shrubs (7)、草地Grassland (10)、永久湿地Permanent wetland (11)、稀疏植被Sparse vegetation (16) |
林地Forest | 常绿针叶林Evergreen coniferous forest (1)、常绿阔叶林Broad-leaved evergreen forest (2)、落叶针叶林Deciduous needle-leaf forest (3)、落叶阔叶林Deciduous broadleaved forest (4)、混交林Mixed forest (5)、木本热带稀树草原Woody tropical savanna (8)、热带稀树草原Tropical savanna (9) |
水体Water bodies | 水Water (17) |
永久冰雪Permanent snow and ice | 雪和冰Snow and ice (15) |
其他Others | 农用地Agricultural land (12)、城市和建筑区Cities and building areas (13)、农用地和自然植被Agricultural land and natural vegetation (14) |
图4 无人机观测样地草地类型识别结果该图基于审图号为 GS(2019)1822 号的标准地图制作,底图无修改。The map was based on the standard map with the drawing review No. GS(2019)1822, and the base map was not modified.
Fig.4 Results of grassland type identification in UAV observation plot
指标Index | 重要性Importance | 累计贡献度Cumulative contribution | 指标Index | 重要性Importance | 累计贡献度Cumulative contribution |
---|---|---|---|---|---|
Pre_max | 8.46 | 8.46 | Pre_mea | 2.91 | 82.43 |
Tem_med | 8.07 | 16.53 | NDVI_min | 2.30 | 84.72 |
Pre_ran | 7.05 | 23.57 | Pre_min | 1.99 | 86.72 |
Tem_max | 6.98 | 30.56 | NDVI_ran | 1.88 | 88.60 |
Tem_mea | 6.31 | 36.86 | Tem_std | 1.75 | 90.35 |
Tem_sum | 6.30 | 43.17 | Slope | 1.52 | 91.87 |
Tem_min | 5.87 | 49.04 | NDVI_std | 1.49 | 93.36 |
Pre_std | 4.90 | 53.94 | Tem_ran | 1.48 | 94.84 |
NDVI_mea | 4.22 | 58.16 | Clay1 | 1.15 | 95.99 |
NDVI_sum | 4.07 | 62.23 | Sand1 | 1.08 | 97.06 |
Pre_sum | 3.77 | 66.00 | Aspect | 0.96 | 98.03 |
NDVI_max | 3.63 | 69.63 | Sand2 | 0.95 | 98.98 |
NDVI_med | 3.42 | 73.05 | Clay2 | 0.80 | 99.77 |
DEM | 3.39 | 76.44 | Posi | 0.23 | 100.00 |
Pre_med | 3.08 | 79.52 |
表3 NDVI特征指数的重要性和累积贡献度
Table 3 Importance and cumulative contribution of NDVI characteristics indices (%)
指标Index | 重要性Importance | 累计贡献度Cumulative contribution | 指标Index | 重要性Importance | 累计贡献度Cumulative contribution |
---|---|---|---|---|---|
Pre_max | 8.46 | 8.46 | Pre_mea | 2.91 | 82.43 |
Tem_med | 8.07 | 16.53 | NDVI_min | 2.30 | 84.72 |
Pre_ran | 7.05 | 23.57 | Pre_min | 1.99 | 86.72 |
Tem_max | 6.98 | 30.56 | NDVI_ran | 1.88 | 88.60 |
Tem_mea | 6.31 | 36.86 | Tem_std | 1.75 | 90.35 |
Tem_sum | 6.30 | 43.17 | Slope | 1.52 | 91.87 |
Tem_min | 5.87 | 49.04 | NDVI_std | 1.49 | 93.36 |
Pre_std | 4.90 | 53.94 | Tem_ran | 1.48 | 94.84 |
NDVI_mea | 4.22 | 58.16 | Clay1 | 1.15 | 95.99 |
NDVI_sum | 4.07 | 62.23 | Sand1 | 1.08 | 97.06 |
Pre_sum | 3.77 | 66.00 | Aspect | 0.96 | 98.03 |
NDVI_max | 3.63 | 69.63 | Sand2 | 0.95 | 98.98 |
NDVI_med | 3.42 | 73.05 | Clay2 | 0.80 | 99.77 |
DEM | 3.39 | 76.44 | Posi | 0.23 | 100.00 |
Pre_med | 3.08 | 79.52 |
草地类型 Grassland classes | 随机森林RF | 支持向量机SVM | 人工神经网络ANN | |||
---|---|---|---|---|---|---|
PA (%) | UA (%) | PA (%) | UA (%) | PA (%) | UA (%) | |
草甸草原Meadow steppe | 64.29 | 77.14 | 85.00 | 80.95 | 65.71 | 65.71 |
典型草原Typical steppe | 89.27 | 78.02 | 81.58 | 65.22 | 82.22 | 81.32 |
荒漠化草原Desert steppe | 78.00 | 88.64 | 75.53 | 75.00 | 71.43 | 68.18 |
草原化荒漠Steppe desert | 85.71 | 85.71 | 75.00 | 79.59 | 76.67 | 82.14 |
荒漠 Desert | 100.00 | 93.33 | 100.00 | 91.18 | 87.50 | 93.33 |
总体分类精度OA (%) | 82.16 | 79.81 | 77.00 | |||
卡帕系数Kappa | 0.76 | 0.72 | 0.68 |
表4 基于随机森林、支持向量机和人工神经网络的内蒙古5个草地类型的精度
Table 4 Accuracy of five grasslands based on random forest (RF), support vector machine (SVM) and artificial neural network (ANN) in Inner Mongolia
草地类型 Grassland classes | 随机森林RF | 支持向量机SVM | 人工神经网络ANN | |||
---|---|---|---|---|---|---|
PA (%) | UA (%) | PA (%) | UA (%) | PA (%) | UA (%) | |
草甸草原Meadow steppe | 64.29 | 77.14 | 85.00 | 80.95 | 65.71 | 65.71 |
典型草原Typical steppe | 89.27 | 78.02 | 81.58 | 65.22 | 82.22 | 81.32 |
荒漠化草原Desert steppe | 78.00 | 88.64 | 75.53 | 75.00 | 71.43 | 68.18 |
草原化荒漠Steppe desert | 85.71 | 85.71 | 75.00 | 79.59 | 76.67 | 82.14 |
荒漠 Desert | 100.00 | 93.33 | 100.00 | 91.18 | 87.50 | 93.33 |
总体分类精度OA (%) | 82.16 | 79.81 | 77.00 | |||
卡帕系数Kappa | 0.76 | 0.72 | 0.68 |
草地类型 Grassland classes | 验证集Validation dataset | 总计 Total | 用户精度 UA (%) | ||||
---|---|---|---|---|---|---|---|
草甸草原 Meadow steppe | 典型草原Typical steppe | 荒漠化草原Desert steppe | 草原化荒漠Steppe desert | 荒漠 Desert | |||
草甸草原Meadow steppe | 27 | 5 | 2 | 1 | 0 | 35 | 77.14 |
典型草原Typical steppe | 15 | 71 | 5 | 0 | 0 | 91 | 78.02 |
荒漠化草原Desert steppe | 0 | 3 | 39 | 2 | 0 | 44 | 88.64 |
草原化荒漠Steppe desert | 0 | 0 | 4 | 24 | 0 | 28 | 85.71 |
荒漠Desert | 0 | 0 | 0 | 1 | 14 | 15 | 93.33 |
总计Total | 42 | 79 | 50 | 28 | 14 | 213 | - |
生产者精度PA (%) | 64.29 | 89.27 | 78.00 | 85.71 | 100.00 | - | - |
表5 基于RF算法的草地分类混淆矩阵
Table 5 The confusion matrix of five grassland classes based on RF algorithma
草地类型 Grassland classes | 验证集Validation dataset | 总计 Total | 用户精度 UA (%) | ||||
---|---|---|---|---|---|---|---|
草甸草原 Meadow steppe | 典型草原Typical steppe | 荒漠化草原Desert steppe | 草原化荒漠Steppe desert | 荒漠 Desert | |||
草甸草原Meadow steppe | 27 | 5 | 2 | 1 | 0 | 35 | 77.14 |
典型草原Typical steppe | 15 | 71 | 5 | 0 | 0 | 91 | 78.02 |
荒漠化草原Desert steppe | 0 | 3 | 39 | 2 | 0 | 44 | 88.64 |
草原化荒漠Steppe desert | 0 | 0 | 4 | 24 | 0 | 28 | 85.71 |
荒漠Desert | 0 | 0 | 0 | 1 | 14 | 15 | 93.33 |
总计Total | 42 | 79 | 50 | 28 | 14 | 213 | - |
生产者精度PA (%) | 64.29 | 89.27 | 78.00 | 85.71 | 100.00 | - | - |
图5 基于2000-2009年、2010-2019年MODIS NDVI特征指标和RF算法的内蒙古地区草地类型空间分布该图基于审图号为 GS(2019)1822 号的标准地图制作,底图无修改。The map was based on the standard map with the drawing review No. GS(2019)1822, and the base map was not modified. Non表示非草地。下同。Non was represented non-grassland. The same below.
Fig.5 Spatial distribution of grassland types in Inner Mongolia based on MODIS NDVI and RF algorithm from 2000 to 2009 and from 2010 to 2019
图6 内蒙古地区草地类型空间分布该图基于审图号为 GS(2019)1822 号的标准地图制作,底图无修改。The map was based on the standard map with the drawing review No. GS(2019)1822, and the base map was not modified. D-DS: 荒漠转化为荒漠化草原,以此类推。Desert was transformed into desert steppe, and so on.
Fig.6 The spatial distribution of grassland types in Inner Mongolia
1 | Ren J Z, Hu Z Z, Mou X D, et al. Comprehensive sequential classification of grassland and its significance in grassland genesis. Chinese Journal of Grassland, 1980(1): 12-24, 38. |
任继周, 胡自治, 牟新待, 等. 草原的综合顺序分类法及其草原发生学意义. 中国草原, 1980(1): 12-24, 38. | |
2 | Ren J Z. Classfication and cluster applicable for grassland type. Acta Agrestia Sinica, 2008, 16(1): 4-10. |
任继周. 分类、聚类与草原类型. 草地学报, 2008, 16(1): 4-10. | |
3 | Ren J Z, Hu Z Z, Zhao J, et al. A grassland classification system and its application in China. The Rangeland Journal, 2008, 30(2): 199-209. |
4 | Ma X L, Li W J, Chen Q G. Preliminary exploration of native grassland classification of Gansu Province based on GIS and comprehensive and sequential grassland classification method. Pratacultural Science, 2009, 26(5): 7-13. |
马轩龙, 李文娟, 陈全功. 基于GIS与草原综合顺序分类法对甘肃省草地类型的划分初探. 草业科学, 2009, 26(5): 7-13. | |
5 | Su D X. The compilation and study of the grassland resource map of China on the scale of 1∶1000000. Journal of Natural Resources, 1996, 11(1): 75-83. |
苏大学. 1∶1000000中国草地资源图的编制与研究. 自然资源学报, 1996, 11(1): 75-83. | |
6 | Yue R W, Zhang N, Wang J J, et al. Spatiotemporal variation of grassland aboveground biomass in Inner Mongolia from 2000 to 2019. Journal of University of Chinese Academy of Sciences, 2022, 39(1): 21-33. |
乐荣武, 张娜, 王晶杰, 等. 2000-2019年内蒙古草地地上生物量的时空变化特征. 中国科学院大学学报, 2022, 39(1): 21-33. | |
7 | Xu B, Yang X C, Tao W G, et al. Remote sensing monitoring upon the grass production in China. Acta Ecologica Sinica, 2007, 27(2): 405-413. |
徐斌, 杨秀春, 陶伟国, 等. 中国草原产草量遥感监测. 生态学报, 2007, 27(2): 405-413. | |
8 | Sun M, Shen W S, Xie M, et al. The identification of grassland types in the source region of the Yarlung Zangbo River based on spectral features. Remote Sensing for Land & Resources, 2012, 24(1): 83-89. |
孙明, 沈渭寿, 谢敏, 等. 基于光谱特征的雅鲁藏布江源区草地类型识别. 国土资源遥感, 2012, 24(1): 83-89. | |
9 | Yang J L, Zhou Z F, Zhao Z L, et al. Research of the grassland types extraction by ALOS image in Karst mountainous area. Chinese Journal of Agricultural Resources and Regional Planning, 2013, 34(6): 81-85. |
杨尽利, 周忠发, 赵正隆, 等. 基于ALOS影像的喀斯特山区草地类型提取研究. 中国农业资源与区划, 2013, 34(6): 81-85. | |
10 | Guo F F, Fan J R, Tang X G, et al. Comparison of methods for grassland classification based on HJ-1A hyperspectral image data in North Tibet. Remote Sensing Information, 2013, 28(1): 77-82. |
郭芬芬, 范建容, 汤旭光, 等. 基于HJ-1A高光谱数据的藏北高原草地分类方法对比. 遥感信息, 2013, 28(1): 77-82. | |
11 | Qian Y R, Yu J, Jia Z H, et al. The classification strategy of desert grassland based on decision tree using remote sensing image. Journal of Northwest A & F University (Natural Science Edition), 2013, 41(2): 159-166. |
钱育蓉, 于炯, 贾振红, 等. 基于决策树的典型荒漠草地遥感分类策略. 西北农林科技大学学报(自然科学版), 2013, 41(2): 159-166. | |
12 | Navin M S, Agilandeeswari L. Multispectral and hyperspectral images based land use/land cover change prediction analysis: An extensive review. Multimedia Tools and Applications, 2020, 79(11): 1-24. |
13 | Meng B P, Yang Z G, Yu H Y, et al. Mapping of Kobresia pygmaea community based on unmanned aerial vehicle technology and Gaofen remote sensing data in alpine meadow grassland: A case study in eastern of Qinghai-Tibetan Plateau. Remote Sensing, 2021, 13(13): 2483. |
14 | Yang C, Wu G F, Li Q Q, et al. Research progress on remote sensing classification of vegetation. Geography and Geo-Information Science, 2018, 34(4): 24-32. |
杨超, 邬国锋, 李清泉, 等. 植被遥感分类方法研究进展. 地理与地理信息科学, 2018, 34(4): 24-32. | |
15 | You X B, Wang L. Application of auxiliary information to improve forest classification capability and forest division. Journal of Beijing Forestry University, 2003, 25(S1): 41-42. |
游晓斌, 王蕾. 应用辅助信息提高森林分类和森林区划能力的研究. 北京林业大学学报, 2003, 25(S1): 41-42. | |
16 | Elumnoh A, Shrestha R P. Application of DEM data to Landsat image classification: Evaluation in a tropical wet-dry landscape of Thailand. Photogrammetric Engineering & Remote Sensing, 2000, 66(3): 297-304. |
17 | Huo H T, Wang R H, You X X. Vegetation classification of TM imagery using ancillary data. Journal of Beijing Forestry University, 2001, 23(2): 28-31. |
霍宏涛, 王任华, 游先祥. 三维及相关辅助信息在提高图像分类精度中的研究. 北京林业大学学报, 2001, 23(2): 28-31. | |
18 | Li D F, Tian Y, Hao F H. NDVI data based study on complex classification of vegetation cover of Yellow River Basin. Research of Soil and Water Conservation, 2003, 10(4): 88-91. |
李道峰, 田英, 郝芳华. 基于NDVI数据的黄河流域地表植被覆盖综合分类研究. 水土保持研究, 2003, 10(4): 88-91. | |
19 | Zhen Y, Wu Z P, Yin Z H, et al. Study on spatio-temporal change of land use in Zoige County, Sichuan Province. Ecological Science, 2022, 41(2): 41-49. |
甄艳, 吴宗攀, 尹志恒, 等. 四川省若尔盖县土地利用时空变化研究. 生态科学, 2022, 41(2): 41-49. | |
20 | Xiao Y F, Chen W Y, Wang B J, et al. Study on temporal and spatial change of land use and its relationship with climate factors in Qilian Mountain National Nature Reserve. Acta Agrestia Sinica, 2021, 29(9): 2049-2057. |
肖云飞, 陈文业, 王斌杰, 等. 祁连山国家级自然保护区土地利用时空变化及与气候因子关系研究.草地学报, 2021, 29(9): 2049-2057. | |
21 | Zhang Y M, Zhao S D. Temporal and spatial change of land use in Horqin Desert and its outer area. Chinese Journal of Applied Ecology, 2004, 15(3): 429-435. |
张永民, 赵士洞. 科尔沁沙地及其周围地区土地利用的时空动态变化研究. 应用生态学报, 2004, 15(3): 429-435. | |
22 | Ge J, Meng B P, Yang S X, et al. Dynamic monitoring of alpine grassland coverage based on UAV technology and MODIS remote sensing data-A case study in the headwaters of the Yellow River. Acta Prataculturae Sinica, 2017, 26(3): 1-12. |
葛静, 孟宝平, 杨淑霞, 等. 基于UAV技术和MODIS遥感数据的高寒草地盖度动态变化监测研究——以黄河源东部地区为例. 草业学报, 2017, 26(3): 1-12. | |
23 | Li F X. Application and discussion of UAV technology in ecological remote sensing monitoring of grassland. Bulletin of Surveying and Mapping, 2017(7): 99-102. |
李风贤. 无人机技术在草原生态遥感监测中的应用与探讨. 测绘通报, 2017(7): 99-102. | |
24 | Yi S H, Chen J J, Qin Y, et al. The burying and grazing effects of plateau pika on alpine grassland are small: A pilot study in a semiarid basin on the Qinghai-Tibet Plateau. Biogeosciences, 2016, 13(22): 6273-6284. |
25 | Guo Q H, Wu F F, Hu T Y, et al. Perspectives and prospects of unmanned aerial vehicle in remote sensing monitoring of biodiversity. Biodiversity Science, 2016, 24(11): 1267-1278. |
郭庆华, 吴芳芳, 胡天宇, 等. 无人机在生物多样性遥感监测中的应用现状与展望. 生物多样性, 2016, 24(11): 1267-1278. | |
26 | Yang H, Zhou W, Huang L. Temporal and spatial patterns of grassland coverage and responses to hydrothermic factors in Inner Mongolia from 2001 to 2016. Pratacultural Science, 2019, 36(2): 359-367. |
杨晗, 周伟, 黄露. 2001-2016年内蒙古草地覆盖度时空格局及其对水热因子的响应. 草业科学, 2019, 36(2): 359-367. | |
27 | Hua Y C, Sa R L, Wang B. Spatial and temporal variation of grassland NPP and its driving forces in Inner Mongolia. Journal of Desert Research, 2021, 41(5): 130-139. |
滑永春, 萨如拉, 王冰. 内蒙古草原NPP时空变化及驱动力. 中国沙漠, 2021, 41(5): 130-139. | |
28 | Su L D, Yang J, Wan Z Q, et al. Climate change and its impacts on distribution pattern of grassland types in Inner Mongolia. Chinese Journal of Agrometeorology, 2015, 36(2): 139-148. |
苏力德, 杨劼, 万志强, 等. 内蒙古地区草地类型分布格局变化及气候原因分析. 中国农业气象, 2015, 36(2): 139-148. | |
29 | Gao H, Pan X B, Fu Y. Influence of climate change on potential climate productivity in grassland of central Inner Mongolia. Chinese Journal of Agrometeorology, 2009, 30(3): 277-282. |
高浩, 潘学标, 符瑜. 气候变化对内蒙古中部草原气候生产潜力的影响. 中国农业气象, 2009, 30(3): 277-282. | |
30 | Liu H, Guo W L, Quan W J. Climatic division of the types and yields of grassland in Inner Mongolia. Journal of Applied Meteorological Science, 2011, 22(3): 329-335. |
刘洪, 郭文利, 权维俊. 内蒙古草地类型与生物量气候区划. 应用气象学报, 2011, 22(3): 329-335. | |
31 | Yi S H. FragMAP: A tool for long-term and cooperative monitoring and analysis of small-scale habitat fragmentation using an unmanned aerial vehicle. International Journal of Remote Sensing, 2017, 38(10): 2686-2697. |
32 | Gong J M. Spatial distribution of grassland classes in Dalhanmaomingan Union Banner. Inner Mongolia Prataculture, 2011, 23(3): 53-56. |
贡吉玛. 达尔罕茂明安联合旗草原类型空间分布的特征. 内蒙古草业, 2011, 23(3): 53-56. | |
33 | Wang C L, Sa R, Tu L G E, et al. Remote sensing investigation and analysis of grassland resources in Wuhai City. Inner Mongolia Prataculture, 2009, 21(3): 18-24. |
王春兰, 萨仁, 图力古尔, 等. 乌海市草地资源遥感调查分析. 内蒙古草业, 2009, 21(3): 18-24. | |
34 | Zhang Y P, Man L, Jin S, et al. Types of Xilinguole grassland——Based on the Honggeergaole ecological experimental area. Journal of Beijing Institute of Education (Natural Science Edition), 2010, 5(3): 4-9. |
张玉平, 满良, 金山, 等. 锡林郭勒草原草地类型研究——以洪格尔高勒生态建设试验区为例. 北京教育学院学报(自然科学版), 2010, 5(3): 4-9. | |
35 | Meng B P. Estimation grassland above ground biomass based on UAV technology and machine learning methods in alpine grassland, Gannan Region. Lanzhou: Lanzhou University, 2018. |
孟宝平. 基于UAV和机器学习方法的甘南地区高寒草地地上生物量遥感估测研究. 兰州: 兰州大学, 2018. | |
36 | Du J X, Sun Y, Xiang B, et al. Potential distribution of plateau pika and its influence factors in the source region of the Yellow River Basin using BIOMOD. Pratacultural Science, 2019, 36(4): 1074-1083. |
杜嘉星, 孙义, 向波, 等. 基于BIOMOD的黄河源区高原鼠兔潜在分布及其影响因子. 草业科学, 2019, 36(4): 1074-1083. | |
37 | Breiman L. Random forests. Machine Learning, 2001, 45(1): 5-32. |
38 | Wang D J, Jiang Q G, Li Y H, et al. Land use classification of farming areas based on time series Sentinel-2A/B data and random forest algorithm. Remote Sensing for Land & Resources, 2020, 32(4): 236-243. |
王德军, 姜琦刚, 李远华, 等. 基于Sentinel-2A/B时序数据与随机森林算法的农耕区土地利用分类. 国土资源遥感, 2020, 32(4): 236-243. | |
39 | Yang C K, Wang C C, Zhang D K, et al. Classification of GF-1 satellite image based on SVM. Geomatics & Spatial Information Technology, 2015, 38(9): 142-146. |
杨长坤, 王崇倡, 张鼎凯, 等. 基于SVM的高分一号卫星影像分类. 测绘与空间地理信息, 2015, 38(9): 142-146. | |
40 | Du P J, Xia J S, Xue Z H, et al. Review of hyperspectral remote sensing image classification. Journal of Remote Sensing, 2016, 20(2): 236-256. |
杜培军, 夏俊士, 薛朝辉, 等. 高光谱遥感影像分类研究进展. 遥感学报, 2016, 20(2): 236-256. | |
41 | Luo J C, Zhou C H, Yang Y. ANN remote sensing classification model and its integration approach with geo-knowledge. Journal of Remote Sensing, 2001, 5(2): 122-129. |
骆剑承, 周成虎, 杨艳. 人工神经网络遥感影像分类模型及其与知识集成方法研究. 遥感学报, 2001, 5(2): 122-129. | |
42 | Xiu L N, Liu X N. Current status and future direction of the study on artificial neural network classification processing in remote sensing. Remote Sensing Technology and Application, 2003, 18(5): 339-345. |
修丽娜, 刘湘南. 人工神经网络遥感分类方法研究现状及发展趋势探析. 遥感技术与应用, 2003, 18(5): 339-345. | |
43 | Qiao W F, Sheng Y H, Fang B, et al. Land use change information mining in highly urbanized area based on transfer matrix: A case study of Suzhou, Jiangsu Province. Geographical Research, 2013, 32(8): 1497-1507. |
乔伟峰, 盛业华, 方斌, 等. 基于转移矩阵的高度城市化区域土地利用演变信息挖掘——以江苏省苏州市为例. 地理研究, 2013, 32(8): 1497-1507. | |
44 | Su Y J, Guo Q H, Hu T Y, et al. An updated vegetation map of China (1∶1000000). Science Bulletin, 2020, 65(13): 1125-1136. |
苏艳军, 郭庆华, 胡天宇, 等. 中国植被图(1∶1000000)现实性更新. 科学通报, 2020, 65(13): 1125-1136. | |
45 | Wang Z X, Liu C, Zhao B R. Potentials and limitation of AVHRR for grassland classification in Xilingol, Inner Mongolia. Journal of Natural Resources, 2003, 18(6): 704-711. |
王正兴, 刘闯, 赵冰茹. AVHRR草地分类的潜力和局限: 以锡林郭勒草原为例. 自然资源学报, 2003, 18(6): 704-711. | |
46 | Zhao B R, Liu C, Liu A J, et al. Estimate the yield of grassland using MODIS-NDVI——A case study of the grassland in Xilinguole in Inner Mongolia. Pratacultural Science, 2004, 21(8): 12-15. |
赵冰茹, 刘闯, 刘爱军, 等. 利用MODIS-NDVI进行草地估产研究——以内蒙古锡林郭勒草地为例. 草业科学, 2004, 21(8): 12-15. | |
47 | Guo Q H, Guan H C, Hu T Y, et al. Remote sensing-based mapping for the new generation of Vegetation Map of China (1∶500,000). Scientia Sinica Vitae, 2021, 51(3): 229-241. |
郭庆华, 关宏灿, 胡天宇, 等. 新一代1∶50万中国植被图绘制方法探讨. 中国科学: 生命科学, 2021, 51(3): 229-241. | |
48 | Zhang J G, Liu D W, Meng B P, et al. Using UAVs to assess the relationship between alpine meadow bare patches and disturbance by pikas in the source region of Yellow River on the Qinghai-Tibetan Plateau. Global Ecology and Conservation, 2021, 26(6): e01517. |
49 | Meng B P, Gao J L, Liang T G, et al. Modeling of alpine grassland cover based on unmanned aerial vehicle technology and multi-factor methods: A case study in the east of Tibetan Plateau, China. Remote Sensing, 2018, 10(2): 320. |
50 | Wen Q K, Zhang Z X, Liu S, et al. Classification of grassland types by MODIS time-series images in Tibet, China. IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing, 2010, 3(3): 404-409. |
[1] | 张慧龙, 杨秀春, 杨东, 陈昂, 张敏. 2000-2020年内蒙古草地植被覆盖度时空变化及趋势预测[J]. 草业学报, 2023, 32(8): 1-13. |
[2] | 李芳, 王广军, 杜海波, 李萌, 梁四海, 彭红明. 融合MODIS和Landsat数据的青海湖流域典型区NDVI重构与年内最大值变化分析[J]. 草业学报, 2023, 32(8): 28-39. |
[3] | 邢虎成, 王贤芳, 周清, 闫景彩, 揭雨成. 湖南52县草地资源的类型、等级及利用现状分析[J]. 草业学报, 2023, 32(8): 91-103. |
[4] | 郭芮, 伏帅, 侯蒙京, 刘洁, 苗春丽, 孟新月, 冯琦胜, 贺金生, 钱大文, 梁天刚. 基于Sentinel-2数据的青海门源县天然草地生物量遥感反演研究[J]. 草业学报, 2023, 32(4): 15-29. |
[5] | 修炀景, 侯蒙京, 田骄阳, 梁天刚, 冯琦胜. 基于土地利用/覆盖的甘肃省景观生态风险时空变化特征[J]. 草业学报, 2023, 32(1): 1-15. |
[6] | 厉方桢, 钟华平, 欧阳克蕙, 赵小敏, 李愈哲. 基于机器学习的阿勒泰地区草地地下生物量估测与数字制图[J]. 草业学报, 2022, 31(8): 13-23. |
[7] | 秦格霞, 吴静, 李纯斌, 吉珍霞, 邱政超, 李颖. 基于机器学习算法的天祝藏族自治县草地地上生物量反演[J]. 草业学报, 2022, 31(4): 177-188. |
[8] | 李颖, 吴静, 李纯斌, 秦格霞. 2003-2018年青藏高原草地的地表层土壤热通量时空变化[J]. 草业学报, 2022, 31(11): 1-14. |
[9] | 金哲人, 冯琦胜, 王瑞泾, 梁天刚. 基于MODIS数据与机器学习的青藏高原草地地上生物量研究[J]. 草业学报, 2022, 31(10): 1-17. |
[10] | 张仁平, 郭靖, 马晓芳, 郭伟勇. 基于MODIS数据的新疆草地物候提取方法及变化趋势分析[J]. 草业学报, 2022, 31(1): 1-12. |
[11] | 付刚, 王俊皓, 李少伟, 何萍. 藏北高寒草地牧草营养品质对放牧的响应机制[J]. 草业学报, 2021, 30(9): 38-50. |
[12] | 赵文, 尹亚丽, 李世雄, 刘燕, 刘晶晶, 董怡玲, 苏世锋, 吉凌鹤. 祁连山不同类型草地土壤细菌群落特征研究[J]. 草业学报, 2021, 30(12): 161-171. |
[13] | 崔博超, 郑江华, 吐尔逊·哈斯木, 段素素, 杜梦洁. 塔里木河流域草地净初级生产力时空分异特征研究[J]. 草业学报, 2020, 29(6): 1-13. |
[14] | 普雪可, 吴春花, 周永瑾, 勉有明, 苗芳芳, 侯贤清, 李荣. 宁南旱区地膜秸秆沟垄双覆盖对土壤水分时空变化及马铃薯产量的影响[J]. 草业学报, 2020, 29(10): 149-160. |
[15] | 张仁平, 郭靖, 冯琦胜, 梁天刚. 新疆地区草地植被物候时空变化[J]. 草业学报, 2018, 27(10): 66-75. |
阅读次数 | ||||||
全文 |
|
|||||
摘要 |
|
|||||