Please wait a minute...
img

官方微信

遥感技术与应用  2021, Vol. 36 Issue (6): 1259-1271    DOI: 10.11873/j.issn.1004-0323.2021.6.1259
LiDAR专栏     
基于机载LiDAR数据和Landsat 8影像的芬兰北部泰加林—苔原过渡带提取
常潇月1(),荆林海2,林沂1()
1.北京大学 遥感与地理信息系统研究所,北京 100871
2.中国科学院空天信息创新研究院 数字地球重点实验室,北京 100094
Extraction of the Taiga-tundra Ecotone in Northern Finland based on Airborne LiDAR Data and Landsat 8 Images
Xiaoyue Chang1(),Linhai Jing2,Yi Lin1()
1.Institute of Remote Sensing and Geographic Information Science,Peking University,Beijing 100871,China
2.Aerospace Information Research Institute,Key Laboratory of Digital Earth,Chinese Academy of Sciences,Beijing 100094,China
 全文: PDF(6631 KB)   HTML
摘要:

泰加林—苔原过渡带对气候变化敏感,确定其位置可以帮助理解北极地区气候变化。针对当前过渡带提取中存在的自动化程度低、提取困难的问题,以芬兰北部泰加林—苔原过渡带为研究区,以高分辨率航空遥感影像和冠层高度模型生成的过渡带参考数据为基准数据,构建基Landsat影像和LiDAR数据的4个随机森林过渡带分类模型。对模型分类结果去除“椒盐”图斑,使用连通区域边界点提取算法提取过渡带边界的位置坐标,实现过渡带边界提取,并检验过渡带边界的位置精度。其中,RF_Spring_Las模型和RF_Summer_Las模型的Kappa系数分别为0.92、0.98,分类总体精度分别为94.66%、94.44%,分类精度远高于RF_Spring模型和RF_Summer模型。基于RF_Spring_Las模型和RF_Summer_Las模型的过渡带边界提取结果具有较高位置精度,过渡带下边界位置误差分别为25.13 m、25.11 m,过渡带上边界位置误差分别为43.11 m、44.80 m,实现春季和夏季两个季节的芬兰北部泰加林—苔原过渡带提取,为后续过渡带位置监测提供基准数据。

关键词: 泰加林-苔原过渡带机载LiDAR数据Landsat 8影像随机森林    
Abstract:

The taiga-tundra ecotone is sensitive to climate change, and location determination helps to understand climate change in the Arctic region. At present, most of the ecotone extraction methods are manual and semi-automatic, and it is difficult to distinguish forest, ecotone and tundra from moderate resolution satellite data, which have similar spectra. The taiga-tundra ecotone reference data was generated using high-resolution aerial images and Canopy Height Model (CHM). After that, four Random Forest (RF) classification models based on Landsat images and LiDAR data were constructed, named RF_Spring, RF_Summer, RF_Spring_Las and RF_Summer_Las. The salt-and-pepper patches were removed from classification results, and the ecotone boundaries were extracted using the connected region boundary point extraction algorithm in MATLAB. In addition, the position accuracies of ecotone boundaries were tested. The Kappa coefficients of RF_Spring_Las model and RF_Summer_Las model are 0.92 and 0.98 respectively, and the overall accuracies are 0.95 and 0.94 respectively. The classification accuracies of the two models are much higher than those of RF_Spring model and RF_Summer model. Based on the classification results of RF_Spring_Las model and RF_Summer_Las model, the extraction results of ecotone boundaries have high precision. The position errors of the lower boundaries of ecotones are 25.13 m and 25.11 m respectively, and the position errors of the upper boundaries of ecotones are 43.11 m and 44.80 m respectively. Thus, the taiga-tundra ecotone in northern Finland can be extracted from spring and summer Landsat8 images and Airborne LiDAR data, which can help long-term monitoring of the taiga-tundra ecotone.

Key words: Taiga-tundra ecotone    Aerial LiDAR data    Landsat8 image    Random forest
收稿日期: 2020-11-25 出版日期: 2022-01-26
ZTFLH:  TP79  
基金资助: 国家自然科学基金项目“激光扫描与涡度测量:三维森林生态系统碳水过程模式”(31870531);中国科学院数字地球重点实验室开放基金项目“环北极泰加林-苔原过渡带的激光雷达与高分卫星遥感观测”(2017LDE007)
通讯作者: 林沂     E-mail: 1801210261@pku.edu.cn;yi.lin@pku.edu.cn
作者简介: 常潇月(1996-),女,山东莱阳人,硕士研究生,主要从事激光雷达遥感研究。E?mail: 1801210261@pku.edu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
常潇月
荆林海
林沂

引用本文:

常潇月,荆林海,林沂. 基于机载LiDAR数据和Landsat 8影像的芬兰北部泰加林—苔原过渡带提取[J]. 遥感技术与应用, 2021, 36(6): 1259-1271.

Xiaoyue Chang,Linhai Jing,Yi Lin. Extraction of the Taiga-tundra Ecotone in Northern Finland based on Airborne LiDAR Data and Landsat 8 Images. Remote Sensing Technology and Application, 2021, 36(6): 1259-1271.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2021.6.1259        http://www.rsta.ac.cn/CN/Y2021/V36/I6/1259

图1  研究区位置及数据分布图
图2  图像梯度法示意图
序号参数描述序号参数描述
原始反射率15EVI增强型植被指数
1B1Band 1反射率11GNDVI绿色归一化植被指数
2B2Band 2反射率12OSAVI土壤调节植被指数
3B3Band 3反射率13TVI三角植被指数
4B4Band 4反射率纹理参数
5B5Band 5反射率16texture_mean均值
6B6Band 6反射率17texture_variance标准差
7B7Band 7反射率18texture_contrast对比度
植被指数19texture_correlation相关性
8DVI差值植被指数20texture_dissimilarity相异性
9RVI比值植被指数21texture_entropy信息熵
10NDVI归一化植被指数22texture_homogeneity协同性
14ARVI大气阻抗植被指数23texture_secondmonent二阶矩
表1  Landsat 8影像参数
序号名称描述
高度参数1var方差
2stdv标准差
3skew偏度
4med中值
5mean均值
6max最大值
7kurt峰度
8iqr四分位间距,75th高度百分位数和25th高度百分位数之差
9cv变异系数,所有点高度的变异系数
10-18prctile_90、prctile_80……prctile_10高度百分位数,点云由低到高排列,高度前90%、80%……10%的点所在的高度
水平差异参数19CHM_slope冠层高度模型的坡度
20texture_mean_las冠层高度模型的纹理均值
21texture_variance_las冠层高度模型的纹理标准差
22texture_contrast_las冠层高度模型的纹理对比度
23texture_correlation_las冠层高度模型的纹理相关性
24texture_dissimilarity_las冠层高度模型的纹理相异性
25texture_entropy_las冠层高度模型的纹理信息熵
26texture_homogeneity_las冠层高度模型的纹理协同性
27texture_secondmonent_las冠层高度模型的纹理二阶矩
表2  LiDAR统计参数
图3  技术流程图
图4  树木提取结果及过渡带参考边界
参考数据(像素)

总体精度

/%

区域类别非树

分类数据

(像素)

研究区A2722890.83
非树27273
研究区B2633792.67
非树7293
研究区C2703092.00
非树18282
研究区D2742693.33
非树14286
研究区E2703092.33
非树16284
研究区F2663493.33
非树6294
验证区G2821894.67
非树14286
验证区H2604092.67
非树4296
表3  树木分类结果精度检验
研究区位置误差(单位:m)
均值标准差最小值最大值
森林线A2.362.640.0014.50
B2.652.110.008.00
C2.912.420.0010.00
D2.733.020.0014.50
E2.882.780.0012.00
F3.062.660.009.00
树线A2.051.540.007.00
B2.662.510.0012.50
C2.772.190.0010.50
D3.352.810.0010.50
E3.042.340.007.00
F2.822.160.006.50
表4  参考森林线和树线位置精度
模型决策树个数输入参数个数n

每个节点处

随机抽取的

变量个数m

Kappa

系数

总体

精度

OA

RF_Spring100730.7784.87%
RF_Summer10014100.6878.93%
RF_Spring_Las8022190.9294.66%
RF_Summer_Las1001870.9894.44%
表5  随机森林分类模型参数及分类精度
序号参数重要性序号参数重要性
1B6_spring3.155GNDVI_spring2.11
2B1_spring2.366texture_mean_spring1.76
3EVI_spring2.297ARVI_spring1.75
4B7_spring2.27
表6  RF_Spring模型输入参数
序号参数重要性序号参数重要性
1B4_summer2.388NDVI_summer1.44
2ARVI_summer1.889texture_mean_summer1.38
3B7_summer1.7110DVI_summer1.29
4TVI_summer1.6811B6_summer1.24
5B5_summer1.5612B1_summer1.17
6RVI_summer1.5413B2_summer1.13
7B3_summer1.4714GNDVI_summer1.03
表7  RF_Summer模型输入参数
序号参数重要性序号参数重要性
1texture_mean_las1.6612texture_dissimilarity_las0.87
2B6_spring1.1213texture_variance_spring0.86
3h_var1.1114texture_variance_las0.85
4texture_contrast_las1.0715DVI_spring0.82
5h_stdv0.9916prctile_800.81
6h_med0.9617prctile_900.80
7prctile_600.9618B1_spring0.80
8prctile_700.9219h_max0.80
9h_mean0.9120texture_homogeneity_las0.78
10h_iqr0.8921texture_entropy_las0.77
11B7_spring0.8722h_kurt0.74
表8  RF_Spring_Las模型输入参数
序号参数重要性序号参数重要性
1texture_mean_las2.2410h_skew0.86
2h_med1.1911B4_summer0.85
3prctile_601.0912prctile_900.84
4h_stdv1.0813texture_homogeneity_las0.82
5h_kurt0.9714B7_summer0.79
6h_var0.9515NDVI_summer0.79
7h_mean0.9216RVI_summer0.79
8h_max0.9117TVI_summer0.79
9GNDVI_summer0.8818DVI_summer0.76
表9  RF_Summer_Las模型输入参数
图5  研究区A随机森林分类结果及过渡带边界
图6  芬兰北部泰加林-苔原过渡带分布图
模型区域森林线位置误差/m树线位置误差/m
均值标准差位置误差均值均值标准差位置误差均值
RF_SpringA27.3344.6324.9574.19123.0885.46
B17.6122.3488.07192.20
C14.4415.7682.41150.35
D19.7930.2957.7078.32
E26.5340.6964.1691.86
F18.7920.9345.8179.48
G30.1065.05119.60168.19
H45.0157.99151.74160.22
RF_SummerA52.81101.4275.05113.89172.25133.90
B54.5386.29128.63297.55
C87.80156.3492.55116.85
D100.18322.29263.18565.35
E100.37192.4472.18113.35
F45.4277.5957.2680.85
G80.00145.19150.19247.91
H79.30169.84193.32243.90
RF_Spring_LasA18.4128.4925.1346.0489.2543.11
B22.7127.4434.6184.78
C23.1329.8751.5789.27
D22.1829.4426.1745.13
E23.3240.3022.6753.40
F15.9029.9317.2333.02
G20.3426.7576.56149.09
H55.0562.4769.99103.84
RF_Summer_LasA18.0628.1325.1147.1090.9844.80
B23.6833.1433.3879.84
C20.7325.7547.7278.12
D25.9533.6127.4045.76
E27.7555.7629.2666.42
F15.5329.8917.4834.18
G20.2832.2174.03149.53
H48.9255.0782.05115.13
表10  基于随机森林分类结果的森林线和树线位置误差
1 Callaghan T V, Werkman B R, Crawford R M M. The Tundra-Taiga interface and its dynamics: concepts and applications[J]. Ambio, 2002,12:6-14.
2 Hansen J, Sato M, Ruedy R, et al. Global temperature change[J]. Proceedings of the National Academy of Sciences of the United States of America,2006,103(39):14288-14293.
3 ACIA. Impacts of a warming Arctic: Arctic climate impact assessment[M]. Cambridge:Cambridge University Press,2004.
4 Walther G R. Plants in a warmer world[J]. Perspectives in Plant Ecology Evolution and Systematics,2004,6(3):169-185.
5 Tape K, Sturm M, Racine C. The evidence for shrub expansion in Northern Alaska and the Pan-Arctic[J]. Global Change Biology,2006, 12(4): 686-702.
6 Walker M D, Wahren C H, Hollister R D, et al. Plant community responses to experimental warming across the Tundra Biome[J]. Proceedings of the National Academy of Sciences of the United States of America,2006, 103(5): 1342-1346.
7 Bonan G B, Chapin F S, Thompson S L. Boreal forest and Tundra ecosystems as components of the climate system[J]. Climatic Change, 1995, 29(2): 145-167.
8 Hill R A, Granica K, Smith G M, et al. Representation of an Alpine Treeline dcotone in SPOT 5 Hrg data[J]. Remote Sen-sing of Environment, 2007, 110(4): 458-467.
9 Kharuk V I, Im S T, Dvinskaya M L. Forest-Tundra ecotone response to climate change in the Western Sayan Mountains, Siberia[J]. Scandinavian Journal of Forest Research, 2010, 25(3): 224-233.
10 Ranson K J, Sun G, Kharuk V I, et al. Assessing Tundra-Taiga boundary with multi-sensor satellite data[J]. Remote Sensing of Environment, 2004, 93(3): 283-295.
11 Rees G, Brown I, Mikkola K, et al. How can the dynamics of the Tundra-Taiga boundary be femotely monitored?[J]. Ambio, 2002,12: 56-62.
12 Stueve K M, Cerney D L, Rochefort R M, et al. Post-Fire tree establishment patterns at the Alpine Treeline Ecotone: mount Rainier National Park, Washington, USA[J]. Journal of Vegetation Science, 2009, 20(1): 107-120.
13 Rees W G. Characterisation of Arctic Treelines by Lidar and multispectral imagery[J]. Polar Record,2007,43(227):345-352.
14 Naesset E, Nelson R. Using airborne laser scanning to monitor tree migration in the Boreal-Alpine transition zone[J]. Remote Sensing of Environment, 2007, 110(3): 357-369.
15 Kimball K D, Weihrauch D M. Alpine vegetation communities and the Alpine-Treeline ecotone boundary in New England as biomonitors for climate change[C]∥ Wilderness Science in a Time of Change Conference, Missoula, 2000.
16 Alberto Diaz-Varela R, Colombo R, Meroni M, et al. Spatio-temporal analysis of Alpine Ecotones: a spatial explicit model targeting altitudinal vegetation shifts[J]. Ecological Modelling, 2010, 221(4): 621-633.
17 Hofgaard A, Tommervik H, Rees G, et al. Latitudinal forest advance in Northernmost Norway since the early 20th century[J]. Journal of Biogeography, 2013, 40(5): 938-949.
18 Ranson K J, Montesano P M, Nelson R. Object-based mapping of the circumpolar Taiga-Tundra ecotone with MODIS tree cover[J].Remote Sensing of Environment,2011,115(12): 3670-3680.
19 Walther C, Huettich C, Urban M, et al. Modelling the Arctic Taiga-Tundra ecotone using Alos Palsar and optical earth observation data[J]. International Journal of Applied Earth Observation and Geoinformation, 2019, 81: 195-206.
20 Winings C J. Mapping alpine treeline with high resolution imagery and Lidar data in North Cascades National Park, Washington[D]. Washington: Wertern Washington University, 2013.
21 Rusu R B, Marton Z C, Blodow N, et al. Towards 3d point cloud based object maps for household environments[J]. Robotics and Autonomous Systems, 2008, 56(11): 927-941.
22 Parkan M. Digital forestry toolbox for Matlab/Octave.[EB/OL]. 2018. DOI: 10.5281/zenodo.1213013. http:
doi: 10.5281/zenodo.1213013. http:
23 Payette S. The forest tundra and present treelines of the Northern Quebec-Labrador Peninsula[J].Nordicana,1983,47:3-23.
24 Camarero J J, Gutierrez E. Pace and pattern of recent treeline dynamics: response of ecotones to climatic variability in the Spanish Pyrenees[J]. Climatic Change,2004,63(1-2):181-200.
25 Kullman L. Pine (Pinus Sylvestris) tree-limit surveillance during recent decades, central Sweden[J]. Arctic and Alpine Research, 1993, 25(1): 24-31.
26 Cho M A, Mathieu R, Asner G P, et al. Mapping tree species composition in South African Savannas using an integrated airborne spectral and Lidar system[J]. Remote Sensing of Environment, 2012, 125: 214-226.
27 Malahlela O, Cho M A, Mutanga O. Mapping canopy gaps in an indigenous subtropical coastal forest using high-resolution Worldview-2 data[J]. International Journal of Remote Sensing, 2014, 35(17): 6397-6417.
28 Mao Xuegang, Yao Yao, Chen Shuxin, et al. Forest stand identification based on ecognition software using Quickbird remote sensing image: a case of jiangle forest farm in Fujian province[J]. Journal of Nanjing Forestry University Natural Sciences Edition, 2019, 43(1): 127-134.
28 毛学刚, 姚瑶, 陈树新, 等. 基于易康软件的QuickBird遥感影像林分类型识别——以福建省将乐林场为例[J], 南京林业大学学报(自然科学版), 2019, 43(1): 127-134.
29 MathWorks.Inc. Matlab Help Center[EB/OL]. 2020.
30 Wulder M A, Han T, White J C, et al. An approach for edge matching large-area satellite image classifications[J]. Canadian Journal of Remote Sensing, 2007, 33(4): 266-277.
31 Ma Huijiuan, Gao Xiaohong, Gu Xiaotian. Random forest classification of Landsat 8 imagery for the complex terrain area based on the combination of spectral, topographic and texture information[J]. Journal of Geo-Information Science, 2019, 21(3): 359-371.
31 马慧娟, 高小红, 谷晓天. 随机森林方法支持的复杂地形区土地利用/土地覆被分类研究[J], 地球信息科学学报, 2019, 21(3): 359-371.
32 Phiri D, Morgenroth J, Xu C, et al. Effects of pre-processing methods on Landsat Oli-8 land cover classification using obia and random forests classifier[J]. International Journal of Applied Earth Observation and Geoinformation,2018,73: 170-178.
33 Zhang Xiaoyu, Li Fengri, Zhen Zheng, et al. Forest vegetation classification of Landsat 8 remote sensing image based on random forests model[J]. Journal of North-East Forestry University, 2016, 44(6): 53-57,74.
33 张晓羽, 李凤日, 甄贞, 等. 基于随机森林模型的陆地卫星-8遥感影像森林植被分类[J], 东北林业大学学报, 2016, 44(6): 53-57,74.
34 Goodwin N R, Coops N C, Culvenor D S. Assessment of forest structure with airborne Lidar and the effects of platform altitude[J]. Remote Sensing of Environment,2006,103(2): 140-152.
35 Lu Lin, Zhou Xiaocheng, Yu Zhizhong, et al. Plot-level forest height inversion using airborne Lidar data based on the random forest[J]. Journal of Geo-Information Science, 2016, 18(8): 1133-1140.
35 鲁林, 周小成, 余治忠, 等. 随机森林算法在机载LiDAR数据林分平均树高估算中的应用研究[J], 地球信息科学学报, 2016, 18(8): 1133-1140.
36 Wallace L, Musk R, Lucieer A. An assessment of the repeatability of automatic forest inventory metrics derived from Uav-Borne Laser scanning data[J]. IEEE Transactions on Geoscience and Remote Sensing,2014, 52(11): 7160-7169.
37 Breiman L. Random Forests[J]. Machine Learning,2001, 45(1): 5-32.
38 Ren Chong, Ju Hongbo, Zhang Huaiqing, et al. Research on remote sensing Mmnitoring technology of forest land dynamic change in Tianshui in recent 30 years[J]. Forest Research. 2017, 30(1): 25-33.任冲, 鞠洪波, 张怀清, 等. 天水市近30年林地动态变化遥感监测研究[J]. 林业科学研究, 2017, 30(1): 25-33.
39 Belgiu M, Dragut L. Random forest in remote sensing: a review of applications and future directions[J]. ISPRS Jour-nal of Photogrammetry and Remote Sensing, 2016, 114: 24-31.
40 Liu Yi, Du Peijun, Zheng Hui, et al. Classification of China small satellite remote sensing image based on random forests[J]. Science of Surveying and Mapping, 2012, 37(4): 194-196.
40 刘毅, 杜培军, 郑辉, 等. 基于随机森林的国产小卫星遥感影像分类研究[J], 测绘科学, 2012, 37(4): 194-196.
41 Rodriguez-Galiano V F, Ghimire B, Rogan J, et al. An assessment of the effectiveness of a random forest classifier for land-cover classification[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2012, 67: 93-104.
[1] 魏雪馨,刘洋,闵庆文,刘荣高,张清洋,叶晓星,刘蓓蓓. 基于地物光谱季节曲线特征的毛竹林分布提取[J]. 遥感技术与应用, 2021, 36(5): 1178-1188.
[2] 姚杰鹏,杨磊库,陈探,宋春桥. 基于Sentinel-1,2和Landsat 8时序影像的鄱阳湖湿地连续变化监测研究[J]. 遥感技术与应用, 2021, 36(4): 760-776.
[3] 李晓彤,覃先林,刘倩,赵俊鹏,王崇阳. 基于AISA Eagle Ⅱ机载高光谱数据的森林可燃物类型识别方法[J]. 遥感技术与应用, 2021, 36(3): 544-551.
[4] 盛夏,石玉立,丁海勇. 青藏高原GPM降水数据空间降尺度研究[J]. 遥感技术与应用, 2021, 36(3): 571-580.
[5] 陈彦四,黄春林,侯金亮,韩伟孝,冯娅娅,李翔华,王静. 基于多时相Sentinel-2影像的黑河中游玉米种植面积提取研究[J]. 遥感技术与应用, 2021, 36(2): 324-331.
[6] 杨福芹,冯海宽,李振海,潘洁晨,谢瑞. 苹果叶片氮含量高光谱反演方法对比[J]. 遥感技术与应用, 2021, 36(2): 353-361.
[7] 尹燕旻,贾立. 基于Sentinel-2的闪电河流域农作物分类研究[J]. 遥感技术与应用, 2021, 36(2): 400-410.
[8] 王崇阳,田昕. 基于GF⁃1 PMS数据的森林覆盖变化检测[J]. 遥感技术与应用, 2021, 36(1): 208-216.
[9] 付甜梦,张丽,陈博伟,闫敏. 基于GEE平台的海岛地表覆盖提取及变化监测—以苏拉威西岛为例[J]. 遥感技术与应用, 2021, 36(1): 55-64.
[10] 马腾耀,肖鹏峰,张学良,马威,郭金金. 基于特征优选的GF-3全极化数据积雪识别[J]. 遥感技术与应用, 2020, 35(6): 1292-1302.
[11] 王一帆,徐涵秋. 基于客观阈值与随机森林Gini指标的水体遥感指数对比[J]. 遥感技术与应用, 2020, 35(5): 1089-1098.
[12] 张坤,刘乃文,高帅,赵书慧. 数据驱动的植被总初级生产力估算方法研究[J]. 遥感技术与应用, 2020, 35(4): 943-949.
[13] 李萌,年雁云,边瑞,白艳萍,马金辉. 基于多源遥感影像的青海云杉和祁连圆柏分类[J]. 遥感技术与应用, 2020, 35(4): 855-863.
[14] 董超,赵庚星. 时序数据集构建质量对土地覆盖分类精度的影响研究[J]. 遥感技术与应用, 2020, 35(3): 558-566.
[15] 李净,温松楠. 基于3种机器学习法的太阳辐射模拟研究[J]. 遥感技术与应用, 2020, 35(3): 615-622.