基于时序遥感的庐山自然保护区植被分类及其变化分析

doi:10.18306/dlkxjz.2021.04.014

Abstract

Abstract:

Nature reserves are the areas with the most abundant biodiversity. Conducting a survey of current forest biodiversity in Lushan Nature Reserve and understanding the distribution and changes of vegetation in the protected area is of great significance for the protection of forest resources in Lushan. In this study, we used the Proba-V satellite 100-meter resolution 5-day vegetation index product from 2015 to 2018 using the maximum synthesis and Hants time series harmonic analysis methods to smooth the data and reduce noise, and used a random forest algorithm to classify the forest vegetation. The changes of Lushan vegetation communities were also analyzed. The research results show that: 1) The overall accuracies of the random forest classification of Lushan forestland from 2015 to 2018 were 85%, 84.25%, 84.75%, and 85.25% while Kappa coefficients were 0.80, 0.79, 0.81, and 0.80, respectively. Compared with the Cover-CCI-2010, Globcover-2009, Globeland30, and MODIS-2010 land cover products, the classification results by random forest classifier based on time series NDVI products have achieved good classification effect and high classification accuracy in spatial resolution and mapping accuracy. 2) In Lushan Nature Reserve, coniferous forest and broad-leaved forest are concentrated while mixed forest and bamboo forest are scattered among them. Coniferous forest has the largest distribution area, accounting for 39.36% of the total forest area, and the bamboo forest has the smallest distribution area, accounting for 14.63%. 3) From 2015 to 2018, the spatial distribution of forest vegetation communities in Lushan did not change much. The change rates of broad-leaved forest, coniferous forest, and mixed forest were all less than 10%. Bamboo forest fluctuated during 2015-2018 because of the interference of human activities while the change of broad-leaved forest was the smallest.

Key words: Proba-V, random forest, forest vegetation mapping and classification, spatial and temporal distribution, Lushan

ZHANG Li, LI Bin, YANG Wenjing, LI Qiong. Forest vegetation classification and its variation in Lushan Nature Reserve using Proba-V vegetation products[J].PROGRESS IN GEOGRAPHY, 2021, 40(4): 703-712.

Figures/Tables 8

Fig.1

Fig.2

Fig.3

Tab.1

Fig.4

Tab.2

Fig.5

Tab.3

References 29

[1]	尤慧. 近十年东南亚森林扰动的遥感分析[D]. 南京: 南京信息工程大学, 2013.
	You Hui. Remote sensing analysis of forest disturbance in Southeast Asia for recent decades. Nanjing, China: Nanjing University of Information Science & Technology, 2013.
[2]	Myers N, Mittermeier R A, Mittermeier C G, et al. Biodiversity hotspots for conservation priorities[J]. Nature, 2000, 403:853-858. doi: 10.1038/35002501 pmid: 10706275
[3]	胡美娟, 侯国林, 周年兴, 等. 庐山森林景观空间分布格局及多尺度特征[J]. 生态学报, 2015, 35(16):5294-5305.
	Hu Meijuan, Hou Guolin, Zhou Nianxing, et al. Spatial distribution patterns and multi-scale features of the Lushan forest landscape. Acta Ecologica Sinica, 2015, 35(16):5294-5305.
[4]	付伟, 徐涵秋, 王美雅, 等. 南方红壤典型水土流失区植被分类及植被类型变化的遥感评估: 以福建省长汀县河田地区为例[J]. 遥感技术与应用, 2017, 32(3):546-555.
	Fu Wei, Xu Hanqiu, Wang Meiya, et al. Vegetation classification and variation assessment in a typical red soil erosion area in Southern China: Hetian, Changting County of Fujian Province. Remote Sensing Technology and Application, 2017, 32(3):546-555.
[5]	刘华, 陈永富, 鞠洪波, 等. 美国森林资源监测技术对我国森林资源一体化监测体系建设的启示[J]. 世界林业研究, 2012, 25(6):64-68.
	Liu Hua, Chen Yongfu, Ju Hongbo, et al. Inspiration of forest resources monitoring in USA for integrated forest resources monitoring system in China. World Forestry Research, 2012, 25(6):64-68.
[6]	Jia K, Wei X Q, Gu X F, et al. Land cover classification using Landsat 8 operational land imager data in Beijing, China[J]. Geocarto International, 2014, 29(8):941-951.
[7]	Poursanidis D, Chrysoulakis N, Mitraka Z. Landsat 8 vs. Landsat 5: A comparison based on urban and peri-urban land cover mapping[J]. International Journal of Applied Earth Observation and Geoinformation, 2015, 35:259-269.
[8]	Calleja F, Ondiviela B, Galván C, et al. Mapping estuarine vegetation using satellite imagery: The case of the invasive species Baccharis halimifolia at a Natura 2000 site[J]. Continental Shelf Research, 2019, 174:35-47.
[9]	Petropoulos G P, Kalaitzidis C, Vadrevu K P. Support vector machines and object-based classification for obtaining land-use/cover cartography from Hyperion hyperspectral imagery[J]. Computers & Geosciences, 2012, 41:99-107.
[10]	Barnetson J, Phinn S, Scarth P. Mapping woody vegetation cover across Australia's arid rangelands: Utilising a machine-learning classification and low-cost Remotely Piloted Aircraft System[J]. International Journal of Applied Earth Observation and Geoinformation, 2019, 83: 101909. doi: 10.1016/j.jag.2019.101909.
[11]	Luo S Z, Wang C, Xi X H, et al. Fusion of airborne discrete-return LiDAR and hyperspectral data for land cover classification[J]. Remote Sensing, 2015, 8(1):3. doi: 10.3390/rs8010003.
[12]	Heiskanen J, Kivinen S. Assessment of multispectral, -temporal and -angular MODIS data for tree cover mapping in the tundra-taiga transition zone[J]. Remote Sensing of Environment, 2008, 112(5):2367-2380.
[13]	Zhang X, Zhang M, Zheng , et al. Crop mapping using PROBA-V time series data at the Yucheng and Hongxing farm in China[J]. Remote Sensing, 2016, 8(11):915. doi: 10.3390/rs8110915.
[14]	Thanh Noi P, Kappas M. Comparison of random forest, k-nearest neighbor, and support vector machine classifiers for land cover classification using Sentinel-2 imagery[J]. Sensors (Basel), 2017, 18(1): 18. doi: 10.3390/s18010018.
[15]	Belgiu M, Drăguţ L. Random forest in remote sensing: A review of applications and future directions[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 114:24-31.
[16]	张赫林, 彭代亮, 邓睿, 等. 基于Landsat时间序列数据的祁连山区域土地利用变化[J]. 北京工业大学学报, 2017, 43(5):665-676.
	Zhang Helin, Peng Dailiang, Deng Rui, et al. Dynamic change of land use in Qilian Mountains based on time-series Landsat image. Journal of Beijing University of Technology, 2017, 43(5):665-676.
[17]	周兴文. 庐山植被研究[J]. 沈阳教育学院学报, 1999(2):111-114.
	Zhou Xingwen. Study on the vegetation of the Lushan in China. Journal of Shenyang College of Education, 1999(2):111-114.
[18]	陈世隆, 王江林, 杨建国. 庐山的植被[J]. 自然杂志, 1980, 2(3):204-208.
	Chen Shilong, Wang Jianglin, Yang Jianguo. Vegetation on Lushan Mountain. Nature Magazine, 1980, 2(3):204-208.
[19]	张金泉. 庐山植被的垂直分带[J]. 华南师院学报(自然科学版), 1982, 14(1):1-14.
	Zhang Jinquan. Division of the vertical vegetation zone in Lushan Mountain. Journal of the South China Normal University (Natural Science Edition), 1982, 14(1):1-14.
[20]	孙燕. 庐山自然保护区主要道路对外来植物影响研究[D]. 北京: 北京林业大学, 2012.
	Sun Yan. Alien plant species in major roadsides and trail sides of Lushan Natural Reserve, Jiangxi Province. Beijing, China: Beijing Forestry University, 2012.
[21]	李杭燕, 颉耀文, 马明国. 时序NDVI数据集重建方法评价与实例研究[J]. 遥感技术与应用, 2009, 24(5):596-602.
	Li Hangyan, Xie Yaowen, Ma Mingguo. Reconstruction of temporal NDVI dataset: Evaluation and case study. Remote Sensing Technology and Application, 2009, 24(5):596-602.
[22]	王丹, 姜小光, 唐伶俐, 等. 利用时间序列傅立叶分析重构无云NDVI图像[J]. 国土资源遥感, 2005, 17(2):29-32.
	Wang Dan, Jiang Xiaoguang, Tang Lingli, et al. The application of time -series Fourier analysis to reconstructing cloud-free ndvi images. Remote Sensing for Land & Resources, 2005, 17(2):29-32.
[23]	Breiman L. Random forests[J]. Machine Learning, 2001, 45(1):5-32.
[24]	Biau G E R. Analysis of a random forests model[J]. The Journal of Machine Learning Research, 2012, 13(1):1063-1095.
[25]	张磊, 宫兆宁, 王启为, 等. Sentinel-2影像多特征优选的黄河三角洲湿地信息提取[J]. 遥感学报, 2019, 23(2):313-326.
	Zhang Lei, Gong Zhaoning, Wang Qiwei, et al. Wetland mapping of Yellow River Delta wetlands based on multi-feature optimization of Sentinel-2 images. Journal of Remote Sensing, 2019, 23(2):313-326.
[26]	万慧霖. 庐山森林生态系统植物多样性及其分布格局[D]. 北京: 北京林业大学, 2008.
	Wan Huilin. Plant diversity and its distribution pattern in the forest ecosystem of Lushan Mountain. Beijing, China: Beijing Forestry University, 2008.
[27]	Friedl M A, Sulla-Menashe D, Tan B, et al. MODIS collection 5 global land cover: Algorithm refinements and characterization of new datasets[J]. Remote Sensing of Environment, 2010, 114(1):168-182.
[28]	樊忠良. 庐山植物区系的特征和植被的分布[J]. 黄冈师专学报, 1994, 14(1):52-55.
	Fan Zhongliang. The features of flora and the distribution of vegetation at Lushan Mountain. Journal of Huanggang Normal University, 1994, 14(1):52-55.
[29]	Jenson J Q, Cowen D.. Principles of change detection using digital remote sensor data M// Star J L, Estes J E, McGwire K C. Integration of geographic information systems and remote sensing. Cambridge, UK: Cambridge University Press, 1997:1-25.

类别	2015年		2016年		2017年		2018年
类别	PA	UA	PA	UA	PA	UA	PA	UA
针叶林	0.86	0.88	0.84	0.86	0.84	0.86	0.83	0.89
混交林	0.85	0.83	0.83	0.84	0.82	0.84	0.87	0.84
阔叶林	0.83	0.86	0.83	0.83	0.82	0.85	0.89	0.83
竹林	0.86	0.83	0.87	0.84	0.91	0.84	0.83	0.85
OA/%	85.00		84.25		84.75		85.25
Kappa系数	0.80		0.79		0.81		0.80

土地覆盖产品	Proba-V	LC-CCI	Globcover	Globeland30	MODIS
空间分辨率/m	100	300	300	250	500
数据源	Proba-V时间序列数据	SPOT-VGT时间序列数据	MERIS卫星10 d 合成产品	Landsat TM、ETM+和 HJ-1多光谱图像	MODIS月EVI、 LST 8 d复合数据
产品可获取时间	2015—2018年	2008—2012年	2009年	2009—2011年	2010年
分类方法	随机森林分类	非监督的时空聚类; 机器学习分类	非监督时空聚类; 基于专家经验的标签	基于像素和对象的分类;基于知识的交互验证的集成	决策树
总体分类精度/%	>84	74.4	70.7	83.5	74.8

2015年	2016年
2015年	混交林	阔叶林	针叶林	竹林	变化率/%
混交林	33.97	0.35	0.81	1.00	5.99
阔叶林	0.11	56.88	0.38	0.33	1.41
针叶林	0.96	0.54	84.39	0.91	2.78
竹林	0.44	0.08	0.33	16.97	4.80
2016年	2017年
2016年	混交林	阔叶林	针叶林	竹林	变化率/%
混交林	33.57	0.11	0.91	0.45	4.37
阔叶林	0.32	56.53	0.44	0.14	1.59
针叶林	0.88	0.48	84.53	0.37	2.00
竹林	1.32	0.52	0.91	16.82	14.04
2017年	2018年
2017年	混交林	阔叶林	针叶林	竹林	变化率/%
混交林	33.70	0.53	0.94	1.60	9.09
阔叶林	0.04	56.31	0.20	0.59	1.48
针叶林	0.92	0.49	84.91	1.00	2.76
竹林	0.39	0.11	0.20	16.38	4.08

Forest vegetation classification and its variation in Lushan Nature Reserve using Proba-V vegetation products

RichHTML

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 8

References 29

Related Articles 6

Metrics

Comments

Recommended 0

[1]	Ming XU, Yuli SHI, Bin WANG. Reconstruction of high resolution monthly precipitation data of the Tibetan Plateau [J]. PROGRESS IN GEOGRAPHY, 2018, 37(7): 923-932.
[2]	Lin LIU, Wenjuan LIU, Weiwei LIAO, Hongjie YU, Chao JIANG, Rongping LIN, Jiakai JI, Zheng ZHANG. Comparison of random forest algorithm and space-time kernel density mapping for crime hotspot prediction [J]. PROGRESS IN GEOGRAPHY, 2018, 37(6): 761-771.
[3]	Min TAN, Kai LIU, Lin LIU, Yuanhui ZHU, Dashan WANG. Spatialization of population in the Pearl River Delta in 30 m grids using random forest model [J]. PROGRESS IN GEOGRAPHY, 2017, 36(10): 1304-1312.
[4]	CHEN Kai, LIU Kai, LIU Lin, ZHU Yuanhui. Urban expansion simulation by random-forest-based cellular automata: a case study of Foshan City [J]. PROGRESS IN GEOGRAPHY, 2015, 34(8): 937-946.
[5]	LAN Hengxing, ZHOU Chenghu, GAO Xing, CHENG Weiming, WANG Zhihua, YANG Zhihua, LI Langping, WU Yuming. Secondary geological hazard assessment and hazard mitigation countermeasures in Lushan, Ya'an Earthquake, Sichuan Province [J]. PROGRESS IN GEOGRAPHY, 2013, 32(4): 499-504.
[6]	CHENG Jiangang, WANG Xuefeng, FAN Lizhang, YANG Xiaopeng, YANG Pengwu. Variations of Yunnan Climatic Zones in Recent 50 Years [J]. PROGRESS IN GEOGRAPHY, 2009, 28(1): 18-24.