基于WorldView-2影像和随机森林算法的天山云杉蓄积量反演

doi:10.6048/j.issn.1001-4330.2022.08.020

新疆农业科学 ›› 2022, Vol. 59 ›› Issue (8): 1992-1998.DOI: 10.6048/j.issn.1001-4330.2022.08.020

• 植物保护·农产品分析检测·农业装备工程与机械化 • 上一篇下一篇

基于WorldView-2影像和随机森林算法的天山云杉蓄积量反演

吕金城(), 王振锡(), 杨勇强, 曲延斌, 马琪瑶

新疆农业大学林学与园艺学院 / 新疆教育厅干旱区林业生态与产业技术重点实验室,乌鲁木齐 832003

收稿日期:2021-10-13 出版日期:2022-08-20 发布日期:2022-10-01
通信作者: 王振锡
作者简介:吕金城（1995-）,男,新疆乌鲁木齐人,硕士研究生,研究方向为林业3S技术及应用,（E-mail） 1287460632@qq.com
基金资助:
新疆维吾尔自治区林业改革发展基金“新疆天保工程精准监测技术与评价体系研究”(XJTB20181102)

Inversion of Picea schrenkiana var. tianshanica Growing Stock Based on WorldView-2 Image and Random Forest Algorithm

LV Jincheng(), WANG Zhenxi(), YANG Yongqiang, QU Yanbin, MA Qiyao

College of Forestry and Horticulture, Xinjiang Agricultural University, Key Laboratory of Forestry Ecology and Industrial Technology in Arid Area of Xinjiang Education Department. Urumqi 830052, China

Received:2021-10-13 Online:2022-08-20 Published:2022-10-01
Correspondence author: WANG Zhenxi
Supported by:
Reform and Development Fund of Xinjiang Uygur Autonomous Region “Research on Engineering Precision Monitoring Technology and Evaluation System of Xinjiang Natural Forestry Protection”(XJTB20181102)

摘要/Abstract

摘要：

【目的】研究林地遥感因子与蓄积量的关系来反演天山云杉林分蓄积量,为新疆天然林保护工程实施后天山云杉生态恢复与科学管理提供参考依据。【方法】以新疆天山西部巩留县恰国家西森林公园的天山云杉（Picea schrenkiana var.tianshanica）为研究对象,以样地内每木检尺为依据,基于WorldView-2影像,使用eCognition Developer 提取样地的光谱信息、纹理因子与植被指数三种遥感因子,通过随机森林算法建立模型反演天山云杉林分蓄积量。【结果】提取的24种遥感因子,筛选出对蓄积量影响最大的5种特征变量,分别为NDVI1、NDVI2、RVI2、均一性（Homogeneity）与相关性（Correlation）,建立随机森林回归模型,解释度高达81.27%,决定系数R²=0.8648（P<0.05）,估测样地蓄积量精度为86.38%。【结论】建立的随机森林回归模型可以有效地反演天山云杉林林分蓄积量。

关键词: 蓄积量; WorldView-2影像; 天山云杉; 随机森林算法

Abstract:

【Objective】 Taking the Picea schrenkiana var. tianshanica of Qiaxi National Forest Park in Gongliu County, western Tianshan, Xinjiang as the research object, World View-2 images and the sample plot scale per tree as the data source, the volume of Picea schrenkiana var. tianshanica was retrieved by looking for the relationship between remote sensing factors and volume. The purpose of this project is to provide a reference basis for Picea schrenkiana var. tianshanica ecological restoration and scientific management after the implementation of the natural forest protection project. 【Method】 The spectral information, texture factor and vegetation index of the sample plot were extracted by eCognition Developer, and a model was established to retrieve the volume of Picea schrenkiana var. tianshanica forest by random forest algorithm. 【Result】The random forest algorithm was used to screen 24 kinds of remote sensing factors, and the five characteristic variables which had the greatest influence on the stock were selected. The five characteristic variables with the largest impact on the accumulation were selected, respectively, NDVI1, NDVI2, RVI2, homogeneity（Homogeneity） and correlation（Correlation）, thus establishing a random forest regression model. Its interpretation was up to 81.27%, the determination coefficient R² was = 0.8648（P <0.05） and the accuracy of estimating sample plot volume was 86.38%. 【Conclusion】 The stochastic forest regression model established by random forest algorithm and WorldView-2 image can effectively retrieve the volume of Picea schrenkiana var. tianshanica.

Key words: growing stock; World View-2 imaging; Picea schrenkiana var. tianshanica; random forest algorithm

中图分类号:

S725

吕金城, 王振锡, 杨勇强, 曲延斌, 马琪瑶. 基于WorldView-2影像和随机森林算法的天山云杉蓄积量反演[J]. 新疆农业科学, 2022, 59(8): 1992-1998.

LV Jincheng, WANG Zhenxi, YANG Yongqiang, QU Yanbin, MA Qiyao. Inversion of Picea schrenkiana var. tianshanica Growing Stock Based on WorldView-2 Image and Random Forest Algorithm[J]. Xinjiang Agricultural Sciences, 2022, 59(8): 1992-1998.

图/表 7

图 1 处理结果

Fig. 1 Preprocessing result diagram

图 2 研究区WorldView-2影像植被指数

Fig. 2 Vegetation index of WorldView-2 image in study area

表 1 纹理特征

Table 1 The texture characteristics

图 3 随机森林遥感因子筛选

Fig. 3 Screening of random forest remote sensing factors

图 4 随机森林结果

Fig. 4 Random forest result

图 5 样地蓄积量实测值与预测值线性回归

Fig. 5 Linear regression of measured and predicted stock volume in sample plots

图 6 蓄积量残差分布

Fig. 6 Residual distribution of stock volume

参考文献 16

[1]	吴霜, 延晓冬, 张丽娟. 中国森林生态系统与服务功能价值的关系[J]. 地理学报, 2014, 69(3): 334-342. DOI
	WU Shuang, YAN Xiaodong, ZHANG Lijuan. The relationship between forest ecosystem emergy andforest ecosystem service value in China[J]. ActaGeographicaSincia, 2014, 69(3): 334-342.
[2]	于生华. 天然林资源共享保护工程在我区经济社会发展中的地位和重要性[J]. 新疆林业, 2015,(1): 21-23.
	YU Shenghua. The status and importance of natural forest resource sharing and protection project ineconomic and social development[J]. Forestry of Xinjiang, 2015,(1): 21-23.
[3]	李明辉, 何风华, 刘云, 等. 天山云杉种群空间格局与动态[J]. 生态学报, 2005, 25(5):1000-1006.
	LI Minghui, HE Fenghua, LIU Yun, et al. Spatial distribution pattern of tree individuals in the PiceaSchrenkianavartianshanica[J]. ActaEcologicaSinica, 2005, 25(5): 1000-1006.
[4]	王雅佩, 王振锡, 刘梦婷, 等. 基于无人机影像天山云杉林主伐迹地提取研究[J]. 新疆农业科学, 2019, 56(7):1315-1327. DOI
	WANG Yapei, WANG Zhengxi, LIU Mengting, et al. Research on estimation of stand density of regenerate PiceaSchrenkianavartianshanica based on UAV Image[J]. Xinjiang Agricultural Sciences, 2019, 56(7):1315-1327. DOI
[5]	李世波, 林辉, 王光明, 等. 基于GF-1的森林蓄积量遥感估测[J]. 中南林业科技大学学报, 2019, 39(8):70-75,86.
	LI Shibo, LIN Hui, WANG Guangming, et al. Remote sensing estimation of forest stock based on GF-1[J]. Journal of Central South University of Forestry & Technology, 2019,(8): 70-75,86.
[6]	贾嘉辉. 高分遥感森林蓄积量估测算法研究[D]. 西安: 西安科技大学, 2017.
	JIA Jiahui. Study on forest Stock Estimation Algorithm for high resolution remote sensing[D]. Shanxi: Xian Technology University. 2017.
[7]	曹霖. 基于Sentinel-2影像的延庆区森林蓄积量遥感估测研究[D]. 北京: 北京林业大学. 2019.
	CAO Lin. Estimation of Pinuskesiya var. langbianensis Forest Stock Volume based on Sentinel-1A SAR Image Remote sensing Estimation of Forest stock in Yanqing District based on Sentinel-2 image[D]. Beijing: Beijing Forestry University. 2019
[8]	Chen J, Gu S, Shen M, Tang Y, Matsushita B. Estimating aboveground Biomassof grassland having a high canopy cover: an exploratory analysis of in situ hyperspectral data[J]. International Journal of Remote Sensing, 2009, 30,6497-6517. DOI URL
[9]	Chen J, Song G, Shen M, Tang Y. Estimating above-ground biomass of grassland having a high canopy cover: an explanatoryanalysisof in situ hyperspectral data[J]. International Journal of Remote Sensing, 2009, 24, 6497-6517.
[10]	MutangaO,; SkidmoreA.k; Narrow band vegetationindices overcome thesaturation problem in biomass estimation[J]. International Journal of Remote Sensing, 2004, 25, 3999-4014. DOI URL
[11]	MutangaO, ; SkidmoreA.K; Hyperspectral band depth analysis for a betterestimation of pasture biomass[J]. International Journal of Applied Earth Observation and Geoinformation, 2004, 5, 87-96. DOI URL
[12]	MuthuriF,; KinyamarioJ; Nutritive value of papyrus(Cyperus papyrus, Cyperaceae), a tropical emergent macrophyte[J]. Economic Botany, 1989, 43, 23-30. DOI URL
[13]	PalM; Random forest classifier for remote sensing classification[J]. InternationalJournal of Remote Sensing, 2005, 26, 217-222.
[14]	刘俊. 基于ALOS遥感影像纹理信息的怀柔区针、阔叶林蓄积量反演模型研究[D]. 北京: 北京林业大学, 2014.
	LIU Jun. Study on Volume inversion Model of coniferous and Broad-leaved Forest in Huairou area based on texture Information of ALOS remote Sensing Image[D]. Beijing: Beijing Forestry University. 2014.
[15]	王海宾, 彭道黎, 高秀会, 等. 基于GF-1 PMS影像和k-NN方法的延庆区森林蓄积量估测[J]. 浙江农林大学学报, 2018, 35(6):1070-1078.
	Wang Haibin, Peng Daoli, Gao Xiuhui, et al. Estimation of Forest Volume in Yanqing District based on GF-1 PMS Image and k-NN method[J]. Journal of Zhejiang Agriculture and Forestry University, 2018, 35(6): 1070-1078.
[16]	冯凯, 刘昌华, 彭词清. 基于landset8遥感影像数据的森林蓄积量反演[J]. 矿山测量, 2020, 48(1):27-30,39.
	FENG Kai, LIU Changhua, PENG Ciqing. Forest stock inversion based on landset8 remote sensing image data[J]. Mine Survey, 2020, 48(1): 27-30,39.

基于WorldView-2影像和随机森林算法的天山云杉蓄积量反演

Inversion of Picea schrenkiana var. tianshanica Growing Stock Based on WorldView-2 Image and Random Forest Algorithm

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 7

参考文献 16

相关文章 15

编辑推荐

Metrics

[1]	席丽, 李思瑶, 夏晓莹, 陈玉雯, 李林, 王杰, 马小龙, 米尔扎提·柯尼加里木, 阿丽耶·麦麦提, 王卫霞. 不同郁闭度天山云杉林土壤养分特征[J]. 新疆农业科学, 2023, 60(9): 2216-2222.
[2]	曲延斌, 王振锡, 胡天祺, 董巍, 陈哲. 基于机载激光雷达影像的天山云杉林树高提取及蓄积量反演[J]. 新疆农业科学, 2023, 60(4): 958-964.
[3]	夏晓莹, 李思瑶, 王杰, 马小龙, 席丽, 米尔扎提·柯尼加里木, 阿丽耶·麦麦提, 王卫霞. 地形因子对天山北坡天山云杉林土壤有机碳的影响[J]. 新疆农业科学, 2023, 60(4): 965-973.
[4]	胡文聪, 潘存德, 赵善超, 宋梦真, 童海麦, 田晨阳. 天山北坡中部天山云杉1 a生天然更新幼苗存活数量与功能性状的微生境分析[J]. 新疆农业科学, 2023, 60(2): 454-463.
[5]	葛瑶, 王振锡. 天山云杉林不同林型物种多样性对土壤因子的响应[J]. 新疆农业科学, 2022, 59(1): 134-144.
[6]	裴媛, 王振锡, 朱思名, 葛瑶, 师玉霞. 天山西部云杉林群落数量分类与排序[J]. 新疆农业科学, 2021, 58(2): 313-323.
[7]	吕金城, 王振锡, 杨勇强, 曲延斌, 马琪瑶, 朱思明. 基于无人机影像的天山云杉林树高提取及蓄积量的反演[J]. 新疆农业科学, 2021, 58(10): 1838-1845.
[8]	杨勇强, 王振锡, 师玉霞, 连玲, 高亚利. 基于无人机影像的天山云杉林单木树冠信息提取[J]. 新疆农业科学, 2020, 57(8): 1484-1492.
[9]	王卫霞, 杨光, 王振锡. 更新方式对天山云杉林土壤碳氮的影响[J]. 新疆农业科学, 2020, 57(8): 1474-1483.
[10]	王雅佩, 王振锡, 刘梦婷, 李擎, 杨勇强. 基于无人机影像天山云杉林主伐迹地提取研究[J]. 新疆农业科学, 2019, 56(7): 1312-1324.
[11]	禹思慧, 王振锡, 王雅佩, 刘梦婷, 李擎. 高强度采伐对天山云杉更新群落物种组成的影响[J]. 新疆农业科学, 2018, 55(7): 1274-1285.
[12]	伊丽米努尔;李宏. 天山云杉成熟与未成熟合子胚的胚性愈伤组织诱导及增殖研究[J]. , 2017, 54(2): 262-271.
[13]	马晓瑜;孟晖;潘存德;张国林. 天山中部不同年龄和海拔高度天山云杉天然更新幼苗茎干功能性状[J]. , 2014, 51(7): 1238-1245.
[14]	周琳;孟晖;潘存德;张国林;王兵. 天山中部天山云杉林土壤种子库与地上植被的物种相似性[J]. , 2013, 50(7): 1235-1245.
[15]	李华东;潘存德;张国林;王兵. 天山中部天山云杉林土壤种子库海拔梯度分布格局[J]. , 2012, 49(8): 1373-1380.