基于Sentinel-2卫星影像与梯度提升树回归模型的疏林郁闭度精准监测——以内蒙古退耕还林工程为例

doi:10.11707/j.1001-7488.LYKX20240765

林业科学 ›› 2026, Vol. 62 ›› Issue (2): 173-185.doi: 10.11707/j.1001-7488.LYKX20240765

基于Sentinel-2卫星影像与梯度提升树回归模型的疏林郁闭度精准监测——以内蒙古退耕还林工程为例

王天璨^1,^2,³,格根塔娜⁴,李晓松^1,^2,*(),月亮高可⁵,沈通^1,²,陈超超^1,^2,³,智育博^1,^2,³,赵立成^1,²,姬翠翠⁵

1. 中国科学院空天信息创新研究院　北京 100094
2. 可持续发展大数据国际研究中心　北京 100094
3. 中国科学院大学　北京100049
4. 内蒙古自治区林业与草原工作总站　呼和浩特 010010
5. 重庆交通大学智慧城市学院　重庆 400074

收稿日期:2024-12-16 修回日期:2025-02-17 出版日期:2026-02-25 发布日期:2026-03-04
通讯作者: 李晓松 E-mail:lixs@aircas.ac.cn
基金资助:
能力培育项目-MFST-蒙古高原土地退化零增长决策支持系统与示范应用(4221101459)；内蒙古自治区林业与草原工作总站委托项目“内蒙古自治区退耕还林生态成效监测评估与数据库建立（二期）”；重庆市自然科学基金面上项目(CSTB2023NSCQ-MSX0967)；空间观测可持续发展国际大科学计划(STS)(313GJHZ2022040BS)

Accurate Monitoring of Sparse Forest Canopy Closure Based on Sentinel-2 and GBRT Model: a Case Study on the Returning Farmland to Forest Project in the Inner Mongolia

Tiancan Wang^1,^2,³,Gegentana ⁴,Xiaosong Li^1,^2,*(),Yuelianggaoke ⁵,Tong Shen^1,²,Chaochao Chen^1,^2,³,Yubo Zhi^1,^2,³,Licheng Zhao^1,²,Cuicui Ji⁵

1. Aerospace Information Research Institute, Chinese Academy of Sciences　Beijing 100094
2. International Research Center of Big Data for Sustainable Development Goals　Beijing 100094
3. University of Chinese Academy of Sciences　Beijing 100101
4. Forestry and Grassland Work Station of Inner Mongolia　Hohhot 010010
5. Smart City Academy, Chongqing Jiaotong University　Chongqing 400074

Received:2024-12-16 Revised:2025-02-17 Online:2026-02-25 Published:2026-03-04
Contact: Xiaosong Li E-mail:lixs@aircas.ac.cn

摘要/Abstract

摘要：

目的: 协同高分辨率无人机数据与Sentinel-2卫星遥感影像，利用梯度提升回归树算法，实现对退耕还林区疏林郁闭度的精准监测，为新一轮退耕还林工程成效评估提供技术支持。方法: 在退耕还林典型区域收集无人机激光雷达及可见光影像数据，结合2024年生长季和非生长季的Sentinel-2遥感影像及地形数据，构建梯度提升回归树模型对退耕还林疏林郁闭度进行估算，并对其精度与区分能力进行评估。结果: 基于无人机获取90个退耕还林地块激光雷达点云和可见光影像，利用点云计算冠层高度模型（CHM）结合阈值分割法，实现了5 764个疏林郁闭度样本集构建；基于多时相Sentinel-2遥感影像特征与地形信息等多种变量，建立了梯度提升回归树模型，实现了疏林郁闭度的精细监测，模型决定系数R²为0.731，均方根误差RMSE为0.028，平均绝对误差MAE为0.021；非生长季的反射率、植被指数及海拔特征重要性较高，证明地形信息和非生长季的光谱信息是低郁闭度精准估测的关键因子。结论: 结合高精度无人机激光雷达数据和Sentinel-2遥感影像构建的梯度提升树回归模型可以较好地估算疏林郁闭度，并且在不同地理环境和植被类型的影响下具有较好的稳定性，对内蒙古新一轮退耕还林工程建设效益评估具有重要意义。

关键词: Sentinel-2, 无人机, 退耕还林, 内蒙古, 疏林, 郁闭度, 梯度提升树

Abstract:

Objective: The purpose of this study is to integrate high-resolution UAV data with Sentinel-2 satellite imagery and utilize the Gradient Boosting Regression Tree algorithm to achieve accurate monitoring of sparse forest canopy closure in the Returning Farmland to Forest Project areas, thereby providing technical support for effectiveness assessment of the new round of the project. Method: UAV LiDAR and visible light image data were collected in typical areas of returning farmland to forest. Combined with Sentinel-2 remote sensing images in the growing and non-growing seasons of 2024 and terrain data, a gradient boosting regression tree model was established to estimate the canopy closure of the sparse forest, and its accuracy and discrimination ability were evaluated. Result: With UAV-based LiDAR point cloud and visible light images of 90 open forest plots of land for returning farmland to forests, the canopy height model (CHM) combined with the threshold segmentation method were used to construct 5 764 sparse forest canopy closure sample points. Based on multi-temporal Sentinel-2 remote sensing image features and topographic information, a gradient lifting regression tree model was established to realize the accurate monitoring of sparse forest canopy closure, and the model coefficient of determination (R²) was 0.731, the root mean squared error (RMSE) was 0.028, and the mean absolute error (MAE) was 0.021. The vegetation indexes and reflectance of non-growing seasons and the elevation were the key factors for estimating sparse forest canopy closure. Conclusion: The gradient boosting tree regression model constructed by combining high-precision UAV LiDAR data and Sentinel-2 remote sensing images can better predict the sparse forest canopy closure, and has good stability under the influence of different geographic environments and vegetation types, which is of great significance for the effectiveness assessment of the new round of returning farmland to forest projects in Inner Mongolia.

Key words: Sentinel-2, UAV, returning farmland to forest, Inner Mongolia, sparse vegetation, canopy cover, gradient boosting regression tree

中图分类号:

S771.8
TP79

王天璨,格根塔娜,李晓松,月亮高可,沈通,陈超超,智育博,赵立成,姬翠翠. 基于Sentinel-2卫星影像与梯度提升树回归模型的疏林郁闭度精准监测——以内蒙古退耕还林工程为例[J]. 林业科学, 2026, 62(2): 173-185.

Tiancan Wang,Gegentana ,Xiaosong Li,Yuelianggaoke ,Tong Shen,Chaochao Chen,Yubo Zhi,Licheng Zhao,Cuicui Ji. Accurate Monitoring of Sparse Forest Canopy Closure Based on Sentinel-2 and GBRT Model: a Case Study on the Returning Farmland to Forest Project in the Inner Mongolia[J]. Scientia Silvae Sinicae, 2026, 62(2): 173-185.

参考文献 0

	陈宝瑞, 辛晓平, 朱玉霞, 等. 内蒙古荒漠化年际动态变化及与气候因子分析. 遥感信息, 2007, 22 (6): 39- 44,104.
	Chen B R, Xin X P, Zhu Y X, et al. Change and analysis of annual desertification and climate factors in Inner Mongolia using MODIS data. Remote Sensing Information, 2007, 22 (6): 39- 44,104.
	胡婵娟, 郭　雷. 植被恢复的生态效应研究进展. 生态环境学报, 2012, 21 (9): 1640- 1646.
	Hu C J, Guo L. Advances in the research of ecological effects of vegetation restoration. Ecology and Environmental Sciences, 2012, 21 (9): 1640- 1646.
	贾　坤, 姚云军, 魏香琴, 等. 植被覆盖度遥感估算研究进展. 地球科学进展, 2013, 28 (7): 774- 782.
	Jia K, Yao Y J, Wei X Q, et al. A review on fractional vegetation cover estimation using remote sensing. Advances in Earth Science, 2013, 28 (7): 774- 782.
	冷若琳, 张瑶瑶, 谢建全, 等. 基于多光谱数据与小型无人机的甘南草地非生长季植被覆盖度. 草业科学, 2019, 36 (11): 2742- 2751.
	Leng R L, Zhang Y Y, Xie J Q, et al. An analysis of fractional vegetation cover of the Gannan grassland in the non-growing season based on Multispectral data and small UVAs. Pratacultural Science, 2019, 36 (11): 2742- 2751.
	李世东, 吴转颖. 中西部地区退耕还林还草模式探讨. 林业科学, 2002, 38 (3): 154- 159.
	Li S D, Wu Z Y. Study on models of conversion of cropland to forest and grassland in the midwest China. Scientia Silvae Sinicae, 2002, 38 (3): 154- 159.
	李晓雅, 田　昕, 段　涛, 等. 融合无人机和卫星影像的温带疏林草原木本和草本植物覆盖度遥感估算. 遥感学报, 2023, 27 (9): 2139- 2152.
	Li X Y, Tian X, Duan T, et al. Estimation of fractional woody and herbaceous vegetation cover in temperate sparse forest grassland using fusion of UAV and satellite imagery. Journal of Remote Sensing, 2023, 27 (9): 2139- 2152.
	李新荣, 张景光, 李玉俊, 等. 我国北方荒漠化地区主要灌木种的物候学研究. 自然资源学报, 1999, 14 (2): 128- 134.
	Li X R, Zhang J G, Li Y J, et al. A phenological study on main shrub species in the desertification region of northern China. Journal of Natural Resources, 1999, 14 (2): 128- 134.
	刘佳丽, 范建容, 张茜彧, 等. 高寒草地生长季/非生长季植被盖度遥感反演. 草业学报, 2021, 30 (9): 15- 26.
	Liu J L, Fan J R, Zhang X Y, et al. Remote sensing estimation of vegetation cover in alpine grassland in the growing and non-growing seasons. Acta Prataculturae Sinica, 2021, 30 (9): 15- 26.
	刘清旺, 李世明, 李增元, 等. 无人机激光雷达与摄影测量林业应用研究进展. 林业科学, 2017, 53 (7): 134- 148.
	Liu Q W, Li S M, Li Z Y, et al. Review on the applications of UAV-based LiDAR and photogrammetry in forestry. Scientia Silvae Sinicae, 2017, 53 (7): 134- 148.
	刘清旺, 谭炳香, 胡凯龙, 等. 机载激光雷达和高光谱组合系统的亚热带森林估测遥感试验. 高技术通讯, 2016, 26 (3): 264- 274.
	Liu Q W, Tan B X, Hu K L, et al. The remote sensing experiment on airborne LiDAR and hyperspectral integrated system for subtropical forest estimation. Chinese High Technology Letters, 2016, 26 (3): 264- 274.
	吕长春, 王忠武, 钱少猛. 混合像元分解模型综述. 遥感信息, 2003, 18 (3): 55- 58,60.
	Lü C C, Wang Z W, Qian S M. A review of pixel unmixing models. Remote Sensing Information, 2003, 18 (3): 55- 58,60.
	苗百岭, 梁存柱, 韩　芳, 等. 内蒙古主要草原类型植物物候对气候波动的响应. 生态学报, 2016, 36 (23): 7689- 7701.
	Miao B L, Liang C Z, Han F, et al. Responses of phenology to climate change over the major grassland types. Acta Ecologica Sinica, 2016, 36 (23): 7689- 7701.
	沈泽昊, 张新时, 金义兴. 地形对亚热带山地景观尺度植被格局影响的梯度分析. 植物生态学报, 2000, 24 (4): 430- 435.
	Shen Z H, Zhang X S, Jin Y X. Gradient analysis of the influence of mountain topography on vegetation pattern. Chinese Journal of Plant Ecology, 2000, 24 (4): 430- 435.
	王枭轩, 左小清, 杨泽楠. 遥感影像重采样方法实现与应用研究. 软件, 2019, 40 (7): 42- 46.
	Wang X X, Zuo X Q, Yang Z N. Research on realization and application of remote sensing image resampling. Computer Engineering & Software, 2019, 40 (7): 42- 46.
	吴炳方, 苑全治, 颜长珍, 等. 21世纪前十年的中国土地覆盖变化. 第四纪研究, 2014, 34 (4): 723- 731.
	Wu B F, Yuan Q Z, Yan C Z, et al. Land cover changes of China from 2000 to 2010. Quaternary Sciences, 2014, 34 (4): 723- 731.
	吴　飏, 张登荣, 张汉奎, 等. 结合图像纹理特征的森林郁闭度遥感估测. 林业科学, 2012, 48 (2): 48- 53.
	Wu Y, Zhang D R, Zhang H K, et al. Remote sensing estimation of forest canopy density combined with texture features. Scientia Silvae Sinicae, 2012, 48 (2): 48- 53.
	杨存建, 刘纪远, 张增祥, 等. 遥感和GIS支持下的中国退耕还林还草决策分析. 遥感学报, 2002, 6 (3): 205- 211.
	Yang C J, Liu J Y, Zhang Z X, et al. Decision-marking on returning the dry upland to forest or grass land with support of GIS and remote sensing in China. Journal of Remote Sensing, 2002, 6 (3): 205- 211.
	杨欣慰, 曹春香, 徐　敏, 等. 基于Li-Strahler几何光学模型的区域人工林郁闭度反演. 航天返回与遥感, 2024, 45 (3): 137- 149.
	Yang X W, Cao C X, Xu M, et al. Canopy closure inversion of regional plantation based on Li-strahler geometric-optical model. Spacecraft Recovery & Remote Sensing, 2024, 45 (3): 137- 149.
	张宏鸣, 刘　雯, 韩文霆, 等. 基于梯度提升树算法的夏玉米叶面积指数反演. 农业机械学报, 2019, 50 (5): 251- 259.
	Zhang H M, Liu W, Han W T, et al. Inversion of summer maize leaf area index based on gradient boosting decision tree algorithm. Transactions of the Chinese Society for Agricultural Machinery, 2019, 50 (5): 251- 259.
	周杰英, 贺鹏飞, 邱荣发, 等. 融合随机森林和梯度提升树的入侵检测研究. 软件学报, 2021, 32 (10): 3254- 3265.
	Zhou J Y, He P F, Qiu R F, et al. Research on intrusion detection based on random forest and gradient boosting tree. Journal of Software, 2021, 32 (10): 3254- 3265.
	Anchang J Y, Prihodko L, Ji W J, et al. Toward operational mapping of woody canopy cover in tropical savannas using google earth engine. Frontiers in Environmental Science, 2020, 8, 4. doi: 10.3389/fenvs.2020.00004
	Chen A, Xu C, Zhang M, et al. Cross-scale mapping of above-ground biomass and shrub dominance by integrating UAV and satellite data in temperate grassland. Remote Sensing of Environment, 2024, 304, 114024. doi: 10.1016/j.rse.2024.114024
	Bergamo T F, de Lima R S, Kull T, et al. From UAV to PlanetScope: Upscaling fractional cover of an invasive species Rosa rugosa. Journal of Environmental Management, 2023, 336, 117693. doi: 10.1016/j.jenvman.2023.117693
	Blackburn G A, Milton E J. Seasonal variations in the spectral reflectance of deciduous tree canopies. International Journal of Remote Sensing, 1995, 16 (4): 709- 720. doi: 10.1080/01431169508954435
	Carreiras J M B, Pereira J M C, Pereira J S. Estimation of tree canopy cover in evergreen oak woodlands using remote sensing. Forest Ecology and Management, 2006, 223 (1/2/3): 45- 53.
	Coulston J W, Jacobs D M, King C R, et al. The influence of multi-season imagery on models of canopy cover. Photogrammetric Engineering & Remote Sensing, 2013, 79 (5): 469- 477.

[1]	周晟,蒋馥根,陈帅,龙依,王彬彬,宋子戈,孙华. 联合星−空激光雷达和Sentinel-2数据的森林地上生物量估测方法[J]. 林业科学, 2026, 62(3): 74-87.
[2]	陈洪立,王冠凯,张文福,张建,黄宏亮,杨振华,赵胤,杜小强. 基于无人机的竹产品与疫木下山吊运系统设计与试验[J]. 林业科学, 2026, 62(1): 177-187.
[3]	于晓燕,高雅娴,魏光普,张舒宇,张文君. 内蒙古自治区植被恢复力时空格局及其对极端气候的响应[J]. 林业科学, 2025, 61(9): 48-58.
[4]	张宇娇,赵恒谦,付含聪,刘哿,皇甫霞丹,刘轩绮. 基于无人机遥感多特征的单木地上生物量反演模型[J]. 林业科学, 2025, 61(8): 129-141.
[5]	熊晓燕,李彩霞,柴国奇,陈龙,贾翔,雷令婷,张晓丽. 联合UAV-LiDAR和GEDI数据的区域森林地上生物量估算[J]. 林业科学, 2025, 61(8): 142-153.
[6]	吴家敏,王亚欣,孙斌,马志杰,孙维娜,洪亮. 基于无人机的柠条锦鸡儿生物量遥感估测[J]. 林业科学, 2025, 61(6): 13-24.
[7]	格根塔娜,月亮高可,李晓松,姬翠翠,王建和,沈通,王天璨. 基于GEDI和Sentinel-2的内蒙古退耕还林地块树高估测[J]. 林业科学, 2025, 61(3): 16-26.
[8]	魏光普,张文君,朱治衡,高雅娴,于晓燕. 基于kNDVI的内蒙古自治区2004—2023年植被覆盖度时空变化及气候驱动因子[J]. 林业科学, 2025, 61(11): 80-91.
[9]	谢婉滢,刘文萍,王晗. 无人机松林图像早期松材线虫病害检测[J]. 林业科学, 2024, 60(9): 124-133.
[10]	李美琪,刘美玲,王璇,刘湘南,吴伶,李军集. 八角林病虫害遥感识别模型[J]. 林业科学, 2024, 60(11): 128-138.
[11]	杨晓慧,吴金卓,刘浩然,钟浩,林文树. 基于UAV-LiDAR的人工林林分郁闭度估测[J]. 林业科学, 2023, 59(8): 12-21.
[12]	张婧怡,陈琛,王立群. 首轮退耕还林补贴到期对农户内部收入不平等的影响[J]. 林业科学, 2023, 59(4): 139-148.
[13]	郭旭展,陈巧,张晓芳,洪亮,尤媛媛,唐守正,符利勇. 基于无人机高分辨率影像的油松新造林健康树冠提取[J]. 林业科学, 2022, 58(10): 111-120.
[14]	黄翀,张晨晨,刘庆生,李贺,杨晓梅,刘高焕. 结合光学与雷达影像多特征的热带典型人工林树种精细识别[J]. 林业科学, 2021, 57(7): 80-91.
[15]	周小成,郑磊,黄洪宇. 基于多特征优选的无人机可见光遥感林分类型分类[J]. 林业科学, 2021, 57(6): 24-36.

基于Sentinel-2卫星影像与梯度提升树回归模型的疏林郁闭度精准监测——以内蒙古退耕还林工程为例

Accurate Monitoring of Sparse Forest Canopy Closure Based on Sentinel-2 and GBRT Model: a Case Study on the Returning Farmland to Forest Project in the Inner Mongolia

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献 0

相关文章 15

编辑推荐

Metrics

本文评价

作者中心

期刊获奖

引证指标

联系方式