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

doi:10.11707/j.1001-7488.LYKX20250054

摘要/Abstract

摘要：

目的: 探索新一代冰、云和陆地高程卫星（ICESat-2）与机载激光雷达及Sentinel-2多源数据联合反演区域森林地上生物量（AGB）的适配性，为大范围森林资源管理和动态监测提供科学依据。方法: 以内蒙古赤峰市旺业甸林场为研究区，基于机载激光雷达数据和样地实测数据建立高精度AGB估测模型，将样地AGB由离散的“点”状数据扩展到连续的“面”状数据，以克服样地点与星载点之间难以匹配的问题；在此基础上，联合ICESat-2与Sentinel-2遥感数据进行AGB反演，并基于最佳特征变量组合与最优反演模型，绘制研究区森林地上生物量空间分布图。结果: 1）基于机载激光雷达提取的三维结构信息与森林AGB高度相关，随机森林模型反演结果精度最高，相关系数为0.91，均方根误差（RMSE）为17.00 t·hm^?2, 估测精度（EA）为88.90%。2）在Sentinel-2基础上引入ICESat-2变量后，可进一步提升模型反演精度（R²=0.74, RMSE=27.44 t·hm^?2, EA=69.32%），R²和EA分别提高30.26%和14.18%。3）研究区森林AGB空间分布结果显示，东南部森林AGB分布较低（平均为97.13t·hm^?2），中东部和东北部森林AGB分布较高（平均为117.03 t·hm^?2），与实际分布一致。结论: 基于机载激光雷达数据反演的森林AGB精度较高，可作为连接样地实测数据和星载数据的中间参数。结合机载激光雷达、Sentinel-2及ICESat-2数据，不仅可提升森林AGB估测精度，也可为区域范围的森林资源管理和动态监测提供新的方法参考。

关键词: 森林地上生物量, 机器学习, ICESat-2, UAV-LiDAR, Sentinel-2

Abstract:

Objective: This study aims to explore the adaptability of the joint retrieval of regional forest aboveground biomass (AGB) by the new generation of ice, cloud, and land elevation satellite (ICESat-2), airborne LiDAR and Sentinel-2 multi-source data, providing scientific basis for large-scale forest resource management and dynamic monitoring. Method: Wangyedian Forest Farm in Chifeng City was selected as the research area, and a high-precision AGB estimation model was established based on airborne LiDAR data and sample plot measured data. The AGB of the sample plot was extended from discrete “points” to “surface” data on a large regional scale to overcome the problem of difficulty in matching sample points with spaceborne points. On this basis, ICESat-2 and Sentinel-2 remote sensing data were combined for AGB inversion, and the optimal variable combination and optimal inversion model were finally selected to draw the spatial distribution map of forest AGB in the study area. Result: 1) The three-dimensional structural information extracted from airborne LiDAR was highly correlated with forest AGB, and the inversion results of the random forest model had the highest accuracy with r of 0.91, root mean squared error (RMSE) of 17.00 t·hm^?2, and estimation accuracy (EA) of 88.90%. 2) After combining the ICESat-2 and Sentinel-2 variables, the accuracy of the inversion model was further improved (R²=0.74, RMSE=27.44 t·hm^?2, EA=69.32%), with R² and EA increasing by 30.26% and 14.18%, respectively. 3) The spatial distribution results of forest AGB in the study area showed that the forest AGB in the southeast was relatively low (with an average of 97.13 t·hm^?2), while that in the mid-east and northeast was relatively high (with an average of 117.03 t·hm^?2), which was consistent with the actual distribution. Conclusion: The AGB inverted from airborne LiDAR data has high accuracy, which can be used as an intermediate parameter to connect measured data and satellite data. Combining airborne LiDAR, Sentinel-2 and ICESat-2 data can not only further improve the estimation accuracy of forest AGB, but also provide a new reference for large-scale forest resource management and dynamic detection in the future.

Key words: forest aboveground biomass, machine learning, ICESat-2, UAV-LiDAR, Sentinel-2

中图分类号:

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.

Sheng Zhou,Fugen Jiang,Shuai Chen,Yi Long,Binbin Wang,Zige Song,Hua Sun. Estimation of Forest Aboveground Biomass Using Joint Spaceborne-UAV LiDAR and Sentinel-2 Data[J]. Scientia Silvae Sinicae, 2026, 62(3): 74-87.

图/表 13

图1

表1

表2

研究使用的光谱遥感变量①"

变量名称 Variable name	计算公式 Calculation formula	变量名称 Variable name	计算公式 Calculation formula
大气阻抗植被指数 Atmospherically resistant vegetation index (ARVI)	$ \dfrac{\left[{{\mathrm{NIR-(2Red-Blue)}}}\right]}{\left[{{\mathrm{NIR+(2Red-Blue)}}}\right]} $	绿色归一化差异植被指数 Green normalized difference vegetation index (GNDVI)	$ \dfrac{{{\mathrm{NIR-Green}}}}{{{\mathrm{NIR+Green}}}} $
差异植被指数 Difference vegetation index (DVI)	$ {{\mathrm{NIR-Red}}} $	绿色比值植被指数 Green ratio vegetation index (GRVI)	$ \dfrac{{{\mathrm{NIR}}}}{{{\mathrm{Green}}}} $
增强植被指数 Enhanced vegetation index (EVI)	$ {2.5\times }\dfrac{{{\mathrm{NIR-Red}}}}{{{\mathrm{NIR+6\times Red-7.5\times Blue+1}}}} $	归一化植被指数 Normalized difference vegetation index (NDVI)	$ \dfrac{{{\mathrm{NIR-Red}}}}{{{\mathrm{NIR+Red}}}} $
绿色大气阻力指数 Green atmospherically resistant index (GARI)	$ \dfrac{{{\mathrm{NIR}}-}\left[{{\mathrm{Green}}-1.7\times }\left({{\mathrm{Blue}}-{\mathrm{Red}}}\right)\right]}{{{\mathrm{NIR}}+}\left[{{\mathrm{Green}}+1.7\times }\left({{\mathrm{Blue-Red}}}\right)\right]} $	红边简单比值 Red edge simple ratio (RESR)	$ \dfrac{{{\mathrm{NIR}}}}{{{\mathrm{Red Edge}}1}} $
绿差植被指数 Green difference vegetation index (GDVI)	$ {{\mathrm{NIR-Green}}} $	红边叶绿素指数 Red edge chlorophyll index (RECI)	$ \dfrac{{{\mathrm{NIR}}}}{{{\mathrm{Red Edge}}1}}{-1} $
红边归一化差值植被指数a Red edge normalized difference vegetation index a (RENDVI_a)	$ \dfrac{{{\mathrm{NIR-Red Edge}}1}}{{{\mathrm{NIR+Red Edge}}1}} $	红边归一化差值植被指数b Red edge normalized difference vegetation index b (RENDVI_b)	$ \dfrac{{{\mathrm{NIR-Red Edge}}2}}{{{\mathrm{NIR+Red Edge}}2}} $
单波段反射率 Original band reflectance	$ B_i=\mathrm{Band}_i,\ i=1,2,\ldots,8 $	灰度差分向量 Gray level difference vector (GLDV)	$ {\mathrm{GLDV}}\_ i\_ j $
灰度共生矩阵 Gray level co-occurrence matrix (GLCM)	$ {\mathrm{GLCM}}\_ i\_ j $	和差直方图 Sum and difference histogram (SADH)	$ {\mathrm{SADH}}\_ i\_ j $

表2

图2

图3

表3

图4

表4

图5

图6

图7

图8

图9

参考文献 0

	曹海翊, 邱心怡, 贺　涛. 森林生物量遥感卫星发展综述. 光学学报, 2022, 42 (17): 402- 409. doi: 10.3788/AOS202242.1728001
	Cao H Y, Qiu X Y, He T. Review on development of forest biomass remote sensing satellites. Acta Optica Sinica, 2022, 42 (17): 402- 409. doi: 10.3788/AOS202242.1728001
	杜　洁, 史　硕, 刘晨曦. 基于ICESat-2光斑尺度外推建模的不同森林类型地上生物量反演. 测绘通报, 2024, 62 (10): 32- 38. doi: 10.13474/j.cnki.11-2246.2024.1006
	Du J, Shi S, Liu C X. Extrapolation modeling of aboveground biomass for different forest types based on ICESat-2 footprint scale. Bulletin of Surveying and Mapping, 2024, 62 (10): 32- 38. doi: 10.13474/j.cnki.11-2246.2024.1006
	何钊全, 尚　雪, 张铜会, 等. 近20年陕北黄土丘陵区景观生态风险时空变化及其冷热点格局. 生态学杂志, 2023, 42 (10): 2514- 2525. doi: 10.13292/j.1000-4890.202310.007
	He Z Q, Shang X, Zhang T H, et al. Spatiotemporal variations of landscape ecological risk and its cold-hot spot pattern in the loess hills of northern Shaanxi over the past 20 years. Chinese Journal of Ecology, 2023, 42 (10): 2514- 2525. doi: 10.13292/j.1000-4890.202310.007
	姬永杰, 张王菲. 森林地上生物量合成孔径雷达技术反演研究综述. 世界林业研究, 2022, 35 (3): 32- 39. doi: 10.13348/j.cnki.sjlyyj.2021.0113.y
	Ji Y J, Zhang W F. Research on retrieval of forest aboveground biomass by SAR technology. World Forestry Research, 2022, 35 (3): 32- 39. doi: 10.13348/j.cnki.sjlyyj.2021.0113.y
	蒋馥根, 孙　华, 李成杰, 等. 联合GF-6和Sentinel-2红边波段的森林地上生物量反演. 生态学报, 2021, 41 (20): 8222- 8236.
	Jiang F G, Sun H, Li C J, et al. Retrieving the forest aboveground biomass by combining the red edge bands of Sentinel-2 and GF-6. Acta Ecologica Sinica, 2021, 41 (20): 8222- 8236.
	雷宇宙, 毛学刚. 结合UAV-LiDAR和Sentinel-2的森林蓄积量估测. 森林工程, 2023, 39 (6): 46- 54.
	Lei Y Z, Mao X G. Integrating UAV-LiDAR and Sentinel-2 for growing stock volume estimation. Forest Engineering, 2023, 39 (6): 46- 54.
	李　梅, 刘清旺, 冯益明, 等. 无人机激光雷达人工林林分高估测模型分析. 遥感学报, 2022, 26 (12): 2665- 2678. doi: 10.11834/jrs.20210246
	Li M, Liu Q W, Feng Y M, et al. Analysis of estimation models of plantation stand heights using UAV LiDAR. National Remote Sensing Bulletin, 2022, 26 (12): 2665- 2678. doi: 10.11834/jrs.20210246
	刘美艳, 聂　胜, 王　成, 等. 基于ICESat-2和Sentinel-2A数据的森林蓄积量反演. 自然资源遥感, 2024, 36 (1): 210- 216. doi: 10.6046/zrzyyg.2022478
	Liu M Y, Nie S, Wang C, et al. Forest stock volume inversion based on ICESat-2 and Sentinel-2A data. Remote Sensing for Natural Resources, 2024, 36 (1): 210- 216. doi: 10.6046/zrzyyg.2022478
	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. doi: 10.11707/j.1001-7488.20170714
	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. doi: 10.11707/j.1001-7488.20170714
	蒙诗栎, 庞　勇, 张钟军, 等. WorldView-2纹理的森林地上生物量反演. 遥感学报, 2017, 21 (5): 812- 824. doi: 10.11834/jrs.20176083
	Meng S L, Pang Y, Zhang Z J, et al. Estimation of aboveground biomass in a temperate forest using texture information from WorldView-2. National Remote Sensing Bulletin, 2017, 21 (5): 812- 824. doi: 10.11834/jrs.20176083
	孟　鸽, 赵　旦, 许　聪, 等. 联合ICESat-2和GEDI星载激光雷达数据的森林地上生物量估算. 遥感学报, 2024, 28 (6): 1632- 1647. doi: 10.11834/jrs.20222120
	Meng G, Zhao D, Xu C, et al. Forest aboveground biomass estimation combining ICESat-2 and GEDI spaceborne LiDAR data. National Remote Sensing Bulletin, 2024, 28 (6): 1632- 1647. doi: 10.11834/jrs.20222120
	庞　勇, 李增元, 陈博伟, 等. 星载激光雷达森林探测进展及趋势. 上海航天, 2019, 36 (3): 20- 28. doi: 10.19328/j.cnki.1006-1630.2019.03.003
	Pang Y, Li Z Y, Chen B W, et al. Status and development of spaceborne LiDAR applications in forestry. Aerospace Shanghai, 2019, 36 (3): 20- 28. doi: 10.19328/j.cnki.1006-1630.2019.03.003
	全国森林资源标准化技术委员会. 2024,. 主要树种立木生物量模型与碳计量参数(GB/T 43648—2024,). 北京: 中国标准出版社.
	National Forest Resources Standardization Technical Committee. 2024,. Tree biomass models and related parameters to carbon accounting for major tree species(GB/T 43648—2024,). Beijing: Standards Press of China. ［in Chinese］
	饶　昕, 舒清态, 王继雄, 等. 基于ICESat-2/ATLAS的景东彝族自治县森林生物量估测研究. 西南林业大学学报, 2025, 45 (2): 159- 168. doi: 10.11929/j.swfu.202401017
	Rao X, Shu Q T, Wang J X, et al. Estimation of forest biomass based on ICESat-2/ATLAS data in Jingdong Yi Autonomous County. Journal of Southwest Forestry University, 2025, 45 (2): 159- 168. doi: 10.11929/j.swfu.202401017
	宋涵玥, 舒清态, 席　磊, 等. 基于星载ICESat-2/ATLAS数据的森林地上生物量估测. 农业工程学报, 2022, 38 (10): 191- 199. doi: 10.11975/j.issn.1002-6819.2022.10.023
	Song H Y, Shu Q T, Xi L, et al. Remote sensing estimation of forest above-ground biomass based on spaceborne LiDAR ICESat-2/ATLAS data. Transactions of the Chinese Society of Agricultural Engineering, 2022, 38 (10): 191- 199. doi: 10.11975/j.issn.1002-6819.2022.10.023
	宋柯馨, 蒋馥根, 胡宗达, 等. 西藏自治区草地地上生物量遥感反演研究. 生态学报, 2023, 43 (13): 5600- 5613. doi: 10.5846/stxb202206061593
	Song K X, Jiang F G, Hu Z D, et al. Remote sensing inversion of above-ground biomass of grassland in the Tibet Autonomous Region. Acta Ecologica Sinica, 2023, 43 (13): 5600- 5613. doi: 10.5846/stxb202206061593
	田晓敏, 张晓丽. 森林地上生物量遥感估算方法. 北京林业大学学报, 2021, 43 (8): 137- 148.
	Tian X M, Zhang X L. Estimation of forest aboveground biomass by remote sensing. Journal of Beijing Forestry University, 2021, 43 (8): 137- 148.
	杨泽至, 舒清态, 邱　霜, 等. 基于ICESat-2/ATLAS数据结合克里格插值进行区域尺度森林LAI估测. 云南大学学报, 2023, 45 (5): 1157- 1170. doi: 10.7540/j.ynu.20220509
	Yang Z Z, Shu Q T, Qiu S, et al. Regional-scale forest LAI estimation based on ICESat-2/ATLAS data combined with Kriging interpolation. Journal of Yunnan University, 2023, 45 (5): 1157- 1170. doi: 10.7540/j.ynu.20220509
	竹　亮. 2022,. 结合无人机LiDAR与Sentinel-2B影像的郁闭度估测. 哈尔滨: 东北林业大学.
	Zhu L. 2022,. Canopy cover estimation combined with UAV LiDAR and Sentinel-2B images. Harbin: Northeast Forestry University. ［in Chinese］
	周文武, 舒清态, 胥　丽, 等. 基于星载光子计数雷达数据的森林郁闭度估测模型优化. 中南林业科技大学学报, 2024, 44 (4): 84- 95, 105. doi: 10.14067/j.cnki.1673-923x.2024.04.010
	Zhou W W, Shu Q T, Xu L, et al. Optimization of forest canopy closure estimation model based on spaceborne photon counting LiDAR data. Journal of Central South University of Forestry & Technology, 2024, 44 (4): 84- 95, 105. doi: 10.14067/j.cnki.1673-923x.2024.04.010
	朱笑笑, 王　成, 习晓环, 等. ICESat-2星载光子计数激光雷达数据处理与应用研究进展. 红外与激光工程, 2020, 49 (11): 76- 85. doi: 10.3788/IRLA20200259
	Zhu X X, Wang C, Xi X H, et al. Research progress of ICESat-2/ATLAS data processing and applications. Infrared and Laser Engineering, 2020, 49 (11): 76- 85. doi: 10.3788/IRLA20200259
	Bhandari K, Srinet R, Nandy S. Forest height and aboveground biomass mapping by synergistic use of GEDI and Sentinel data using random forest algorithm in the Indian Himalayan region. Journal of the Indian Society of Remote Sensing, 2024, 52 (4): 857- 869. doi: 10.1007/s12524-023-01792-z
	Chen L, Ren C, Bao G, et al. Improved object-based estimation of forest aboveground biomass by integrating LiDAR data from GEDI and ICESat-2 with multi-sensor images in a heterogeneous mountainous region. Remote Sensing, 2022, 14 (12): 2743. doi: 10.3390/rs14122743
	Jiang F, Sun H, Chen E, et al. Above-ground biomass estimation for coniferous forests in northern China using regression Kriging and Landsat 9 images. Remote Sensing, 2022a, 14 (22): 5734. doi: 10.3390/rs14225734
	Jiang F, Sun H, Ma K, et al. Improving aboveground biomass estimation of natural forests on the Tibetan Plateau using spaceborne LiDAR and machine learning algorithms. Ecological Indicators, 2022b, 143, 109365. doi: 10.1016/j.ecolind.2022.109365
	Khan M N, Tan Y, He L, et al. From air to space: a comprehensive approach to optimizing aboveground biomass estimation on UAV-based datasets. Forests, 2025, 16 (2): 214. doi: 10.3390/f16020214
	Li W, Niu Z, Shang R, et al. High-resolution mapping of forest canopy height using machine learning by coupling ICESat-2 LiDAR with Sentinel-1, Sentinel-2 and Landsat-8 data. International Journal of Applied Earth Observation and Geoinformation, 2020, 92, 102163. doi: 10.1016/j.jag.2020.102163
	Li X, Lin H, Long J, et al. Mapping the growing stem volume of the coniferous plantations in north China using multispectral data from integrated GF-2 and Sentinel-2 images and an optimized feature variable selection method. Remote Sensing, 2021, 13 (14): 2740. doi: 10.3390/rs13142740
	Luo Y C, Qi S H, Liao K T, et al. Mapping the forest height by fusion of ICESat-2 and multi-source remote sensing imagery and topographic information: a case study in Jiangxi Province, China. Forests, 2023, 14 (3): 454. doi: 10.3390/f14030454
	Markus T, Neumann T, Martino A, et al. The ice, cloud, and land elevation Satellite-2 (ICESat-2): science requirements, concept, and implementation. Remote Sensing of Environment, 2017, 190, 260- 273. doi: 10.1016/j.rse.2016.12.029
	Narine L L, Popescu S C, Malambo L. Using ICESat-2 to estimate and map forest aboveground biomass: a first example. Remote Sensing, 2020, 12 (11): 1824. doi: 10.3390/rs12111824
	Neuenschwander A L, Magruder L A. Canopy and terrain height retrievals with ICESat-2: a first look. Remote Sensing, 2019, 11 (14): 1721. doi: 10.3390/rs11141721
	Ou G L, Lü Y Y, Xu H, et al. Improving forest aboveground biomass estimation of Pinus densata forest in Yunnan of southwest China by spatial regression using Landsat 8 images. Remote Sensing, 2019, 11 (23): 2750. doi: 10.3390/rs11232750
	Queinnec M, White J C, Coops N C. Comparing airborne and spaceborne photon-counting LiDAR canopy structural estimates across different boreal forest types. Remote Sensing of Environment, 2021, 262, 112510. doi: 10.1016/j.rse.2021.112510
	Rai N, Ma Q, Poudel K P, et al. 2024,. Evaluating the uncertainties in forest canopy height measurements using ICESat-2 Data. Journal of Remote Sensing, 2024,, 4: 0160.
	Tamiminia H, Salehi B, Mahdianpari M, et al. State-wide forest canopy height and aboveground biomass map for New York with 10 m resolution, integrating GEDI, Sentinel-1, and Sentinel-2 data. Ecological Informatics, 2024, 79, 102404. doi: 10.1016/j.ecoinf.2023.102404
	Unser M. Sum and difference histograms for texture classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986, 8 (1): 118- 125.
	Wang Y, Jia X, Chai G, et al. Improved estimation of aboveground biomass of regional coniferous forests integrating UAV-LiDAR strip data, Sentinel-1 and Sentinel-2 imageries. Plant Methods, 2023, 19 (1): 65. doi: 10.1186/s13007-023-01043-9
	Wang Y, Wang H, Wang C, et al. Co-Kriging-Guided interpolation for mapping forest aboveground biomass by integrating global ecosystem dynamics investigation and Sentinel-2 data. Remote Sensing, 2024, 16 (16): 2913. doi: 10.3390/rs16162913
	Xie Z, Chen Y, Lu D, et al. Classification of land cover, forest, and tree species classes with Ziyuan-3 multispectral and stereo data. Remote Sensing, 2019, 11 (2): 164. doi: 10.3390/rs11020164
	Zhen Z, Li X, Ma Y, et al. A hybrid method for forest aboveground biomass estimation: fusion of individual tree-and area-based approaches over northeast China. GIScience & Remote Sensing, 2025, 62 (1): 2497629.

数据类型 Data type	变量名称 Variable name	缩写 Abbreviation
无人机激光雷达 UAV LiDAR	密度特征变量Density metrics	den
	高度特征变量Elevation metrics	ele
	强度特征变量Intensity metrics	int
星载激光雷达 Spaceborne LiDAR	表观地表反射率Apparent surface reflectance	asr
	最小冠层高度Minimum height	h_min
	平均冠层高度Mean height	h_mean
	中位数冠层高度Median height	h_mid
	最大冠层高度Maximum height	h_max
	地形最合适高度Terrain height best fit	h_dem
	冠层高度百分位数Canopy height percentile	h_p (p=25, 50, 60, 70, 75, 80, 85, 90, 95, 98)

参数 Parameters	系数 Coefficient	显著性 Significance
常数Constant	–30.49	0.03
ele_p_80	8.88	0
ele_kurto	–8.94	0
ele_crr	134.37	0.01

数据源 Data source	组合 Combination	变量 Variables	决定系数 R²	均方根误差 RMSE/ ( t?hm^?2)	相对均方根误差 rRMSE (%)	估测精度 EA (%)
Sentinel-2	变量组合1 Combination 1	b2, EVI, b3, GDVI, b4	0.44	35.21	36.88	59.26
	变量组合2 Combination 2	b2, GLCM_3_ent, b3, GLCM_2_sec, GLCM_3_sec, GLCM_2_ent, GLCM_7_var, GLCM_5_ent, GLCM_1_var, GLCM_7_con	0.53	34.37	35.99	59.20
	变量组合3 Combination 3	b2, GLDV_8_sec, b3, GLDV_5_ent, GLDV_2_var, GLDV_2_ent, GLDV_4_ent, GLDV_2_mea, GLDV_7_var, GLDV_2_con, GLDV_4_sec	0.51	33.74	35.33	61.46
	变量组合4 Combination 4	b2, SADH_8_cor, SADH_1_sec, b3, SADH_6_var, SADH_7_con, SADH_3_sec, SADH_2_sec, SADH_4_cor, SADH_7_var, SADH_7_hom, SADH_4_mea	0.54	33.46	35.04	60.78
	变量组合5 Combination 5	b2, GLDV_8_var, GLCM_4_mea, GLDV_8_ent, GLCM_7_dis, b3, GLCM_2_ent, GLDV_8_sec, GLDV_2_var	0.56	33.02	34.58	60.71
Sentinel-2+ ICESat-2	变量组合6 Combination 6	h_85, NDVI, h_max, GLCM_3_ent, h_dem, GLCM_3_cor, GLCM_6_ent, GLDV_1_ent, h_70, h_mean, RENDVI_a, ARVI, GLCM_1_cor	0.74	27.44	28.74	69.32

[1]	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.
[2]	黄柳源,郑炎,程欣杰,曾伟生,徐晴,侯正阳. 面向非全覆盖遥感辅助数据的森林地上生物量估算[J]. 林业科学, 2025, 61(9): 22-38.
[3]	施正煌,侯方淼,张浩昆,黄国星. 新一轮集体林权制度改革对中国木质林产品出口边际增长的影响分析[J]. 林业科学, 2025, 61(9): 211-222.
[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]	袁泽雨,许行,任怡,许杨,庞建壮,吴小云,张翰遥,张志强. 2001—2021年“三北”工程区植被韧性分布特征及其驱动因素[J]. 林业科学, 2025, 61(7): 182-191.
[7]	杨菲菲,张王菲,赵磊,赵含,姬永杰,王梦金. 基于GF-1数据的二阶段遥感特征优选与森林地上生物量反演模型[J]. 林业科学, 2025, 61(4): 9-19.
[8]	葛晓宁,许新桥,张怀清,张京,杨杰,崔泽宇,傅汝饶,梁金洁,邹添华,王林龙,刘洋. 林木基因型-环境互作算法研究进展与思考[J]. 林业科学, 2025, 61(3): 1-15.
[9]	李倩,张帆,孟祥雪,吴小云,庞建壮,许行,张志强. 基于分解重构与机器学习的华北平原杨树人工林净碳交换模拟[J]. 林业科学, 2025, 61(12): 72-82.
[10]	潘丹,罗璐薏,季凯文,孔凡斌. 农村电子商务发展对林区内部收入差距与共同富裕的影响[J]. 林业科学, 2024, 60(5): 35-50.
[11]	沈琛琛,肖文发,朱建华,曾立雄,陈吉臻,黄志霖. 基于机器学习算法的华中天然林土壤有机碳特征与关键影响因子[J]. 林业科学, 2024, 60(3): 65-77.
[12]	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.
[13]	焦强英,韩宗甫,王炜烨,刘迪,潘鹏旭,李博,张念慈,王萍,陶金花,范萌. 基于多源数据和机器学习方法的大兴安岭地区雷击火驱动因子及火险预测模型[J]. 林业科学, 2023, 59(6): 74-87.
[14]	杨楠楠,白岩,姜苏译,杨春梅,徐凯宏. 基于AlexNet优化的板材材种识别方法[J]. 林业科学, 2022, 58(3): 149-158.
[15]	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.