基于无人机遥感多特征的单木地上生物量反演模型

doi:10.11707/j.1001-7488.LYKX20240390

摘要/Abstract

摘要：

目的: 针对北方森林，协同无人机激光雷达和无人机RGB影像进行单木地上生物量估测，以彰武县樟子松和杨树为研究对象，探究应用组合数据和单一数据对针、阔叶林单木地上生物量估测的影响，为彰武县防风固沙人工林单木地上生物量的精准预测提供技术参考。方法: 从LiDAR点云和基于RGB光学影像获取的数字正射影像图（DOM）中提取单木尺度高度、强度、密度、冠层结构、光谱、纹理和植被指数多特征，采用置换重要性（PI）和Boruta优选特征子集，结合地面实测单木地上生物量数据，使用随机森林（RF）、极端梯度提升树（XGBoost）和分类提升算法（CatBoost）3种典型机器学习方法构建樟子松和杨树地上生物量估测模型，对仅用LiDAR数据、仅用DOM数据以及联合二者的建模结果进行比较。结果: 1）点云高度和冠层结构是估测2个树种单木地上生物量的关键特征；纹理特征仅对樟子松地上生物量估测产生积极影响。2）对于樟子松，基于组合数据的单木地上生物量估测精度最高，优于单一LiDAR和单一RGB影像；3种数据集的最优模型分别为ALL-PI-XGBoost、LiDAR-PI-XGBoost和DOM-PI-RF，测试集R²分别为0.77、0.69、0.67，RMSE分别为10.94、12.75、13.16 kg·plant^?1。对于杨树，基于组合数据和单一LiDAR数据的单木地上生物量估测精度相当，且优于单一RGB影像；3种数据集的最优模型分别为ALL-PI-XGBoost、LiDAR-Boruta-XGBoost和DOM-Boruta-CatBoost，测试集R²分别为0.85、0.85、0.59，RMSE分别为17.63、17.11、28.99 kg·plant^?1。结论: 基于低成本无人机遥感技术获取的高密度点云和高分辨率影像可以实现彰武县防风固沙人工林单木地上生物量高精度、快速且无损估测；应用组合数据和单一数据对针、阔叶林单木地上生物量估测有不同影响，组合数据可以显著提高樟子松单木地上生物量估测精度。

关键词: 无人机激光雷达, 无人机光学影像, 单木尺度, 地上生物量, 机器学习

Abstract:

Objective: The aim of this study is to estimate aboveground biomass (AGB) at individual tree scale in northern forests by synergistically utilizing UAV-LiDAR and UAV-RGB data. Pinus sylvestris var. mongolica and Populus. in Zhangwu County were used as the research object to investigate the influence of using combined data versus single data on AGB estimation in coniferous and broadleaf forests. The findings are to provide technical references for precise prediction of AGB at individual tree scale in windbreak and sand fixation plantations in Zhangwu County. Method: Multiple features at individual tree scale, including height, intensity, density, crown structure, spectrum, texture and vegetation index, were extracted from LiDAR point clouds and digital orthophoto map (DOM) derived from RGB optical imagery. Permutation importance (PI) and Boruta methods were used to select feature subsets. Combining these features with the aboveground biomass (AGB) data of individual trees calculated from field-measured tree height and diameter at breast height, three typical machine learning methods, including random forest (RF), extreme gradient boosting (XGBoost), and categorical features gradient boosting (CatBoost), were adopted to construct biomass estimation models for the two tree species, P. sylvestris var. mongolica and Populus. The modeling results using only LiDAR data, only DOM data, and a combination of both methods were compared. Result: 1) Point cloud height and crown structure were identified as key features for AGB estimation at individual tree scale for both species, whereas texture features only positively influenced the estimation of AGB for P. sylvestris var. mongolica. 2) For P. sylvestris var. mongolica, the estimation accuracy of AGB at individual tree scale based on combined data was highest, outperforming models based on single LiDAR and RGB imagery. The optimal models for the three datasets were ALL-PI-XGBoost, LiDAR-PI-XGBoost, and DOM-PI-RF, with R² of 0.77, 0.69, and 0.67, and RMSE of 10.94, 12.75, and 13.16 kg·plant^?1, respectively. For Populus, the estimation accuracy of AGB at individual tree scale was comparable when using combined and single LiDAR data, and both outperformed the model based on single RGB imagery. The optimal models for the three datasets were ALL-PI-XGBoost, LiDAR-Boruta-XGBoost, and DOM-Boruta-CatBoost, with R² of 0.85, 0.85, and 0.59, and RMSE of 17.63, 17.11, and 28.99 kg·plant^?1, respectively. Conclusion: The high-density point clouds and high-resolution images obtained from two types of low-cost UAV remote sensing technology can achieve high-precision, fast, and non-destructive estimation of individual tree aboveground biomass in the windbreak and sand fixation plantations in Zhangwu County. The use of combined data versus single data has different impacts on AGB estimation at individual tree scale in coniferous and broadleaf forests, with combined data significantly improving the accuracy of AGB estimation for P. sylvestris var. mongolica.

Key words: UAV-LiDAR, UAV optical imagery, individual tree scale, aboveground biomass (AGB), machine learning

中图分类号:

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.

Yujiao Zhang,Hengqian Zhao,Hancong Fu,Ge Liu,Xiadan Huangfu,Xuanqi Liu. Inversion Model of Aboveground Biomass at Individual Tree Scale Based on the Multiple Features of UAV Remote Sensing[J]. Scientia Silvae Sinicae, 2025, 61(8): 129-141.

图/表 13

图1

图2

表1

图3

表2

从UAV-LiDAR点云数据提取的特征"

特征类型 Feature type	特征缩写 Feature abbreviation	描述 Description	特征类型 Feature type	特征缩写 Feature abbreviation	描述 Description
点云高度特征 Point cloud height feature	H_P01-95th	点云高度百分位数Height percentiles	点云强度特征 Point cloud intensity feature	I_P01-95th	点云强度百分位数Intensity percentiles
	H_CRR	冠层起伏率Canopy relief rate		I_IQ	点云强度百分位数四分位数间距Intensity percentile interquartile range
	H_IQ	点云高度百分位数四分位数间距 Height percentile interquartile range		I_AAD	点云强度平均绝对偏差Mean absolute deviation
	H_CV	点云高度变异系数Variable coefficient		I_CV	点云强度变异系数Variable coefficient
	H_KURT	点云高度峰度Kurtosis		I_KURT	点云强度峰度Kurtosis
	H_SKE	点云高度偏斜度Skewness		I_SKE	点云强度偏斜度Skewness
	H_MAX	点云高度最大值Max.		I_MAX	点云强度最大值Max.
	H_MIN	点云高度最小值Min.		I_MIN	点云强度最小值Min.
	H_MEAN	点云高度平均值Mean		I_MEAN	点云强度平均值Mean
	H_ MEDIAN	点云高度中位数Median		I_ MEDIAN	点云强度中位数Median
	H_STD	点云高度标准差Standard deviation		I_STD	点云强度标准差 Standard deviation
	H_V	点云高度方差Variance		I_V	点云强度方差Variance
	H_MAD	点云高度中位数绝对偏差 Median absolute deviation		I_MAD	点云强度中位数绝对偏差Median absolute deviation
	H_SQRT	点云高度2次幂平均2nd power average	点云冠层结构特征 Canopy structure feature of point cloud	TH	树高Tree height
	H_CURT	点云高度3次幂平均3nd power average		CD	冠径Canopy diameter
	H_AIH_IQ	点云累积高度百分位数四分位数间距 Interquartile range of accumulate height percentile		CD	冠径Canopy diameter
点云密度特征 Point cloud density feature	D_1-10	将点云数据从低到高分成10个相同高度的切片，每层回波数的比例就是相应的密度特征Divide the point cloud data into 10 slices of the same height from low to high， and the proportion of echoes in each layer is the corresponding density feature		CA	树冠面积Canopy area
点云密度特征 Point cloud density feature	D_1-10			CV	树冠体积Canopy volume

表2

表3

表4

图4

图5

图6

表5

图7

图8

参考文献 0

	包栎炀, 王祥军, 李少达, 等. 基于无人机LiDAR的橡胶树单木地上生物量估测. 热带作物学报, 2023, 44 (6): 1266- 1275. doi: 10.3969/j.issn.1000-2561.2023.06.020
	Bao L Y, Wang X J, Li S D, et al. Estimation of individual tree above-ground biomass of rubber tree based on UAV-LiDAR. Chinese Journal of Tropical Crops, 2023, 44 (6): 1266- 1275. doi: 10.3969/j.issn.1000-2561.2023.06.020
	戴莉莉, 李海涛, 顾海燕, 等. 特征优选下的遥感影像面向对象分类规则构建. 测绘科学, 2019, 44 (2): 26- 32.
	Dai L L, Li H T, Gu H Y, et al. Construction of object-based image classification rules for remote sensing images supported by feature optimization. Science of Surveying and Mapping, 2019, 44 (2): 26- 32.
	耿　林, 李明泽, 范文义, 等. 基于机载LiDAR的单木结构参数及林分有效冠的提取. 林业科学, 2018, 54 (7): 62- 72. doi: 10.11707/j.1001-7488.20180707
	Geng L, Li M Z, Fan W Y, et al. Individual tree structure parameters and effective crown of the stand extraction base on airborn LiDAR data. Scientia Silvae Sinicae, 2018, 54 (7): 62- 72. doi: 10.11707/j.1001-7488.20180707
	黄金龙, 居为民, 郑　光, 等. 基于高分辨率遥感影像的森林地上生物量估算. 生态学报, 2013, 33 (20): 6497- 6508. doi: 10.5846/stxb201212211841
	Huang J L, Ju W M, Zheng G, et al. Estimation of forest aboveground biomass using high spatial resolution remote sensing imagery. Acta Ecologica Sinica, 2013, 33 (20): 6497- 6508. doi: 10.5846/stxb201212211841
	菅永峰, 韩泽民, 黄光体, 等. 基于高分辨率遥感影像的北亚热带森林生物量反演. 生态学报, 2021, 41 (6): 2161- 2169.
	Jian Y F, Han Z M, Huang G T, et al. Estimation of forest biomass using high spatial resolution remote sensing imagery in north subtropical forests. Acta Ecologica Sinica, 2021, 41 (6): 2161- 2169.
	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.
	李　丹. 2018. 基于数字航空摄影数据的森林参数反演估测研究. 北京: 中国科学院大学(中国科学院遥感与数字地球研究所).
	Li D. 2018. Retrieval and estimation research of forest parameters based on digital aerial photograph data. Beijing: University of Chinese Academy of Sciences(Institute of Remote Sensing and Digital Earth Chinese Academy of Sciences. ［in Chinese ］
	李　旺, 牛　铮, 王　成, 等. 机载LiDAR数据估算样地和单木尺度森林地上生物量. 遥感学报, 2015, 19 (4): 669- 679.
	Li W, Niu Z, Wang C, et al. Forest above-ground biomass estimation at plot and tree levels using airborne Li DAR data. Journal of Remote Sensing, 2015, 19 (4): 669- 679.
	孙　钊, 谢运鸿, 王宝莹, 等. 基于无人机多维数据集的森林地上生物量估测模型研究. 农业机械学报, 2024, 55 (6): 186- 195,236. doi: 10.6041/j.issn.1000-1298.2024.06.019
	Sun Z, Xie Y H, Wang B Y, et al. Development of forest aboveground biomass estimation model based on multidimensional dataset of UAV. Transactions of the Chinese Society for Agricultural Machinery, 2024, 55 (6): 186- 195,236. doi: 10.6041/j.issn.1000-1298.2024.06.019
	王　嫚. 2023. 基于贝叶斯方法和多源遥感的落叶松人工林多尺度地上生物量估算. 哈尔滨: 东北林业大学.
	Wang M. 2023. The estimation of aboveground biomass of larix olgensis plantation based on Bayesian approach and multi-source remote sensing data. Harbin: Northeast Forestry University.［in Chinese］
	武晓康. 2023. 基于UAV LiDAR的单木生物量反演研究. 桂林: 桂林理工大学.
	Wu X K. 2023. Research on individual tree biomass extraction based on UAV LiDAR. Guilin: Guilin University of Technology. ［ in Chinese］.
	武晓康, 王浩宇, 冯宝坤, 等. 基于无人机LiDAR的单木生物量估测. 科学技术与工程, 2022, 22 (34): 15028- 15035. doi: 10.3969/j.issn.1671-1815.2022.34.006
	Wu X K, Wang H Y, Feng B K, et al. Individual tree biomass estimation based on UAV airborne LiDAR. Science Technology and Engineering, 2022, 22 (34): 15028- 15035. doi: 10.3969/j.issn.1671-1815.2022.34.006
	徐　婷, 曹　林, 申　鑫, 等. 基于机载激光雷达与Landsat 8 OLI数据的亚热带森林生物量估算. 植物生态学报, 2015, 39 (4): 309- 321. doi: 10.17521/cjpe.2015.0030
	Xu T, Cao L, Shen X, et al. Estimates of subtropical forest biomass based on airborne LiDAR and Landsat 8 OLI data. Chinese Journal of Plant Ecology, 2015, 39 (4): 309- 321. doi: 10.17521/cjpe.2015.0030
	杨晓慧, 吴金卓, 刘浩然, 等. 基于UAV-LiDAR的人工林林分郁闭度估测. 林业科学, 2023, 59 (8): 12- 21. doi: 10.11707/j.1001-7488.LYKX20210955
	Yang X H, Wu J Z, Liu H R, et al. Estimation on canopy closure for plantation forests based on UAV-LiDAR. Scientia Silvae Sinicae, 2023, 59 (8): 12- 21. doi: 10.11707/j.1001-7488.LYKX20210955
	于海洋, 谢赛飞, 郭灵辉, 等. 融合光谱和空间特征的土壤重金属含量极端随机树估算. 农业机械学报, 2022, 53 (8): 231- 239.
	Yu H Y, Xie S F, Guo L H, et al. Extremely randomized trees estimation of soil heavy metal content by fusing spectra and spatial features. Transactions of the Chinese Society for Agricultural Machinery, 2022, 53 (8): 231- 239.
	钟　浩. 2024. 联合无人机多源遥感数据单木生物量反演研究. 哈尔滨: 东北林业大学.
	Zhong H. 2024. Study on biomass inversion of single tree from multi-source remote sensing data of UAV. Harbin: Northeast Forestry University. ［in Chinese］.
	周　榕. 2023. 机载与地基激光点云融合及林木参数提取研究. 长沙: 中南林业科技大学.
	Zhou R. 2023. Study on fusion of airborne and ground-based laser point clouds and extraction of forest parameters. Changsha: Central South University of Forestry & Technology. ［in Chinese］.
	Dalla Corte A P, Souza D V, Rex F E, et al. Forest inventory with high-density UAV-lidar: machine learning approaches for predicting individual tree attributes. Computers and Electronics in Agriculture, 2020, 179, 105815. doi: 10.1016/j.compag.2020.105815
	Dalponte M, Frizzera L, Orka HO, et al. Predicting stem diameters and aboveground biomass of individual trees using remote sensing data. Ecological Indicators, 2018, 85, 367- 376. doi: 10.1016/j.ecolind.2017.10.066
	Jin S C, Su Y J, Gao S, et al. The transferability of random forest in canopy height estimation from multi-source remote sensing data. Remote Sensing, 2018, 10 (8): 1183. doi: 10.3390/rs10081183
	Juan-Ovejero R, Elghouat A, Navarro C J, et al. Estimation of aboveground biomass and carbon stocks of Quercus ilex L. saplings using UAV-derived RGB imagery. Annals of Forest Science, 2023, 80 (1): 44. doi: 10.1186/s13595-023-01210-x
	Jucker T, Caspersen J, Chave J, et al. Allometric equations for integrating remote sensing imagery into forest monitoring programmes. Global Change Biology, 2017, 23 (1): 177- 190. doi: 10.1111/gcb.13388
	Liang Y Y, Kou W L, Lai H Y, et al. Improved estimation of aboveground biomass in rubber plantations by fusing spectral and textural information from UAV-based RGB imagery. Ecological Indicators, 2022, 142, 109286. doi: 10.1016/j.ecolind.2022.109286
	Lin J Y, Chen D C, Wu W J, et al. Estimating aboveground biomass of urban forest trees with dual-source UAV acquired point clouds. Urban Forestry & Urban Greening, 2022, 69, 127521.
	Liu Y, Lei P, You Q X, et al. Individual tree aboveground biomass estimation based on UAV stereo images in a Eucalyptus plantation. Forests, 2023, 14 (9): 1748. doi: 10.3390/f14091748
	Malek S, Miglietta F, Gobakken T, et al. Prediction of stem diameter and biomass at individual tree crown level with advanced machine learning techniques. IForest - Biogeosciences and Forestry, 2019, 12 (3): 323- 329. doi: 10.3832/ifor2980-012
	Mao Z H, Lu Z, Wu Y J, et al. 2023. DBH estimation for individual tree: two-dimensional images or three-dimensional point clouds? Remote Sensing, 15(16): 4116.
	Sun Z, Wang Y F, Ding Z D, et al. Individual tree segmentation and biomass estimation based on UAV Digital aerial photograph. Journal of Mountain Science, 2023, 20 (3): 724- 737. doi: 10.1007/s11629-022-7563-7
	Tian Y C, Huang H, Zhou G Q, et al. Aboveground mangrove biomass estimation in Beibu Gulf using machine learning and UAV remote sensing. Science of the Total Environment, 2021, 781, 146816. doi: 10.1016/j.scitotenv.2021.146816
	Xu D D, Wang H B, Xu W X, et al. LiDAR applications to estimate forest biomass at individual tree scale: opportunities, challenges and future perspectives. Forests, 2021, 12 (5): 550. doi: 10.3390/f12050550
	Yan M, Xia Y H, Yang X Y, et al. Biomass estimation of subtropical arboreal forest at single tree scale based on feature fusion of airborne LiDAR data and aerial images. Sustainability, 2023, 15 (2): 1676. doi: 10.3390/su15021676

样地编号 Plot code	树种 Tree species	株数 Plant number	平均胸径 Mean DBH/cm	平均树高 Mean height/m
1	樟子松 Pinus sylvestris var. mongolica	33	22.6	9.4
2	樟子松 Pinus sylvestris var. mongolica	76	16.8	9.4
3	杨树 Populus	24	21.1	13.9
4	杨树 Populus	36	24.2	14.1
5	樟子松 Pinus sylvestris var. mongolica	41	17.5	7.5

模型 Model	缩写 Abbreviations	超参数 Hyperparameter	数值范围 Range of values
随机森林 Random forest	RF	n_estimators max_depth min_samples_split	[50， 300， 10] [3，10，1] [2， 10， 1]
极端梯度提升树 Extreme gradient boosting	XGBoost	learning_rate max_depth min_child_weight	[0.01， 0.1， 0.01] [2，10，1] [1，10，1]
分类提升算法 Categorical features gradient boosting	CatBoost	iterations learning_rate depth	[20，300， 10] [0.01，0.2，0.01] [2，10，1]

样地编号 Plot code	正确分割数量 Number of correct segments/plant	欠分割数量 Number of under segments/plant	过分割数量 Number of false segments/plant	召回率 Recall（r）	准确率 Precision（p）	调和值 F-score（F）
1	21	6	6	0.78	0.78	0.78
2	38	29	8	0.57	0.82	0.67
3	24	0	0	1	1	1
4	27	7	2	0.79	0.93	0.85
5	25	7	9	0.78	0.73	0.75

树种 Tree species	模型 Model	数据Data
		LiDAR				DOM				ALL（LiDAR+DOM）
		训练集 Training set		测试集 Test set		训练集 Training set		测试集 Test set		训练集 Training set		测试集 Test set
		R²	RMSE	R²	RMSE	R²	RMSE	R²	RMSE	R²	RMSE	R²	RMSE
樟子松 Pinus sylvestris var. mongolica	PI- RF	0.94	6.25	0.67	13.24	0.77	12.17	0.67^**	13.16	0.90	7.97	0.76	11.09
	Boruta-RF	0.91	7.42	0.68	12.91	0.74	12.90	0.66	13.21	0.91	7.63	0.76	11.27
	PI-CatBoost	0.81	11.21	0.63	13.99	0.86	9.49	0.64	13.61	0.90	7.74	0.69	12.80
	Boruta-CatBoost	0.83	10.55	0.68	12.92	0.87	9.01	0.60	14.53	0.86	9.47	0.69	12.74
	PI-XGBoost	0.99^*	2.62	0.69^*	12.75	0.99^**	1.27	0.44	17.13	0.95	5.58	0.77^***	10.94
	Boruta-XGBoost	0.96	4.97	0.63	13.88	0.93	6.41	0.52	15.84	0.95^***	5.44	0.72	12.29
杨树 Populus	PI- RF	0.95	8.31	0.83	18.81	0.94	8.94	0.52	31.15	0.94	8.99	0.82	19.18
	Boruta-RF	0.89	12.26	0.81	19.64	0.93	9.85	0.54	30.65	0.88	12.62	0.82	18.90
	PI-CatBoost	0.94	8.83	0.80	19.85	0.99	3.42	0.48	32.60	0.99	2.04	0.84	17.81
	Boruta-CatBoost	0.95^*	8.16	0.75	22.37	0.99^**	0.47	0.59^**	28.99	0.99^***	0.01	0.64	26.99
	PI-XGBoost	0.94	8.55	0.81	19.58	0.99	3.24	0.55	30.16	0.97	5.78	0.85^***	17.63
	Boruta-XGBoost	0.94	8.40	0.85^*	17.11	0.98	4.71	0.54	30.52	0.91	10.85	0.82	19.05

[1]	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.
[2]	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.
[3]	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.
[4]	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.
[5]	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.
[6]	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.
[7]	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.
[8]	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.
[9]	王薇,赵涵,黄欣,侯卓梁,姜在民,蔡靖. 白杨无性系叶片水力及经济性状与生物量的关系[J]. 林业科学, 2023, 59(10): 89-98.
[10]	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.
[11]	石永磊,王志慧,李世明,李春意,肖培青,张攀,常晓格. 基于光学遥感的稀疏乔灌木地上部分生物量反演方法[J]. 林业科学, 2022, 58(2): 13-22.
[12]	陈星京,冯林艳,张宇超,刘清旺,杨朝晖,符利勇,白晋华. 基于机载激光雷达的崇礼冬奥核心区林分地上生物量反演[J]. 林业科学, 2022, 58(10): 35-46.
[13]	丁家祺,黄文丽,刘迎春,胡杨. 基于机器学习和多源数据的湘西北森林地上生物量估测[J]. 林业科学, 2021, 57(10): 36-48.
[14]	庞荣荣,彭潔莹,闫琰. 太白山次生锐齿栎林地上生物量影响因素[J]. 林业科学, 2021, 57(10): 157-165.
[15]	周律,欧光龙,王俊峰,胥辉. 基于空间回归模型的思茅松林生物量遥感估测及光饱和点确定[J]. 林业科学, 2020, 56(3): 38-47.