基于坡度分级的旺业甸林场森林蓄积量反演

高佳乐; 蒋馥根; 龙依; 陈帅; 孙华

doi:10.12302/j.issn.1000-2006.202410006

基于坡度分级的旺业甸林场森林蓄积量反演

高佳乐, 蒋馥根, 龙依, 陈帅, 孙华

南京林业大学学报（自然科学版） ›› 2025, Vol. 49 ›› Issue (6) : 13-25.

PDF(5119 KB)

国家林草科技领军期刊
中国精品科技期刊
中国高校百佳科技期刊
江苏省新闻出版政府奖期刊奖
RCCSE林学权威期刊（A+）
CSCD核心期刊
Scopus数据库收录期刊
中文核心期刊
SCD核心期刊

作者加群：102861116

微信公众号：南京林业大学学报

高级检索

PDF(5119 KB)

南京林业大学学报（自然科学版） ›› 2025, Vol. 49 ›› Issue (6) : 13-25. DOI: 10.12302/j.issn.1000-2006.202410006

专题报道Ⅰ: 第十四届海峡两岸森林经理研讨会专题（执行主编李凤日曹林）

基于坡度分级的旺业甸林场森林蓄积量反演

作者信息 +

Inversion of forest stock volume in Wangyedian Forest Farm based on slope classification

Author information +

文章历史 +

摘要

【目的】通过构建多源遥感数据集并考虑不同坡度分级的地形校正对于估测的影响,以提升森林蓄积量反演精度,为地形复杂区域的森林蓄积量遥感估算提供参考。【方法】基于Sentinel-2和GF-6遥感影像,结合旺业甸林场野外实测数据,构建多个传统非参数模型和集成学习模型对内蒙古赤峰旺业甸林场森林蓄积量进行反演。为降低地形波动对反演的影响,分别利用Teillet、VECA和SCS+C方法通过坡度分级对影像进行地形校正以提高森林蓄积量反演精度。利用Boruta法和SRF法对不同数据源特征变量进行筛选。【结果】集成学习算法的估测效果整体优于传统非参数模型,其中随机森林模型在所有模型中表现最佳。与单一数据源构建的随机森林模型相比,联合Sentinel-2和GF-6数据源后森林蓄积量反演效果有所提升,基于Boruta法的联合数据源较单一Sentinet和GF-6数据源模型均方根误差(RMSE)分别降低了7.41%和9.61%。经过基于坡度分级的地形校正后,模型RMSE降低了18.48%,森林蓄积量空间分布与旺业甸林场实际情况一致性较高。【结论】以Sentinel-2和GF-6为数据源,构建的集成学习算法可更有效地对森林蓄积量进行估测,基于坡度分级的地形校正有效提高了森林蓄积量估测精度。

Abstract

【Objective】To improve the accuracy of forest stock volume inversion and provide a reference for remote sensing estimation of forest stock volume in areas with complex terrain, this study aims to construct a multi-source remote sensing dataset and examine the impact of terrain correction at different slope classifications on the estimation results.【Method】Using Sentinel-2 and GF-6 remote sensing images, combined with field measurement data from Wangyedian Forest Farm in Chifeng, Inner Mongolia, this study constructed multiple traditional non-parametric models and ensemble learning models to invert the forest stock volume of Wangyedian Forest Farm. To reduce the influence of terrain fluctuations on inversion results, terrain corrections were performed on the images using the Teillet, VECA, and SCS+C methods at different slope classifications to improve the accuracy of forest stock volume inversion.【Result】The estimation performance of ensemble learning algorithms was generally superior to that of traditional non-parametric models, with the random forest model demonstrating the best performance among all models. Compared with the random forest model constructed using a single data source, combining Sentinel-2 and GF-6 data improved the inversion results of forest stock volume inversion performance, reducing the root mean square error (RMSE) of the models using Boruta by 7.41% and 9.61%, respectively. After terrain correction based on slope classification, the RMSE of the model decreased by 18.48%, and the spatial distribution of forest stock volume showed a high degree of consistency with the actual situation in Wangyedian Forest Farm.【Conclusion】Using Sentinel-2 and GF-6 as data sources, the constructed ensemble learning algorithms can more effectively estimate forest stock volume. Terrain correction based on slope classification significantly improves the estimation accuracy of forest stock volume.

导出引用

高佳乐, 蒋馥根, 龙依, 等. 基于坡度分级的旺业甸林场森林蓄积量反演[J]. 南京林业大学学报（自然科学版）. 2025, 49(6): 13-25 https://doi.org/10.12302/j.issn.1000-2006.202410006

GAO Jiale, JIANG Fugen, LONG Yi, et al. Inversion of forest stock volume in Wangyedian Forest Farm based on slope classification[J]. Journal of Nanjing Forestry University (Natural Sciences Edition）. 2025, 49(6): 13-25 https://doi.org/10.12302/j.issn.1000-2006.202410006

中图分类号： S758.51;TP751

参考文献

列表( 原文顺序 | 文献年度倒序 | 文中引用次数倒序 ) 可视化分析

[1]

周友锋, 谢秉楼, 李明诗. 基于随机森林协同克里金法的区域森林地上生物量制图——以粤北森林为例[J]. 南京林业大学学报(自然科学版), 2024, 48(1):169-178.

ZHOU

Y F

, XIE

B L

, LI

M S

. Mapping regional forest aboveground biomass from random forest Co-Kriging approach: a case study from north Guangdong[J]. Journal of Nanjing Forestry University (Natural Sciences Edition), 2024, 48(1):169-178.DOI: 10.12302/j.issn.1000-2006.202202015.

本文引用 [1]

[2]	周小成, 黄婷婷, 李媛, 等. 结合遥感林龄因子的亚热带森林蓄积量估算方法[J]. 林业科学, 2023, 59(4):88-99. ZHOU X C, HUANG T T, LI Y, et al. A method for estimating subtropical forest stock by combining remotely sensed forest age factors[J]. Scientia Silvae Sinicae, 2023, 59(4):88-99.DOI: 10.11707/j.1001-7488.LYKX20210712. 本文引用 [1]

[3]

巨一琳, 姬永杰, 黄继茂, 等. 联合LiDAR和多光谱数据森林地上生物量反演研究[J]. 南京林业大学学报(自然科学版), 2022, 46(1):58-68.

Y L

, JI

Y J

, HUANG

J M

, et al. Inversion of forest aboveground biomass using combination of LiDAR and multispectral data[J]. Journal of Nanjing Forestry University (Natural Sciences Edition), 2022, 46(1):58-68.DOI: 10.12302/j.issn.1000-2006.202109029.

本文引用 [1]

[4]

LIU

Z H

, LONG

J P

, LIN

, et al. Mapping and analyzing the spatiotemporal dynamics of forest aboveground biomass in the ChangZhuTan urban agglomeration using a time series of Landsat images and meteorological data from 2010 to 2020[J]. Science of The Total Environment, 2024,944:173940.DOI: 10.1016/j.scitotenv.2024.173940.

本文引用 [1]

[5]	马永军, 张艺, 王广来, 等. 改进UNet++的遥感影像森林变化检测方法[J]. 森林与环境学报, 2024, 44(3):317-327. MA Y J, ZHANG Y, WANG G L, et al. Improved forest change detection method for remote sensing imagery using UNet++[J]. Journal of Forest and Environment, 2024, 44(3):317-327.DOI: 10.13324/j.cnki.jfcf.2024.03.012. 本文引用 [3]

[6]	CHEN J H, XU H Q. Analysis of the effectiveness of the red-edge bands of GF-6 imagery in forest health discrimination[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17:5621-5636.DOI: 10.1109/JSTARS.2024.3367320. 本文引用 [3]

[7]	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[J]. Acta Ecologica Sinica, 2021, 41(20):8222-8236.DOI: 10.5846/stxb202012173204. 本文引用 [2]

[8]	YIN H, TAN B, FRANTZ D, et al. Integrated topographic corrections improve forest mapping using Landsat imagery[J]. International Journal of Applied Earth Observation and Geoinformation, 2022,108:102716.DOI: 10.1016/j.jag.2022.102716. 本文引用 [2]

[9]	CHEN A, WANG X, ZHANG M, et al. Fusion of LiDAR and multispectral data for aboveground biomass estimation in mountain grassland[J]. Remote Sensing, 2023, 15(2):405.DOI: 10.3390/rs15020405. 本文引用 [2]

[10]	LI M, IM J, BEIER C. Machine learning approaches for forest classification and change analysis using multi-temporal Landsat TM images over Huntington Wildlife Forest[J]. GIScience & Remote Sensing, 2013, 50(4):361-384.DOI: 10.1080/15481603.2013.819161. 本文引用 [2]

[11]

PENG

S F

, WANG

Z H

, LU

X P

, et al. Hybrid inversion of radiative transfer models based on topographically corrected Landsat surface reflectance improves leaf area index and aboveground biomass retrievals of grassland on the hilly Loess Plateau[J]. International Journal of Digital Earth, 2024, 17(1):2316840.DOI: 10.1080/17538947.2024.2316840.

本文引用 [2]

[12]	高永年, 张万昌. 遥感影像地形校正研究进展及其比较实验[J]. 地理研究, 2008, 27(2):467-477,484. GAO Y N, ZHANG W C. Comparison test and research progress of topographic correction on remotely sensed data[J]. Geographical Research, 2008, 27(2):467-477,484.DOI: 10.3321/j.issn:1000-0585.2008.02.024. 本文引用 [3]

[13]	SOENEN S A, PEDDLE D R, COBURN C A. SCS+C:a modified Sun-canopy-sensor topographic correction in forested terrain[J]. IEEE Transactions on Geoscience and Remote Sensing, 2005, 43(9):2148-2159.DOI: 10.1109/TGRS.2005.852480. 本文引用 [3]

[14]	TEILLET P M, GUINDON B, GOODENOUGH D G. On the slope-aspect correction of multispectral scanner data[J]. Canadian Journal of Remote Sensing, 1982, 8(2):84-106.DOI: 10.1080/07038992.1982.10855028. 本文引用 [3]

[15]	胡宇美, 马理辉, 李蕊, 等. 黄土高原地区森林生态系统地下生物量影响因素[J]. 生态学报, 2021, 41(21):8643-8653. HU Y M, MA L H, LI R, et al. Factor analysis of underground biomass in forest ecosystem on the Loess Plateau[J]. Acta Ecologica Sinica, 2021, 41(21):8643-8653.DOI: 10.5846/stxb202008062046. 本文引用 [1]

[16]	刘琪璟. 中国立木材积表[M]. 北京: 中国林业出版社, 2017. LIU Q J. Tree volume tables of China[M]. Beijing: China Forestry Publishing House, 2017. 本文引用 [1]

[17]	CHEN C, YUAN X P, GAN S, et al. A new vegetation index based on UAV for extracting plateau vegetation information[J]. International Journal of Applied Earth Observation and Geoinformation, 2024,128:103668.DOI: 10.1016/j.jag.2024.103668. 本文引用 [1]

[18]	LI Q Y, LIN H, LONG J P, et al. Mapping forest stock volume using phenological features derived from time-serial Sentinel-2 imagery in planted larch[J]. Forests, 2024, 15(6):995.DOI: 10.3390/f15060995. 本文引用 [2]

[19]	JIANG F G, KUTIA M, SARKISSIAN A J, et al. Estimating the growing stem volume of coniferous plantations based on random forest using an optimized variable selection method[J]. Sensors, 2020, 20(24):7248.DOI: 10.3390/s20247248. 本文引用 [6]

[20]	SCHNEIDER P, ROBERTS D A, KYRIAKIDIS P C. A VARI-based relative greenness from MODIS data for computing the Fire Potential index[J]. Remote Sensing of Environment, 2008, 112(3):1151-1167.DOI: 10.1016/j.rse.2007.07.010. 本文引用 [1]

[21]	SIMS D A, GAMON J A. Relationships between leaf pigment content and spectral reflectance across a wide range of species,leaf structures and developmental stages[J]. Remote Sensing of Environment, 2002, 81(2-3):337-354.DOI: 10.1016/S0034-4257(02)00010-X. 本文引用 [1]

[22]	XU D W, WANG C, CHEN J, et al. The superiority of the normalized difference phenology index (NDPI) for estimating grassland aboveground fresh biomass[J]. Remote Sensing of Environment, 2021,264:112578.DOI: 10.1016/j.rse.2021.112578. 本文引用 [1]

[23]	ZHANG T, GUAN H O, MA X D, et al. Drought recognition based on feature extraction of multispectral images for the soybean canopy[J]. Ecological Informatics, 2023,77:102248.DOI: 10.1016/j.ecoinf.2023.102248. 本文引用 [1]

[24]	SUN H, WANG Q, WANG G X, et al. Optimizing kNN for mapping vegetation cover of arid and semi-arid areas using landsat images[J]. Remote Sensing, 2018, 10(8):1248.DOI: 10.3390/rs10081248. 本文引用 [1]

[25]	BARALDI A, PARMIGGIANI F. An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters[J]. IEEE Transactions on Geoscience and Remote Sensing, 1995, 33(2):293-304.DOI: 10.1109/36.377929. 本文引用 [1]

[26]	ZHANG L J, ZHAO Y Y, CHEN C, et al. UAV-LiDAR integration with Sentinel-2 enhances precision in AGB estimation for bamboo forests[J]. Remote Sensing, 2024, 16(4):705.DOI: 10.3390/rs16040705. 本文引用 [4]

[27]	郑佳佳, 周忠发, 朱孟, 等. 典型喀斯特山区的森林蓄积量遥感估算[J]. 水土保持通报, 2024, 44(2):176-186. ZHENG J J, ZHOU Z F, ZHU M, et al. Remote sensing estimation of forest volume in typical Karst mountainous areas[J]. Bulletin of Soil and Water Conservation, 2024, 44(2):176-186.DOI: 10.13961/j.cnki.stbctb.2024.02.019. 本文引用 [1]

[28]	WU Y S, ZHANG X L. Object-based tree species classification using airborne hyperspectral images and LiDAR data[J]. Forests, 2020, 11(1):32.DOI: 10.3390/f11010032. 本文引用 [1]

[29]	ZHANG W F, ZHAO L X, LI Y, et al. Forest above-ground biomass inversion using optical and SAR images based on a multi-step feature optimized inversion model[J]. Remote Sensing, 2022, 14(7):1608.DOI: 10.3390/rs14071608. 本文引用 [1]

[30]	HUANG H J, WU D S, FANG L M, et al. Comparison of multiple machine learning models for estimating the forest growing stock in large-scale forests using multi-source data[J]. Forests, 2022, 13(9):1471.DOI: 10.3390/f13091471. 本文引用 [1]

[31]	ZHANG N, CHEN M J, YANG F, et al. Forest height mapping using feature selection and machine learning by integrating multi-source satellite data in Baoding City,north China[J]. Remote Sensing, 2022, 14(18):4434.DOI: 10.3390/rs14184434. 本文引用 [2]

[32]	IL H J. 基于集成学习的天然次生林地上生物量估测[D]. 哈尔滨: 东北林业大学, 2023. IL H J. Aboveground biomass estimation of natural secondary forests based on ensemble learning algorithms[D]. Harbin: Northeast Forestry University, 2023. 本文引用 [1]

[33]	蒋馥根, 孙华, ZHAO Feng, 等. 基于方差优化k最近邻法的森林蓄积量估测[J]. 森林与环境学报, 2019, 39(5):497-504. JIANG F G, SUN H, ZHAO F, et al. Forest stock volume estimation based on a variance-optimized kNN model[J]. Journal of Forest and Environment, 2019, 39(5):497-504.DOI: 10.13324/j.cnki.jfcf.2019.05.008. 本文引用 [1]

[34]

孙忠秋, 高金萍, 吴发云, 等. 基于机载激光雷达点云和随机森林算法的森林蓄积量估测[J]. 林业科学, 2021, 57(8):68-81.

SUN

Z Q

, GAO

J P

, WU

F Y

, et al. Estimating forest stock volume via small-footprint LiDAR point cloud data and random forest algorithm[J]. Scientia Silvae Sinicae, 2021, 57(8):68-81.DOI: 10.11707/j.1001-7488.20210807.

本文引用 [1]

[35]	LIU X Q, SU Y J, HU T Y, et al. Neural network guided interpolation for mapping canopy height of China's forests by integrating GEDI and ICESat-2 data[J]. Remote Sensing of Environment, 2022,269:112844.DOI: 10.1016/j.rse.2021.112844. 本文引用 [1]

[36]	HU Y, XU X L, WU F Y, et al. Estimating forest stock volume in Hunan Province,China,by integrating in situ plot data,Sentinel-2 images,and linear and machine learning regression models[J]. Remote Sensing, 2020, 12(1):186.DOI: 10.3390/rs12010186. 本文引用 [1]

[37]

武燕, 黄青, 刘讯, 等. 西南喀斯特地区马尾松人工林林龄对土壤理化性质的影响[J]. 南京林业大学学报(自然科学版), 2024, 48(3):99-107.

, HUANG

, LIU

, et al. Effects of Pinus massoniana plantation age on soil physical and chemical properties in Karst areas in southwest China[J]. Journal of Nanjing Forestry University (Natural Science Edition), 2024, 48(3):99-107.DOI: 10.12302/j.issn.1000-2006.202210019.

本文引用 [1]