Please wait a minute...
 
Remote Sensing for Natural Resources    2022, Vol. 34 Issue (3) : 129-137     DOI: 10.6046/zrzyyg.2021237
|
Application of airborne LiDAR in the estimation of the mean height of mangrove stand
DENG Jingwen1(), TIAN Yichao1,2(), ZHANG Qiang1, TAO Jin1,3, ZHANG Yali1, HUANG Shengguang3
1. Collage of Resources and Environment, Beibu Gulf University, Qinzhou 535000, China
2. Guangxi Key Laboratory of Marine Disaster in the Beibu Gulf, Beibu Gulf University, Qinzhou 535000, China
3. Key Laboratory of Marine Geographic Information Resources Development and Utilization, Beibu Gulf University, Qinzhou 535000, China
Download: PDF(7423 KB)   HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks    
Abstract  

This study constructed a stand mean height inversion model based on LiDAR data, aiming to provide dynamic monitoring of the growth of Sonneratia apetala. Taking the mangrove wetland of Sonneratia apetala in the Maowei Sea of Beibu Gulf as the study object and based on the height and intensity parameters extracted using airborne LiDAR data, this study compared three models, namely random forest, support vector machine, and neural network, based on the coefficient of determination (R2), root mean square error (RMSE), Akachi information criterion (AIC), and Bayesian information criterion (BIC) and then estimated the mean height and spatial distribution of Mangrove in the study area using the optimal model. The results are as follows. The stand mean height of Sonneratia apetala in the study area is 3.90~11.58 m, and Sonneratia apetala with a higher tree height and a larger diameter at breast height is mainly distributed near the tidal trench and the middle part of the study area. In the estimation of the stand mean height of Sonneratia apetala, the maximum percentile height (hmax) had the highest contribution rate, followed by 75%~99% percentile height. The random forest regression model yielded the highest precision (R2=0.938 1,RMSE=0.58 m,AIC=80.50, and BIC=49.05), followed by the support vector machine model (R2 = 0.766 5 and RMSE = 1.27 m in the test stage), and the neural network regression model yielded the worst fitting effects. Overall, the random forest model is the optimal model for the inversion of the stand mean height of Sonneratia apetala in the study area.
Keywords Sonneratia apetala      support vector machine      neural network      random forest      stand mean height     
ZTFLH:  S771.8  
  TP79  
Corresponding Authors: TIAN Yichao     E-mail: 1687606800@qq.com;tianyichao1314@yeah.net
Issue Date: 21 September 2022
Service
E-mail this article
E-mail Alert
RSS
Articles by authors
Jingwen DENG
Yichao TIAN
Qiang ZHANG
Jin TAO
Yali ZHANG
Shengguang HUANG
Cite this article:   
Jingwen DENG,Yichao TIAN,Qiang ZHANG, et al. Application of airborne LiDAR in the estimation of the mean height of mangrove stand[J]. Remote Sensing for Natural Resources, 2022, 34(3): 129-137.
URL:  
https://www.gtzyyg.com/EN/10.6046/zrzyyg.2021237     OR     https://www.gtzyyg.com/EN/Y2022/V34/I3/129
Fig.1  Location of mangrove in the research area
Fig.2  Field measured sample site data acquisition in the study area
Fig.3  Airborne LiDAR data at the sample site
变量 变量意义①
hp01\ip01,…,hp99\ip99 所有点云1%,…,99%分位数处对应的高度\强度值
hmax\imax 样方点云高度\强度的最大值
hmin\imin 样方点云高度\强度的最小值
hmean\imean 样方点云高度\强度的平均值mean,计算公式为: m e a n = ∑ j = 1 m x j m
hstddev\istddev 样方点云高度\强度的标准差stddev,计算公式为: s t d d e v = 1 m ∑ j = 1 m ( x j - x - ) 2
hcv\icv 样方点云高度\强度的变异系数cv,计算公式为: c v = s t d d e v m e a n
imode\imode 样方点云高度\强度的众数
hiq\iiq 样方点云百分位数高度\强度的四分位数间距iq,计算公式为: i q = p 75 - p 25
Tab.1  Point cloud characteristic statistics for stand mean height estimation
Fig.4  schematic diagram of BP neural network
参数 最大值 最小值 平均值 标准差
树高/m 13.58 1.55 8.09 2.69
胸径/cm 41.00 0.70 15.38 5.55
林分平均高/m 12.02 3.47 8.19 2.28
Tab.2  Basic statistics for field measurements of tree height, diameter at breast height, and stand mean height
Fig.5  Variable importance chart
模型 训练集 测试集
R2 RMSE/m AIC BIC R2 RMSE/m AIC BIC
随机森林 0.985 7 0.28 36.59 21.42 0.938 1 0.58 80.50 49.05
支持向量机 0.985 6 0.30 37.18 22.00 0.766 5 1.27 87.85 56.40
神经网络 0.978 5 0.34 47.01 31.84 0.436 4 2.90 107.61 76.16
Tab.3  Comparison of the performance of three ML models in stand mean high retrieval
Fig.6  Training and testing results of different regression models
Fig.7  Mean stand height distribution
[1] 庞勇, 李增元, 陈尔学, 等. 激光雷达技术及其在林业上的应用[J]. 林业科学, 2005(3):129-136.
[1] Pang Y, Li Z Y, Chen E X, et al. LiDAR remote sensing technology and its application in forestry[J]. Scientia Silvae Sinicae, 2005(3):129-136.
[2] Næsset E, Økland T. Estimating tree height and tree crown properties using airborne scanning laser in a boreal nature reserve[J]. Remote Sensing of Environment, 2002, 79(1):105-115.
doi: 10.1016/S0034-4257(01)00243-7 url: https://linkinghub.elsevier.com/retrieve/pii/S0034425701002437
[3] Andersen H E, Mcgaughey R J, Reutebuch S E. Estimating forest canopy fuel parameters using LiDAR data[J]. Remote Sensing of Environment, 2005, 94(4):441-449.
doi: 10.1016/j.rse.2004.10.013 url: https://linkinghub.elsevier.com/retrieve/pii/S0034425704003438
[4] 焦义涛, 邢艳秋, 霍达, 等. 基于机载LiDAR点云估测林分的平均树高[J]. 西北林学院学报, 2015, 30(3):170-174.
[4] Jiao Y T, Xing Y Q, Huo D, et al. Study on mean canopy height estimation from airborne LiDAR point cloud date[J]. Journal of Northwest Forestry University, 2015, 30(3):170-174.
[5] 洪奕丰, 张守攻, 陈伟, 等. 基于机载激光雷达的落叶松组分生物量反演[J]. 林业科学研究, 2019, 32(5):83-90.
[5] Hong Y F, Zhang S G, Chen W, et al. Inversion of biomass components for Larix olgensis plantation using airborne LiDAR[J]. Forest Research, 2019, 32(5):83-90.
[6] Li M, Im J, Quackenbush L J, et al. Forest biomass and carbon stock quantification using airborne LiDAR data:A case study over Huntington Wildlife Forest in the Adirondack Park[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017, 7(7):3143-3156.
doi: 10.1109/JSTARS.2014.2304642 url: https://ieeexplore.ieee.org/document/6748911/
[7] Monnet J M, Chanussot J, Berger F. Support vector regression for the estimation of forest stand parameters using airborne laser scanning[J]. IEEE Geoscience and Remote Sensing Letters, 2011, 8(3):580-584.
doi: 10.1109/LGRS.2010.2094179 url: http://ieeexplore.ieee.org/document/5682006/
[8] 鲁林, 周小成, 余治忠, 等. 随机森林算法在机载LiDAR数据林分平均树高估算中的应用研究[J]. 地球信息科学学报, 2016, 18(8):1133-1140.
doi: 10.3724/SP.J.1047.2016.01133
[8] Lu L, Zhou X C, Yu Z Z, et al. Plot-level forest height inversion using airborne LiDAR data based on the random forest[J]. Journal of Geo-Information Science, 2016, 18(8):1133-1140.
[9] 赵勋, 岳彩荣, 李春干, 等. 基于机载LiDAR数据估测林分平均高[J]. 林业科学研究, 2020, 33(4):59-66.
[9] Zhao X, Yue C R, Li C G, et al. Estimation of forest stand mean height based on airborne LiDAR point cloud data[J]. Forest Research, 2020, 33(4):59-66.
[10] 王德智. 结合UAV-LiDAR和卫星遥感数据的红树林多尺度观测方法研究[D]. 武汉: 中国地质大学(武汉), 2020.
[10] Wang D Z. Integration of UAV-LiDAR data and satellite imagery for multi-scale mangrove observation[D]. Wuhan: China University of Geosciences(Wuhan), 2020.
[11] Tian Y C, Huang H, Zhang G Q, et al. Aboveground mangrove biomass estimation in Beibu Gulf using machine learning and UAV remote sensing[J]. Science of the Total Environment, 2021, 781:146816-146834.
doi: 10.1016/j.scitotenv.2021.146816 url: https://linkinghub.elsevier.com/retrieve/pii/S0048969721018842
[12] 廖宝文, 郑松发, 陈玉军, 等. 外来红树植物无瓣海桑生物学特性与生态环境适应性分析[J]. 生态学杂志, 2004(1):10-15.
[12] Liao B W, Zheng S F, Chen Y J, et al. Biological characteristics and ecological adaptability for non-indigenous mangrove species Sonneratia apetala[J]. Chinese Journal of Ecology, 2004(1):10-15.
[13] 邓必玉. 广西钦州沿海无瓣海桑入侵性初探[J]. 湖北林业科技, 2020, 49(5):46-52.
[13] Deng B Y. A preliminary exploration on the eological invasion of Sonneratia apetala in Qinzhou area of Guangxi[J]. Hubei Forestry Science and Technology, 2020, 49(5):46-52.
[14] 田义超, 黄远林, 张强, 等. 北部湾典型海岛生态系统服务价值空间异质性对比研究[J]. 海洋科学, 2019, 43(2):60-68.
[14] Tian Y C, Huang Y L Zhang Q, et al. A comparative study of spatial heterogeneity of ecosystem service value in typical islands in Beibu Gulf[J]. Marine Sciences, 2019, 43(2):60-68.
[15] 周生祥. 林分平均树高的求算与分析[J]. 华东森林经理, 1989(3):37-45.
[15] Zhou S X. Calculation and analysis of mean height of tree stand[J]. East China Forest Management, 1989(3):37-45.
[16] Baltsavias E P. Airborne laser scanning:Basic relations and formulas[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 1999, 54(2-3):199-214.
doi: 10.1016/S0924-2716(99)00015-5 url: https://linkinghub.elsevier.com/retrieve/pii/S0924271699000155
[17] 邵为真, 赵富燕, 梁周雁. 基于不规则三角网的渐进加密滤波算法研究[J]. 北京测绘, 2016(6):17-21.
[17] Shao W Z, Zhao F Y, Liang Z Y. The research of improved progressive triangulated irregular network densification filtering algorithm[J]. Beijing Surveying and Mapping, 2016(6):17-21.
[18] Breiman L. Random forest[J]. Machine Learning, 2001, 45:5-32.
doi: 10.1023/A:1010933404324 url: http://link.springer.com/10.1023/A:1010933404324
[19] Gholami R, Fakhari N. Support vector machine:Principles,parameters,and applications[J]. Handbook of Neural Computation, 2017, 27:515-535.
[20] 欧强新. 基于机器学习的吉林天然针阔混交林生长建模[D]. 北京: 中国林业科学研究院, 2019.
[20] Ou Q X. Modeling stand growth of natural conifer and broadleaf mixed forests in Jilin Province based on machine learning[D]. Beijing: Chinese Academy of Forestry, 2019.
[21] Akaike H T. A new look at the statistical model identification[J]. IEEE Transactions on Automatic Control, 1974, 19(6):716-723.
doi: 10.1109/TAC.1974.1100705 url: http://ieeexplore.ieee.org/document/1100705/
[22] Schwarz G E. Estimating the dimension of a model[J]. The Annals of Statistics, 1978, 6(2):461-464.
[23] Vrieze, Scott I. Model selection and psychological theory:A discussion of the differences between the Akaike information criterion (AIC) and the Bayesian information criterion (BIC)[J]. Psychological methods, 2012, 17(2):228-243.
doi: 10.1037/a0027127 pmid: 22309957
[24] 张晓君, 管伟, 廖宝文, 等. 珠海人工红树林与天然红树林群落特征比较研究[J]. 生态科学, 2014, 33(2):321-326.
[24] Zhang X J, Guan W, Liao B W, et al. Comparison on the community characteristics between artificial and natural mangroves in Zhuhai City[J]. Ecological Science, 2014, 33(2):321-326.
[25] 黄晓敏, 卢昌义. 厦门海湾典型无瓣海桑人工种群特征和幼苗更新扩散现状研究[J]. 生态科学, 2018, 37(5):1-6.
[25] Huang X M, Lu C Y. Studies on the characteristics of artificial population of Sonneratia apetala and the current recruitment and dispersal of the seedlings in Xiamen Bay[J]. Ecological Science, 2018, 37(5):1-6.
[26] 吴瑞, 陈丹丹, 王道儒, 等. 海南省东寨港红树林资源现状调查分析[J]. 热带农业科学, 2016, 36(9):62-71.
[26] Wu R, Chen D D, Wang D R, et al. Survey of mangrove resources in Dongzhai Harbour of Hainan Province[J]. Chinese Journal of Tropical Agriculture, 2016, 36(9):62-71.
[27] 郑俊鸣, 舒志君, 方笑, 等. 红树林造林修复技术探讨[J]. 防护林科技, 2016(1):99-103.
[27] Zheng J M, Shu Z J, Fang X, et al. Discussion on techniques of mangrove afforestation and rehabilitation[J]. Protection Forest Science and Technology, 2016(1):99-103.
[28] 廖宝文. 中国红树林恢复与重建技术[M]. 北京: 科学出版社, 2010:20-44.
[28] Liao B W. Restoration and teconstruction techniques of mangrove forests in China[M]. Beijing: Science Press, 2010:20-44.
[29] Lu D S, Chen Q, Wang G X, et al. Aboveground forest biomass estimation with Landsat and LiDAR data and uncertainty analysis of the estimates[J]. International Journal of Forestry Research, 2012(2):436537-436553.
[30] Brice M, Michael A W, Geordie W H, et al. Forest inventory stand height estimates from very high spatial resolution satellite imagery calibrated with LiDAR plots[J]. International Journal of Remote Sensing, 2013, 34(12):4406-4424.
doi: 10.1080/01431161.2013.779041 url: https://www.tandfonline.com/doi/full/10.1080/01431161.2013.779041
[31] Pourrahmati M R, Baghdadi N, Darvishsefat A A, et al. Mapping Lorey’s height over Hyrcanian forests of Iran using synergy of ICESat/GLAS and optical images[J]. European Journal of Remote Sensing, 2018, 51(1):100-115.
doi: 10.1080/22797254.2017.1405717 url: https://www.tandfonline.com/doi/full/10.1080/22797254.2017.1405717
[32] Waske B, Benediktsson J A, Árnason, et al. Mapping of hyperspectral AVIRIS data using machine-learning algorithms[J]. Canadian Journal of Remote Sensing, 2009, 35(1):106-116.
[1] WU Weichao, YE Fawang. Cloud detection of Sentinel-2 images for multiple backgrounds[J]. Remote Sensing for Natural Resources, 2023, 35(3): 124-133.
[2] XI Lei, SHU Qingtai, SUN Yang, HUANG Jinjun, SONG Hanyue. Optimizing an ICESat2-based remote sensing estimation model for the leaf area index of mountain forests in southwestern China[J]. Remote Sensing for Natural Resources, 2023, 35(3): 160-169.
[3] PARIHA Helili, ZAN Mei. Spatio-temporal changes and influencing factors of ecological environments in oasis cities of arid regions[J]. Remote Sensing for Natural Resources, 2023, 35(3): 201-211.
[4] LIANG Jintao, CHEN Chao, ZHANG Zili, LIU Zhisong. A random forest-based method integrating indices and principal components for classifying remote sensing images[J]. Remote Sensing for Natural Resources, 2023, 35(3): 35-42.
[5] XU Xinyu, LI Xiaojun, ZHAO Heting, GAI Junfei. Pansharpening algorithm of remote sensing images based on NSCT and PCNN[J]. Remote Sensing for Natural Resources, 2023, 35(3): 64-70.
[6] LI Zhixin, WANG Mengfei, JIA Weijie, JI Song, WANG Yufei. A method for identifying the number of building floors based on shadow information[J]. Remote Sensing for Natural Resources, 2023, 35(3): 97-106.
[7] GUO Xiaomeng, FANG Xiuqin, YANG Lulu, CAO Yu. Artificial neural network-based estimation of root zone soil moisture in the western Liaohe river basin[J]. Remote Sensing for Natural Resources, 2023, 35(2): 193-201.
[8] WU Yuxin, WANG Juanle, HAN Baomin, YAN Xinrong. Forest classification for Motuo County: A method based on spatio-temporal-spectral characteristics[J]. Remote Sensing for Natural Resources, 2023, 35(1): 180-188.
[9] SUN Sheng, MENG Zhimin, HU Zhongwen, YU Xu. Application of multi-scale and lightweight CNN in SAR image-based surface feature classification[J]. Remote Sensing for Natural Resources, 2023, 35(1): 27-34.
[10] HU Jianwen, WANG Zeping, HU Pei. A review of pansharpening methods based on deep learning[J]. Remote Sensing for Natural Resources, 2023, 35(1): 1-14.
[11] KONG Zhuo, YANG Haitao, ZHENG Fengjie, LI Yang, QI Ji, ZHU Qinyu, YANG Zhonglin. Research advances in atmospheric correction of hyperspectral remote sensing images[J]. Remote Sensing for Natural Resources, 2022, 34(4): 1-10.
[12] ZHANG Hao, GAO Xiaohong, SHI Feifei, LI Runxiang. Sentinel-2 MSI and Sentinel-1 SAR based information extraction of abandoned land in the western Loess Plateau:A case study of Minhe County in Qinghai[J]. Remote Sensing for Natural Resources, 2022, 34(4): 144-154.
[13] WANG Chunxia, ZHANG Jun, LI Yixu, PHOUMILAY. The construction and verification of a water index in the complex environment based on GF-2 images[J]. Remote Sensing for Natural Resources, 2022, 34(3): 50-58.
[14] ZHU Qi, GUO Huadong, ZHANG Lu, LIANG Dong, LIU Xuting, WAN Xiangxing. Classification of tropical natural forests in Hainan Island based on multi-temporal Landsat8 remote sensing images[J]. Remote Sensing for Natural Resources, 2022, 34(2): 215-223.
[15] YANG Zhaoying, HAN Lingyi, ZHENG Xiangxiang, LI Wenji, FENG Lei, WANG Yi, YANG Yongpeng. Landslide identification using remote sensing images and DEM based on convolutional neural network: A case study of loess landslide[J]. Remote Sensing for Natural Resources, 2022, 34(2): 224-230.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
京ICP备05055290号-2
Copyright © 2017 Remote Sensing for Natural Resources
Support by Beijing Magtech