Zhou Wenwu, Qian Changming, Shu Qingtai, Qiu Shuang, Huang Jinjun, Yu Jinge, Gao Yingqun, Guo Chaosheng. LAI Estimation of Pinus densata in Northwest Yunnan Based on UAV and Sentinel–2 Data[J]. Journal of Southwest Forestry University, 2024, 44(6): 141-149. DOI: 10.11929/j.swfu.202310009
Citation: Zhou Wenwu, Qian Changming, Shu Qingtai, Qiu Shuang, Huang Jinjun, Yu Jinge, Gao Yingqun, Guo Chaosheng. LAI Estimation of Pinus densata in Northwest Yunnan Based on UAV and Sentinel–2 Data[J]. Journal of Southwest Forestry University, 2024, 44(6): 141-149. DOI: 10.11929/j.swfu.202310009

LAI Estimation of Pinus densata in Northwest Yunnan Based on UAV and Sentinel–2 Data

More Information
  • Received Date: October 07, 2023
  • Accepted Date: April 07, 2024
  • Available Online: October 20, 2024
  • The research focused on the typical Pinus densata natural forest in Shangri-La and utilized multi-spectral images obtained by low-altitude aerial photography using a UAV. The canopy gap rate model was applied to calculate leaf area index, and the extracted vegetation index from the Sentinel–2 image was integrated. Subsequently, an estimation model for the leaf area index of P. densata was developed using the random forest (RF), Bayesian optimization algorithm improved RF(BO–RF). At the same time, the leave one out cross-validation method was used to evaluate the fitting accuracy of the estimation model by the determination coefficient (R2), root mean square error(RMSE), prediction accuracy(P) and mean absolute error(MRE). The BO–RF model with the highest accuracy was used for LAI remote sensing inversion at the regional scale. The results showed that the mean LAI calculated by the canopy gap rate model was 4.24, and the standard deviation was 0.96 based on the multi-spectral remote sensing image of UAV. Bayesian optimization algorithm can effectively improve the estimation accuracy of the machine learning model and the R2 = 0.82, RMSE=0.41, P=90.03% and MRE=8.78% of the BO–RF model. The R2 increased by 20.59%, RMSE decreased by 24.07%, P increased by 2.87%, and MRE decreased by 1.78%, compared to the values before optimization. The BO–RF model was used to estimate LAI and spatial mapping in the study area. The average value was 4.25, which was mainly distributed in the range of [4,6], accounting for 63.15 %. This distribution aligns with the measured and predicted values, displaying a strong correlation coefficient of 0.75 and R2 = 0.58. The overall distribution of LAI tends to be high in the center and low in the periphery, with the central and northern regions being the main distribution areas for high LAI values, and low values mainly in the southeast. The research results can provide a reference for rapid and precise remote sensing estimation of forest LAI at a large spatial scale using ultra-high resolution optical data in conjunction with spaceborne medium-resolution satellite data.

  • [1]
    Chen J M, Cihlar J Remote Sensing of Environment Retrieving leaf area index of boreal conifer forests using Landsat TM images 1996 55 2 153 162 10.1016/0034-4257(95)00195-6 DOI: 10.1016/0034-4257(95)00195-6
    [2]
    梁顺林, 李小文, 王锦地, 等. 定量遥感: 理念与算法[M]. 2版. 北京: 科学出版社, 2019: 407−409.
    [3]
    刘强, 蔡二丽, 张嘉琳, 等 植物学报 叶面积指数田间测量中有限长度平均法的改进 2018 53 5 671 685
    [4]
    贺敏, 闻建光, 游冬琴, 等 遥感学报 山地森林叶面积指数(LAI)遥感估算研究进展 2022 26 12 2451 2472
    [5]
    王希群, 马履一, 贾忠奎, 等 生态学杂志 叶面积指数的研究和应用进展 2005 24 5 537 541 10.3321/j.issn:1000-4890.2005.05.015 DOI: 10.3321/j.issn:1000-4890.2005.05.015
    [6]
    洪宇, 龚建华, 胡社荣, 等 遥感技术与应用 无人机遥感影像获取及后续处理探讨 2008 23 4 462 466
    [7]
    张潘. 无人机遥感影像数据处理在生产中关键环节研究[D]. 成都: 成都理工大学, 2016.
    [8]
    汪小钦, 王苗苗, 王绍强, 等 农业工程学报 基于可见光波段无人机遥感的植被信息提取 2015 31 5 152 159
    [9]
    胡容海, 阎广建 地球信息科学学报 对Beer-Lambert定律间接测量森林LAI的误差低估分析 2012 14 3 366 375
    [10]
    褚洪亮, 肖青, 柏军华, 等 遥感技术与应用 基于无人机遥感的叶面积指数反演 2017 32 1 140 148
    [11]
    孙越, 顾祝军, 李栋梁 测绘科学 无人机与卫星影像的叶面积指数遥感反演研究 2021 46 2 106 112, 145
    [12]
    姚雄, 余坤勇, 杨玉洁, 等 农业机械学报 基于随机森林模型的林地叶面积指数遥感估算 2017 48 5 159 166
    [13]
    史博太, 常庆瑞, 崔小涛, 等 麦类作物学报 基于Sentinel–2多光谱数据和机器学习算法的冬小麦LAI遥感估算 2021 41 6 752 761
    [14]
    Zhang W F, Zhao L X, Li Y, et al Remote Sensing Forest above-ground biomass inversion using optical and SAR images based on a multi-step feature optimized inversion model 2022 14 7 1608 10.3390/rs14071608 DOI: 10.3390/rs14071608
    [15]
    仉文岗, 唐理斌, 陈福勇, 等 应用基础与工程科学学报 基于4种超参数优化算法及随机森林模型预测TBM掘进速度 2021 29 5 1186 1200
    [16]
    Chen L, Ren C Y, Bao G D, et al Remote Sensing 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 2022 14 12 2743 10.3390/rs14122743 DOI: 10.3390/rs14122743
    [17]
    宋涵玥, 舒清态, 席磊, 等 农业工程学报 基于星载ICESat-2/ATLAS数据的森林地上生物量估测 2022 38 10 191 199
    [18]
    崔佳旭, 杨博 软件学报 贝叶斯优化方法和应用综述 2018 29 10 3068 3090
    [19]
    Cho H, Kim Y, Lee E, et al IEEE Access Basic enhancement strategies when using Bayesian optimization for hyperparameter tuning of deep neural networks 1072 8 52588 52608
    [20]
    谭德宏, 舒清态, 赵洪莹, 等 林业资源管理 基于遗传算法优化BP神经网络模型估测高山松叶面积指数 2020 5 123 130
    [21]
    赵洪莹, 舒清态, 罗文秀, 等 西南林业大学学报(自然科学) 基于Landsat 8-OLI的高山松叶面积指数采样尺度优化分析 2021 41 5 114 120
    [22]
    Lang A Agricultural and Forest Meteorology Estimation of leaf area index from transmission of direct sunlight in discontinuous canopies 1986 37 3 229 243 10.1016/0168-1923(86)90033-X DOI: 10.1016/0168-1923(86)90033-X
    [23]
    徐希孺. 遥感物理[M]. 北京: 北京大学出版社, 2005: 75−85.
    [24]
    田庆久, 闵祥军 地球科学进展 植被指数研究进展 1998 13 4 10 16
    [25]
    Huete A Remote Sensing of Environment A comparison of vegetation indices over a global set of TM images for EOS-MODIS 1997 59 3 440 451 10.1016/S0034-4257(96)00112-5 DOI: 10.1016/S0034-4257(96)00112-5
    [26]
    Jiang Z, Huete A, Didan K, et al Remote Sensing of Environment Development of a two-band enhanced vegetation index without a blue band 2008 112 10 3833 3845 10.1016/j.rse.2008.06.006 DOI: 10.1016/j.rse.2008.06.006
    [27]
    Su T, Spicer R A, Wu F X, et al Proceedings of the National Academy of Sciences of the United States of America A middle Eocene lowland humid subtropical “Shangri-La” ecosystem in central Tibet 2020 117 52 32989 32995
    [28]
    Shi L Y, Zhao H B, Li Y L, et al International Journal of Sustainable Development & World Ecology Evaluation of Shangri-La county’s tourism resources and ecotourism carrying capacity 2015 22 2 103 109
    [29]
    Pu Y H, Xu D D, Wang H B, et al Remote Sensing Extracting canopy closure by the CHM-based and SHP-based methods with a hemispherical FOV from UAV-LiDAR data in a poplar plantation 2021 13 19 3837 10.3390/rs13193837 DOI: 10.3390/rs13193837
    [30]
    Zhao P P, Lu D S, Wang G X, et al Remote Sensing Examining spectral reflectance saturation in landsat imagery and corresponding solutions to improve forest aboveground biomass estimation 2016 8 6 469 10.3390/rs8060469 DOI: 10.3390/rs8060469
    [31]
    周文武, 舒清态, 王书伟, 等 应用生态学报 基于多源遥感数据协同的滇西北森林郁闭度估测 2023 34 7 1806 1816
    [32]
    李擎, 王振锡, 王雅佩, 等 中南林业科技大学学报 基于GF−2号遥感影像的天山云杉林郁闭度估测研究 2019 39 8 48 54
    [33]
    周文武, 舒清态, 胥丽, 等 生态学报 滇西北森林郁闭度估测模型——基于全球生态系统动力学调查多波束激光雷达数据 2024 44 8 3525 3539

Catalog

    Article views (43) PDF downloads (31) Cited by()

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return