基于EBKRP法优化GEDI数据的龙竹叶绿素含量估测

doi:10.13287/j.1001-9332.202505.003

摘要/Abstract

摘要： 叶绿素含量是评价森林健康状况和植被生长状况的重要参数,利用遥感技术以低成本准确估测区域尺度叶绿素含量是当前亟待解决的问题。本研究以云南省玉溪市新平县为研究区,以GEDI数据为主要信息源,基于经验贝叶斯克里金回归预测(EBKRP)法准确获取研究区内光斑特征参数在未知空间的连续分布,结合52块样地实测数据,采用Pearson、随机森林(RF)、梯度提升回归树(GBRT)3种方法筛选最优组合参数,利用随机森林回归(RFR)模型和GBRT模型建立区域尺度龙竹叶绿素含量最佳估测模型。结果表明:EBKRP法预测精度高,结果可靠,R²值在0.34～0.99,RMSE值在0.012～3134.005,rRMSE值在0.011～0.854,CRPS在965.492～1626.887。参数选优方法不同,选出的最佳组合参数略有差异。遥感建模方法不同,构建的模型精度存在差异,利用GBRT模型构建的遥感估测模型(R²=0.94,RMSE=0.132,P=91.2%),其性能优于 RFR模型(R²=0.89,RMSE=0.192,P=89.3%);选用GBRT模型估测研究区龙竹叶绿素含量,其分布范围为0.22～2.32 g·m^-2,平均叶绿素含量为1.36 g·m^-2,此研究结果与研究区龙竹分布具有一致性,说明基于EBKRP法优化后的GEDI数据,选用GBRT模型进行森林生化参数估测具有可行性,结果可靠,可为森林健康监测提供有效支持与服务。

关键词: GEDI, EBKRP, 组合参数选优, 机器学习, 叶绿素含量, 估测

Abstract: Chlorophyll content is a crucial parameter for evaluating forest health and vegetation growth. It is an urgent to accurately estimate chlorophyll content at the regional scale with low cost by using remote sensing techno-logy. In this study, we took Xinping County, Yuxi City, Yunnan Province, as the research area, and used GEDI data as the main information source. Based on the empirical Bayesian Kriging regression prediction (EBKRP) method, we accurately obtained the continuous distribution of the spot characteristic parameters in the unknown space of the study area. Combined with measured data of 52 plots, we used Pearson correlation, random forest (RF) and gradient boosting regression tree (GBRT) to screen the optimal combination parameters. We further established the best estimation model of chlorophyll content of Dendrocalamus giganteus at regional scale by Random forest regression (RFR) and GBRT models. The results showed that EBKRP demonstrated high prediction accuracy and reliability, with R² values ranging from 0.34 to 0.99, RMSE from 0.012 to 3134.005, rRMSE from 0.011 to 0.854, and CRPS from 965.492 to 1626.887. Different parameter optimization methods yielded slightly different optimal para-meter combinations. Different remote sensing modeling methods showed varying accuracy levels. The GBRT model (R²=0.94, RMSE=0.132, P=91.2%) outperformed the RFR model (R²=0.89, RMSE=0.192, P=89.3%). Using the GBRT model for estimating and mapping the spatial distribution of D. giganteus chlorophyll content, which ranged from 0.22 to 2.32 g·m^-2, with an average of 1.36 g·m^-2. These results aligned with the actual D. giganteus distribution in the study area, indicating that the GBRT model using GEDI data optimized by EBKRP could be feasible and reliable for estimating forest biochemical parameters, thereby providing effective support for forest health monitoring.

Key words: GEDI, EBKRP, combination parameter optimization, machine learning, chlorophyll content, estimation

夏翠芬, 周文武, 舒清态, 王明星, 吴再昆, 付连进, 任承芳. 基于EBKRP法优化GEDI数据的龙竹叶绿素含量估测[J]. 应用生态学报, 2025, 36(5): 1319-1329.

XIA Cuifen, ZHOU Wenwu, SHU Qingtai, WANG Mingxing, WU Zaikun, FU Lianjin, REN Chengfang. Estimation of chlorophyll content in Dendrocalamus giganteus based on GEDI data optimized by EBKRP method[J]. Chinese Journal of Applied Ecology, 2025, 36(5): 1319-1329.

参考文献

[1] 祁敏, 张超. 森林理化参数高光谱遥感反演研究进展. 世界林业研究, 2016, 29(1): 52-57
[2] 徐道青, 刘小玲, 王维, 等. 淹水胁迫下棉花叶片高光谱特征及叶绿素含量估算模型. 应用生态学报, 2017, 28(10): 3289-3296
[3] 倪惠菁, 储昊煜, 苏文会, 等. 经营强度对毛竹林土壤团聚体稳定性和碳氮磷分布的影响. 应用生态学报, 2023, 34(4): 928-936
[4] Madeira AC, Mentions A, Ferreira ME, et al. Relationship between spectroradiometric and chlorophyll mea-surements in green beans. Communications in Soil Science and Plant Analysis, 2000, 31: 631-643
[5] Xu XQ, Lu JS, Zhang N, et al. Inversion of rice canopy chlorophyll content and leaf area index based on coupling of radiative transfer and Bayesian network models. ISPRS Journal of Photogrammetry and Remote Sensing, 2019, 150: 185-196
[6] Wu Q, Zhang YP, Zhao ZW, et al. Estimation of relative chlorophyll content in spring wheat based on multi-temporal UAV remote sensing. Agronomy, 2023, 13: 211
[7] Vermote E, Justice C, Claverie M, et al. Preliminary analysis of the performance of the Landsat 8/OLI land surface reflectance product. Remote Sensing of Environment, 2016, 185: 46-56
[8] Yang YF, Zhang X, Gao W, et al. Improving lake chlorophyll-a interpreting accuracy by combining spectral and texture features of remote sensing. Environmental Science and Pollution Research, 2023, 30: 83628-83642
[9] 赵祥, 刘素红, 王培娟, 等. 基于高光谱数据的小麦叶绿素含量反演. 地理与地理信息科学, 2004, 20(3): 36-39
[10] 梁亮, 杨敏华, 张连蓬, 等. 基于SVR算法的小麦冠层叶绿素含量高光谱反演. 农业工程学报, 2012, 28(20): 162-171
[11] 朱蕾, 黄敬峰. 山区县域尺度降水量空间插值方法比较. 农业工程学报, 2007, 23(7): 80-85
[12] Xia CF, Zhou WW, Shu QT, et al. Regional scale inversion of chlorophyll content of Dendrocalamus giganteus by multi-source remote sensing. Forests, 2024, 15: 1211
[13] 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: 2913
[14] Njoku EA, Akpan PE, Effiong AE, et al. The effects of station density in geostatistical prediction of air temperatures in Sweden: A comparison of two interpolation techniques. Resources, Environment and Sustainability, 2023, 11: 100092
[15] Shah SH, Angel Y, Houborg R, et al. A random forest machine learning approach for the retrieval of leaf chlorophyll content in wheat. Remote Sensing, 2019, 11: 920
[16] Darvishzadeh R, Matkan AA, Ahangar AD. Inversion of a radiative transfer model for estimation of rice canopy chlorophyll content using a lookup-table approach. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5: 1222-1230
[17] 刘文雅, 潘洁. 基于神经网络的马尾松叶绿素含量高光谱估算模型. 应用生态学报, 2017, 28(4): 1128-1136
[18] Ta N, Chang QR, Zhang YM. Estimation of apple tree leaf chlorophyll content based on machine learning methods. Remote Sensing, 2021, 13: 3902
[19] 李兴平. 云南新平县雪茄烟种植现状及产业发展建议. 农业工程技术, 2022, 42(32): 18-20
[20] 王学奎, 黄见良. 植物生理生化实验原理与技术. 北京: 高等教育出版社, 2015: 131-132
[21] Liang MY, González-Roglich M, Roehrdanz P, et al. Assessing protected area’s carbon stocks and ecological structure at regional-scale using GEDI lidar. Global Environmental Change, 2023, 78: 102621
[22] Xu L, Lai HY, Yu JG, et al. Carbon storage estimation of Quercus aquifolioides based on GEDI spaceborne LiDAR Data and Landsat 9 images in Shangri-La. Sustai-nability, 2023, 15: 11525
[23] 周文武, 舒清态, 胥丽, 等. 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. 生态学报, 2024, 44(8): 3525-3539
[24] 马战林, 刘昌华, 薛华柱, 等. GEE环境下融合主被动遥感数据的冬小麦识别技术. 农业机械学报, 2021, 52(9): 195-205
[25] Wu Q, Jin Y, Fan H. Evaluating and comparing performances of topographic correction methods based on multi-source DEMs and Landsat-8 OLI data. International Journal of Remote Sensing, 2016, 37: 4712-4730
[26] 王柯人, 罗文秀, 舒清态, 等. 龙竹人工林的含水率分析及地上生物量回归模型构建. 西南林业大学学报: 自然科学, 2021, 41(6): 168-174
[27] Goovaerts P. Geostatistics for Natural Resources Evaluation. Oxford, UK: Oxford University Press, 1997
[28] Chiles JP, Delfiner P. Geostatistics: Modeling Spatial Uncertainty. New York, USA: John Wiley & Sons, 2012
[29] Wu J, Chen XY, Zhang H, et al. Hyperparameter optimization for machine learning models based on Bayesian optimization. Journal of Electronic Science and Techno-logy, 2019, 17: 26-40
[30] Breiman L. Random forests. Machine Learning, 2001, 45: 5-32
[31] 仉文岗, 唐理斌, 陈福勇, 等. 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. 应用基础与工程科学学报, 2021, 29(5): 1186-1200
[32] 龚越, 罗小芹, 王殿海, 等. 基于梯度提升回归树的城市道路行程时间预测. 浙江大学学报: 工学版, 2018, 52(3): 453-460
[33] 纪昌明, 周婷, 向腾飞, 等. 基于网格搜索和交叉验证的支持向量机在梯级水电系统隐随机调度中的应用. 电力自动化设备, 2014, 34(3): 125-131
[34] Giustini F, Ciotoli G, Rinaldini A, et al. Mapping the geogenic radon potential and radon risk by using Empirical Bayesian Kriging regression: A case study from a volcanic area of central Italy. Science of the Total Environment, 2019, 661: 449-464
[35] 周文武, 舒清态, 王书伟, 等. 基于多源遥感数据协同的滇西北森林郁闭度估测. 应用生态学报, 2023, 34(7): 1806-1816
[36] 朱阿兴, 闾国年, 周成虎, 等. 地理相似性: 地理学的第三定律？地球信息科学学报, 2020, 22(4): 673-679
[37] Song HY, Xi L, Shu QT, et al. Estimate forest aboveground biomass of mountain by ICESat-2/ATLAS data interacting cokriging. Forests, 2022, 14: 13
[38] 曲怡铃, 唐燕, 周忠生, 等. 基于无人机可见光影像的毛竹相对叶绿素含量反演研究. 江西农业大学学报, 2022, 44(1): 139-150
[39] 刘小杰, 宋凌寒, 张仓皓, 等. 毛竹叶片叶绿素含量估算模型对比研究. 北京林业大学学报, 2023, 45(10): 70-80
[40] Zhu XX, Nie S, Wang C, et al. Consistency analysis of forest height retrievals between GEDI and ICESat-2. Remote Sensing of Environment, 2022, 281: 113244