摘要
植被地上生物量(AGB)是反映湿地生态系统功能状态与健康水平的重要生态参数,可为生态系统稳定性分析和碳汇能力评估提供关键支撑。以滨海典型芦苇湿地为研究对象,基于无人机获取的高分辨率多光谱影像和113个实测芦苇AGB样本,系统评估不同特征变量组合的建模效果,并利用随机森林(RF)算法的重要性分析对变量进行筛选。随后分别构建了RF、支持向量机(SVM)和极端梯度提升(XGBoost)三种机器学习算法模型,对筛选后的特征变量进行建模与精度对比,旨在探索基于低空遥感技术开展湿地植被生物量反演的可行路径,建立适用于湿地生态监测的高效估算框架。研究结果表明,联合使用多光谱波段反射率与植被指数的变量组合显著优于单一变量类型,能够有效提升AGB估算精度。在三种建模算法中,XGBoost模型性能最优,R2为0.731,RMSE为0.184kg/m^(2),RPD达到2.431,表现出较强的稳定性与鲁棒性。空间分布分析结果显示,研究区芦苇AGB具有显著的空间异质性,高值区主要分布于水体周边的浅水带及地势低洼区域,而地势较高区域的AGB值相对较低。定量统计显示,研究区芦苇总AGB为3038.78吨,芦苇AGB值范围为0.486-1.705kg/m^(2),平均为0.88kg/m^(2)。变量贡献分析显示,红边波段及其衍生植被指数,特别是修正型叶绿素吸收反射植被指数(MCARI),在芦苇AGB反演模型中的贡献度较高,表明其在捕捉湿地植被的叶绿素含量和冠层结构变化方面具有较强的敏感性,对AGB的估算精度有显著提升作用。本研究不仅验证了基于无人机多光谱影像结合机器学习算法进行芦苇AGB反演的可行性和有效性,也为后续开展湿地生态系统功能评价、碳储量估算及关键栖息地监测提供了科学依据。
Vegetation aboveground biomass(AGB)is an important ecological parameter reflecting the functional status and health level of wetland ecosystems,which can provide key support for ecosystem stability analysis and carbon sink capacity assessment.In this paper,we take typical Phragmites australis(P.australis)wetlands in Binhai as the research object,and based on the high-resolution multispectral images acquired by UAV and 113 measured P.australis AGB samples,we systematically evaluate the modelling effect of different combinations of feature variables,and screen the variables by using the importance analysis of the Random Forest(RF)algorithm.Subsequently,three machine learning algorithm models,namely RF,Support Vector Machine(SVM)and Extreme Gradient Boosting(XGBoost),were constructed respectively to model and compare the accuracy of the screened feature variables,aiming at exploring feasible paths to carry out wetland vegetation biomass inversion based on low-altitude remote sensing technology,and establishing a high-efficiency estimation framework applicable to wetland ecological monitoring.The results show that the joint use of the variable combination of multispectral band reflectance and vegetation index is significantly better than the single variable type,which can effectively improve the accuracy of AGB estimation.Among the three modelling algorithms,the XGBoost model has the best performance,with a R^(2) of 0.731,a RMSE of 0.184 kg/m^(2),and a RPD of 2.431,which shows strong stability and robustness.The results of the spatial distribution analysis showed that the P.australis AGB in the study area had significant spatial heterogeneity,with the high value areas mainly distributed in the shallow water zone around the water body and in the low-lying areas,while the AGB values in the higher terrain areas were relatively low.Quantitative statistics showed that the total AGB of P.australis in the study area was 3038.78t,and the range of P.australis AGB values was 0.486-1.705kg/m^(2),with an average of 0.88kg/m^(2).Variable contribution analysis showed that the red edge band and its derived vegetation indexes,especially Modified Chlorophyll Absorption Reflectance Vegetation Index(MCARI)contributed more in the P.australis AGB inversion model,indicating its strong sensitivity in capturing changes in chlorophyll content and canopy structure of wetland vegetation,which significantly enhanced the estimation accuracy of AGB.This study not only verifies the feasibility and effectiveness of P.australis AGB inversion based on UAV multispectral images combined with machine learning algorithms,but also provides a scientific basis for subsequent wetland ecosystem function evaluation,carbon stock estimation and critical habitat monitoring.
作者
张晓彤
刘明月
郎红梅
张龙丰
尹轩
刘玮佳
张永彬
吴风华
李富平
满卫东
ZHANG Xiaotong;LIU Mingyue;LANG Hongmei;ZHANG Longfeng;YIN Xuan;LIU Weijia;ZHANG Yongbin;WU Fenghua;LI Fuping;MAN Weidong(College of Mining Engineering,North China University of Science and Technology,Tangshan 063210,China;Hebei Industrial Technology Institute of Mine Ecological Remediation,Tangshan 063210,China;Collaborative Innovation Center of Green Development and Ecological Restoration of Mineral Resources,Tangshan 063210,China;Tangshan Natural Resources and Planning Bureau,Tangshan 063000,China)
出处
《生态学报》
北大核心
2025年第15期7314-7325,共12页
Acta Ecologica Sinica
基金
河北省自然科学基金项目(D2023209008)
河北省中央引导地方科技发展资金项目(236Z3305G)
国家自然科学基金项目(41901375,52274166)。
关键词
机器学习
地上生物量
植被指数
无人机反演
变量组合
machine learning
aboveground biomass
vegetation index
UAV inversion
variable combinations
