Integration of UAV LiDAR and WorldView-2 images for modeling mangrove aboveground biomass with GA-ANN wrapper  

作　　者：Yuanhui Zhu Soe W.Myint Kai Liu Lin Liu Jingjing Cao 

机构地区：[1]School of Geography and Planning,Sun Yat-Sen University,Guangzhou 510006,China [2]Department of Geography and Environmental Studies,Texas State University,San Marcos,TX 78666,USA [3]The Meadows Center for Water and the Environment,San Marcos,TX 78666,USA [4]Department of Geography,University of Cincinnati,Cincinnati,OH 45221,USA [5]College of Computer Sciences,Guangdong Polytechnic Normal University,Guangzhou 510665,China

出　　处：《Ecological Processes》2024年第4期346-361,共16页生态过程(英文)

基　　金：supported by the National Natural Science Foundation of China(Grant Nos.42001358 and 42201353);the Guangdong Basic and Applied Basic Research Foundation(Grant Nos.2021A1515011462 and 2021A1515110157);the Guangzhou Science,Technology and Innovation Commission(Grant No.201804020016);Forestry Science and Technology Innovation Project of Guangdong Province(Grant No.2023KJCX008).

摘　　要：Background Integrating optical and LiDAR data is crucial for accurately predicting aboveground biomass(AGB)due to their complementarily essential characteristics.It can be anticipated that this integration approach needs to deal with an expanded set of variables and scale-related challenges.To achieve satisfactory accuracy in real-world applications,further exploration is needed to optimize AGB models by selecting appropriate scales and variables.Methods This study examined the impact of LiDAR point cloud-derived metrics on estimation accuracies at diferent scales,ranging from 2 to 16 m cell sizes.We integrated WorldView-2 imagery with LiDAR data to construct biomass models and developed a genetic algorithm-based wrapper for variable selection and parameter tuning in artifcial neural networks(GA-ANN wrapper).Results Our fndings indicated that the highest accuracies in estimating AGB were yielded by 4 m and 6 m cell sizes,followed by 8 m and 10 m,associated with the dimensions of vegetation canopies and sampling plots.Models integrating WorldView-2 and LiDAR data outperformed those using each data source individually,reducing RMSEr by 5.80%and 3.89%,respectively.Combining these data sources can capture the canopy spectral responses and vertical vegetation structure.The GA-ANN wrapper model decreased RMSEr by 1.69%over the ANN model and dwindled the number of variables from 38 to 9.The selected variables included vegetation density,height,species,and vegetation indices.Conclusions The appropriate cell size for AGB estimation should consider the sizes of vegetation canopies,tree densities,and sampling plots.The GA-ANN wrapper efectively reduced variables and achieved the highest accuracy.Additionally,canopy spectral and vertical structure information are vital for accurate AGB estimation.Our study ofered insights into optimizing mangrove AGB models by integrating optical and LiDAR data.The approach,data,model,and indices employed in this research can efectively predict AGB estimates of any other forest types or vege

关 键 词：MANGROVE LIDAR WorldView-2 Artificial neural network Genetic algorithm Remote sensing 

分 类 号：S771.8[农业科学—森林工程] S718.5[农业科学—林学]