文献类型：期刊文献

中文题名：坡垒相对叶绿素含量与图像特征的非线性分析及估测

英文题名：Nonlinear analysis and estimation of relative chlorophyll content based on image features of Hopea hainanensis

作者：袁莹[1,2] 白前[3] 石蒙蒙[1,2] 王雪峰[1,2] 王鹏[1,2] 冯启武[4]

第一作者：袁莹

机构：[1]中国林业科学研究院资源信息研究所,北京100091;[2]国家林业和草原局森林经营与生长模拟重点实验室,北京100091;[3]青海省南北山绿化服务中心,青海西宁810028;[4]都兰林晟防沙治沙有限责任公司,青海海西816100

年份：2023

卷号：43

期号：3

起止页码：295-302

中文期刊名：森林与环境学报

外文期刊名：Journal of Forest and Environment

收录：CSTPCD;;北大核心:【北大核心2020】；CSCD:【CSCD2023_2024】；

基金：中央财政林业科技推广项目“野外伺服仪远程监测分析系统技术推广”(青〔2022〕TG);国家自然科学基金项目“林木对养分与水分需求的机器理解法”(32071761)。

语种：中文

中文关键词：坡垒;叶绿素含量;图像估测法;广义可加模型;非线性关系

外文关键词：Hopea hainanensis;chlorophyll content;image-based estimation;generalized additive model;nonlinear relationship

分类号：S796

摘要：为探讨濒危树种坡垒叶绿素含量与图像特征之间的非线性关系,研究用图像颜色和纹理特征估测坡垒叶绿素含量的可行性,从而为坡垒叶绿素含量的图像无损监测提供参考。以2年生坡垒为研究对象,获取坡垒冠层相对叶绿素含量(SPAD值)和可见光红-绿-蓝图像,采用广义可加模型(GAM)探究图像颜色和纹理特征与坡垒SPAD值的非线性相关性,并用基于Lasso算法筛选后的无多重共线性多图像特征构建多元线性回归模型、GAM、随机森林模型和XGBoost回归模型以估测SPAD值。结果表明:22个图像颜色纹理特征中与坡垒SPAD值线性相关最强的特征为相关标准差,呈正相关,非线性相关最强的特征为熵均值,呈反“J”形负相关;Lasso算法能够有效去除多图像特征之间存在的严重共线性,筛选后保留的15个图像特征方差膨胀因子值均低于10;利用多图像颜色和纹理特征估测SPAD值,经过交叉验证表明,XGBoost回归模型检验精度最高,决定系数、平均绝对误差和均方根误差分别为0.757、2.682和3.242。因此,坡垒图像颜色和纹理特征与SPAD值具有一定的非线性相关性,基于具有非线性解释能力的XGBoost回归模型的图像估测法可作为坡垒叶绿素含量估测的优选方法。
The nonlinear relationship between the chlorophyll content of Hopea hainanensis,an endangered tree species,and image features was discussed,and the feasibility of estimating the chlorophyll content of H.hainanensis by image color and texture features was studied in this paper,providing a reference for image-based non-destructive monitoring.The canopy chlorophyll content(SPAD value)and RGB images were obtained using a 2-year-old H.hainanensis as the research object.The generalized additive model(GAM)was used to explore the nonlinear correlation between the image color and texture characteristics and the SPAD values.The SPAD values were then estimated using the multiple linear regression,GAM,random forest,and XGBoost models based on the features without multicollinearity filtered by the Lasso algorithm.Among the 22-image color and texture features,the feature with the strongest linear correlation was a correlation standard deviation,which was positively correlated,while the feature with the strongest nonlinear correlation was entropy mean,which was inverse J-shaped and negatively correlated.The Lasso algorithm effectively removed the severe collinearity among multiple image features,and the VIF values of the 15 image features retained after screening were all lower than 10.Based on the results of estimating SPAD values using multi-image color texture features,the test accuracy of the XGBoost model was highest,and the average testing R 2,MAE,and RMSE were 0.757,2.682,and 3.242,respectively.Therefore,there are certain nonlinear correlations between SPAD values of H.hainanensis and image color and texture features.The image estimation method based on the GAM model with nonlinear interpretation ability can be used as the optimal method for estimating the chlorophyll content of H.hainanensis.