Estimation of tree height with machine learning techniques in coppice-originated pure sessile oak (Quercus petraea (Matt.) Liebl.) stands

IF 1.8 3区农林科学 Q2 FORESTRY

Scandinavian Journal of Forest Research Pub Date : 2023-01-23 DOI:10.1080/02827581.2023.2168044

Abbas Şahi̇n, Gafura Aylak Ozdemir, O. Oral, Batin Latif Aylak, Murat Ince, Emrah Ozdemir

{"title":"Estimation of tree height with machine learning techniques in coppice-originated pure sessile oak (Quercus petraea (Matt.) Liebl.) stands","authors":"Abbas Şahi̇n, Gafura Aylak Ozdemir, O. Oral, Batin Latif Aylak, Murat Ince, Emrah Ozdemir","doi":"10.1080/02827581.2023.2168044","DOIUrl":null,"url":null,"abstract":"ABSTRACT In this study, in order to estimate total tree height, three different model structures with different input variables were produced through the use of 872 tree data points obtained from different development stages and sites in coppice-originated pure sessile oak (Quercus petraea [Matt.] Liebl.) stands. These models were fitted with machine learning techniques such as artificial neural networks (ANNs), decision trees, support vector machines, and random forests. In addition, the model based on DBH was fitted and its parameters were calculated using the ordinary nonlinear least squares method and this model was selected as the best model in Model 1. In other model structures, ANN model was chosen as the best estimation method based on the relative ranking method in which the goodness of fit statistics of the estimation methods were evaluated together. The inclusion of stand variables in addition to the DBH measurement in the model increased the R 2 by about 36% and reduced the error rate by 55%.","PeriodicalId":21352,"journal":{"name":"Scandinavian Journal of Forest Research","volume":"38 1","pages":"87 - 96"},"PeriodicalIF":1.8000,"publicationDate":"2023-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Scandinavian Journal of Forest Research","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1080/02827581.2023.2168044","RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"FORESTRY","Score":null,"Total":0}

引用次数: 2

Abstract

ABSTRACT In this study, in order to estimate total tree height, three different model structures with different input variables were produced through the use of 872 tree data points obtained from different development stages and sites in coppice-originated pure sessile oak (Quercus petraea [Matt.] Liebl.) stands. These models were fitted with machine learning techniques such as artificial neural networks (ANNs), decision trees, support vector machines, and random forests. In addition, the model based on DBH was fitted and its parameters were calculated using the ordinary nonlinear least squares method and this model was selected as the best model in Model 1. In other model structures, ANN model was chosen as the best estimation method based on the relative ranking method in which the goodness of fit statistics of the estimation methods were evaluated together. The inclusion of stand variables in addition to the DBH measurement in the model increased the R 2 by about 36% and reduced the error rate by 55%.

查看原文本刊更多论文

用机器学习技术估计纯无梗栎树高(栎)Liebl)站

摘要本研究利用从不同发育阶段和不同地点获得的872棵栎树数据点，构建了三种不同输入变量的模型，以估算栎树的总树高。(李伯尔)站着。这些模型采用人工神经网络(ann)、决策树、支持向量机和随机森林等机器学习技术进行拟合。此外，对基于胸径的模型进行拟合，并利用普通非线性最小二乘法计算模型参数，在模型1中选取该模型作为最优模型。在其他模型结构中，采用相对排序法对各估计方法的拟合优度进行综合评价，选择人工神经网络模型作为最佳估计方法。除了胸径测量外，在模型中加入林分变量后，r2提高了约36%，错误率降低了55%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Scandinavian Journal of Forest Research 农林科学-林学

CiteScore

3.00

自引率

5.60%

发文量

审稿时长

3.3 months

期刊介绍： The Scandinavian Journal of Forest Research is a leading international research journal with a focus on forests and forestry in boreal and temperate regions worldwide.