典型文献
Modelling height-diameter relationships in complex tropical rain forest ecosystems using deep learning algorithm
文献摘要：
Modelling tree height-diameter relationships in complex tropical rain forest ecosystems remains a challenge because of characteristics of multi-species, multi-layers, and indeterminate age composition. Effective modelling of such complex systems required innovative techniques to improve prediction of tree heights for use for aboveground biomass estimations. Therefore, in this study, deep learning algo-rithm (DLA) models based on artificial intelligence were trained for predicting tree heights in a tropical rain forest of Nigeria. The data consisted of 1736 individual trees repre-senting 116 species, and measured from 520.25 ha sample plots. A K-means clustering was used to classify the species into three groups based on height-diameter ratios. The DLA models were trained for each species-group in which diam-eter at beast height, quadratic mean diameter and number of trees per ha were used as input variables. Predictions by the DLA models were compared with those developed by nonlinear least squares (NLS) and nonlinear mixed-effects (NLME) using different evaluation statistics and equivalence test. In addition, the predicted heights by the models were used to estimate aboveground biomass. The results showed that the DLA models with 100 neurons in 6 hidden layers, 100 neurons in 9 hidden layers and 100 neurons in 7 hidden layers for groups 1, 2, and 3, respectively, outperformed the NLS and NLME models. The root mean square error for the DLA models ranged from 1.939 to 3.887 m. The results also showed that using height predicted by the DLA models for aboveground biomass estimation brought about more than 30％ reduction in error relative to NLS and NLME. Conse-quently, minimal errors were created in aboveground bio-mass estimation compared to those of the classical methods.
文献关键词：
中图分类号：
作者姓名：
Friday Nwabueze Ogana;Ilker Ercanli
作者机构：
Department of Social and Environmental Forestry,Faculty of Renewable Natural Resources,University of Ibadan,IbadanOyo 200284,Nigeria;Department of Forest Engineering,Faculty of Forestry,?ankiri Karatekin University,?ankiri 18200,Turkey
文献出处：
引用格式：
[1]Friday Nwabueze Ogana;Ilker Ercanli-.Modelling height-diameter relationships in complex tropical rain forest ecosystems using deep learning algorithm)[J].林业研究（英文版）,2022(03):883-898
A类：
NLME
B类：
Modelling,diameter,relationships,complex,tropical,forest,ecosystems,using,deep,learning,algorithm,remains,challenge,because,characteristics,multi,species,layers,indeterminate,age,composition,Effective,modelling,such,required,innovative,techniques,improve,prediction,heights,aboveground,biomass,estimations,Therefore,this,study,DLA,models,artificial,intelligence,were,trained,predicting,Nigeria,data,consisted,individual,trees,repre,senting,measured,from,sample,plots,means,clustering,was,used,classify,into,three,groups,ratios,each,which,beast,quadratic,number,input,variables,Predictions,by,compared,those,developed,nonlinear,least,squares,NLS,mixed,effects,different,evaluation,statistics,equivalence,test,In,addition,predicted,estimate,results,showed,that,neurons,hidden,respectively,outperformed,root,ranged,also,brought,about,more,than,reduction,relative,Conse,quently,minimal,errors,created,classical,methods
AB值：
0.453327
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
