Artificial Neural Network Models: An Alternative Approach for Reliable Aboveground Pine Tree Biomass Prediction

Özçelık, Ramazan; Diamantopoulou, Maria J.; Eker, Mehmet; Gürlevık, Nevzat

doi:10.5849/forsci.16-006

Cited by 4 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The ML technique is characterized by its outstanding generalization ability and the potential of learning from noisy or incomplete data, by detecting inherent complex nonlinear relationships between output and input variables. Successful effort to produce reliable and accurate models for tree biomass estimation using ML techniques have been previously reported (Guo et al 2012, Ozçelik et al 2017, Malek et al 2019, Güner et al 2022. In addition, Artificial Neural Networks (ANNs) and Support Vector Machines for regression (SVR), have recently gained scientific interest in forestry research (Youquan et al 2012, Ozçelik et al 2013, Binoti et al 2016, Tavares Júnior et al 2019, Bolat et al 2023, thanks to their independence of a priori specifications of the (i) form of an equation describing the ground truth data, (ii) data distribution, and (iii) potential transformations of the variables, which are all to be matched in the case of regression modeling.…”

Section: Introductionmentioning

confidence: 99%

Exploring machine learning modeling approaches for biomass and carbon dioxide weight estimation in Lebanon cedar trees

Diamantopoulou,

Çömez,

Özçelik

et al. 2024

iForest

View full text Add to dashboard Cite

Accurate estimates of total tree biomass are of critical importance to obtain reliable estimation of the carbon dioxide weight sequestered from the atmosphere by trees and forest stands. This information has the potential to guide appropriate forest management decisions which allow for both the improvement of forest sustainability and the implementation of multi-task reforestation designs aimed to mitigate the detrimental effects of climate change. The current laborious and tree-destructive procedures needed to attain such information has led to the development of machine learning (ML) models aimed at providing accurate estimations of the tree biomass sequestering the atmospheric carbon dioxide. We tested the Levenberg-Marquardt artificial neural network and the support vector machine for regression techniques as an alternative to non-linear allometric regression (NLR) modelling approaches commonly used for tree biomass estimation. We tested the developed ML models using primary ground-truth data from the Lebanon cedar forests in the Western Inner Anatolian regions of Turkey, and their predictions were compared to those of NLR models developed using the same dataset. The results showed that the ML approaches outperformed the NLR models in accurately estimating tree biomass and its components (above-and belowground dry biomass, dry branches biomass, etc.), and the support vector regression (SVR) models gave the highest accuracy of estimates. Therefore, the carbon dioxide weight sequestered in Lebanon cedar trees were reliably estimated, with the aim of supporting the best forest management practices to be applied in Lebanon cedar tree stands in Turkey.

show abstract

Section: Introductionmentioning

confidence: 99%

Exploring machine learning modeling approaches for biomass and carbon dioxide weight estimation in Lebanon cedar trees

Diamantopoulou,

Çömez,

Özçelik

et al. 2024

iForest

View full text Add to dashboard Cite

show abstract

“…Alguns estudos vêm demonstrando que as RNA podem ser um método alternativo eficiente nas Ciências Florestais. Como exemplos, as RNA foram aplicadas para obtenção de estimativas de volumes (LEAL, 2015;LACERDA et al, 2017); de biomassa (MONTANO et al, 2017;ÖZÇELIK et al, 2017); de diâmetro à altura do peito (d) a partir de variáveis de sensoriamento remoto ou fatores ambientais (ZHOU et al, 2019); para predições do afilamento do fuste (SCHIKOWSKI et al, 2015;SAKICI & OZDEMIR, 2018); e, até mesmo, para prever as propriedades físicas e mecânicas de madeira termicamente modificada com base na mudança de cor (NASIR et al, 2019).…”

Section: Introductionunclassified

Efeito Do Número De Neurônios Na Camada Oculta Para Relações Hipsométricas De Eucalipto Usando Redes Neurais Artificiais

Bueno

Costa

Cristina

et al. 2020

BIOFIX

View full text Add to dashboard Cite

As redes neurais artificiais têm mostrado performance melhor ou pelo menos similar à dos modelos tradicionais de regressão usados a modelagem florestal. No entanto, deve-se atentar para uma configuração que garanta estimativas acuradas e capacidade de generalização, sendo a quantidade de neurônios na camada oculta uma característica crítica a ser decidida. Assim, o presente estudo buscou encontrar a quantidade ótima de neurônios na camada oculta na modelagem da relação hipsométrica em plantio de Eucalyptus saligna Smith. A base de dados foi subdividida de modo aleatório em 50% para treinamento e 50% para validação do modelo, empregando-se a arquitetura de rede neural Multilayer Perceptron (MLP). No processo de modelagem, considerou-se o diâmetro à altura do peito como variável de entrada e a altura como variável de saída. A quantidade de neurônios na camada oculta foi testada com variação entre 1 a 6. Das seis melhores redes treinadas, aquelas que obtiveram neurônios acima de três na camada oculta tenderam a apresentar overfitting quando aplicados aos dados da validação. Com as diferentes arquiteturas na camada oculta, foi possível obter redes treinadas com coeficiente de correlação (r) variando de 0,61 a 0,73 e raiz quadrada do erro quadrático médio de ±1,28 a 1,48 m. Foram escolhidas as RNA com três neurônios na camada oculta devido a sua simplicidade e pouca diferença de acurácia quando comparadas às obtidas com maior número. A quantidade de neurônios a serem considerados na camada oculta deve ser definida com atenção para que o fenômeno modelado conserve capacidade de generalização.

show abstract

“…As resulted from the relative research through the application of the ANN methodology to real life problems, the most attractive characteristics of ANNs are their ability to learn from noisy data and their potential to accurately describe the behavior of complex non-linear systems. Until now, in the field of forest modelling, the implemented research and the related findings led to the same conclusion, that artificial neural network models (ANNs) can be considered as a significant alternative modeling technique for many characteristics of trees against to classical modeling methods, both in classification tasks (Schmoldt et al 1997;Sarigul et al 2003;Liu et al, 2003;Cosenza et al 2017), and for estimation and prediction problems (Özçelik et al, 2008;Pertsen et al 2010;Leite et al 2011;Soares et al, 2013;Reis et al 2016;Özçelik et al 2017;Ercanli et al, 2018;Monteiro da Silva et al 2018;Zhou et al 2018;Socha et al 2020). Specifically, artificial intelligence has been successfully used for total tree height models construction (Li and Jiang 2010;Diamantopoulou and Özçelik 2012;Özçelik et al 2013;Vieira et al 2018;Thanh et al 2019; Ercanli 2020), as well.…”

mentioning

confidence: 99%

Investigation of parametric and artificial neural network modeling approaches for total tree height prediction in cedar plantations

Karatepe¹,

Diamantopoulou²,

Özçelık³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Background: Height-diameter relationships are of critical importance in tree and stand volume estimation. Stand description, site quality determination and proper forest management decisions originate from reliable stem height predictions. Methods: In the context of this work, the prediction ability of the developed height-diameter models was investigated for cedar (Cedrus libani A. Rich.) plantations in Western Mediterranean Region of Turkey. Towards this direction, parametric modeling methods such as fixed-effects, generalized models, and mixed-effects were evaluated. Furthermore, in an effort to come up with the construction of more reliable stem-height prediction models, artificial neural networks were employed using two different modeling algorithms: the Levenberg-Marquardt and the resilient back-propagation. Results: Taking into account the prediction behavior of each respective modelling strategy while using a new validation data set, the mixed-effects model with calibration using 3 trees for each plot seems to be a reliable alternative to the rest standard modelling approaches given the evaluation statistics regarding the predictions of tree heights. Conclusion: Finally, as for providing the most reliable results as compared to the remaining, the resilient propagation algorithm showed its capability of providing more accurate predictions of the tree stem height and thus it can be a reliable alternative to pre-existing modelling methodologies.

show abstract

Artificial Neural Network Models: An Alternative Approach for Reliable Aboveground Pine Tree Biomass Prediction

Cited by 4 publications

References 0 publications

Exploring machine learning modeling approaches for biomass and carbon dioxide weight estimation in Lebanon cedar trees

Exploring machine learning modeling approaches for biomass and carbon dioxide weight estimation in Lebanon cedar trees

Efeito Do Número De Neurônios Na Camada Oculta Para Relações Hipsométricas De Eucalipto Usando Redes Neurais Artificiais

Investigation of parametric and artificial neural network modeling approaches for total tree height prediction in cedar plantations

Contact Info

Product

Resources

About