Modeling of stem form and volume through machine learning

Schikowski, Ana Beatriz; Côrte, Ana Paula Dalla; Ruza, Marieli Sabrina; Sanquetta, Carlos Roberto; Montaño, Razer Anthom Nizer Rojas

doi:10.1590/0001-3765201820170569

Cited by 14 publications

(13 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

Section: Methodsmentioning

confidence: 99%

“…Among the many existing models for expressing wood volume as a function of diameter and height. The model proposed by Schumacher and Hall [8] is one of the most widespread in the forestry area due to its statistical properties since it almost always results in unbiased estimates [29,37,43]. TVb and TVw = total volume with and without bark; V5b and V5w = volume with and without bark up to the commercial diameter of 5 cm; V10b and V10w = volume with and without bark up to the commercial diameter of e 10 cm; V15b and V15w = volume with and without bark up to the commercial diameter of 15 cm; V20b and V20w = volume with and without bark up to the commercial diameter of 20 cm.…”

Section: Schumacher and Hall Modelmentioning

confidence: 99%

“…In general, estimators of volumetric and multi-volume models are obtained by regression techniques [6,14,17,20,24]. However, Artificial Neural Networks (ANNs) is an alternative that has been widespread in forest management to obtain tree volume estimates [5,16,[25][26][27][28][29][30][31][32][33]. ANNs training provides linear and non-linear models based on mathematical estimates obtained identically to the logic of human reasoning [34].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-volume modeling of Eucalyptus trees using regression and artificial neural networks

et al. 2020

View full text Add to dashboard Cite

The stem volume of commercial trees is an important variable that assists in decision making and economic analysis in forest management. Wood from forest plantations can be used for several purposes, which makes estimating multi-volumes for the same tree a necessary task. Defining its exploitation and use potential, such as the total and merchantable volumes (up to a minimum diameter of interest), with or without bark, is a possible work. The goal of this study was to use different strategies to model multi-volumes of the stem of eucalyptus trees. The data came from rigorous scaling of 460 felled trees stems from four eucalyptus clones in high forest and coppice regimes. The diameters were measured at different heights, with the volume of the sections obtained by the Smalian method. Data were randomly separated into fit and validation data. The single multi-volume model, volume-specific models, and the training of artificial neural networks (ANNs) were fitted. The evaluation criteria of the models were: coefficient of determination, root mean square error, mean absolute error, mean bias error, as well as graphical analysis of observed and estimated values and distribution of residuals. Additionally, the t-test (α = 0.05) was performed between the volume obtained in the rigorous scaling and estimated by each strategy with the validation data. Results showed that the strategies used to model different tree stem volumes are efficient. The actual and estimated volumes showed no differences. The multi-volume model had the most considerable advantage in volume estimation practicality, while the volumespecific models were more efficient in the accuracy of estimates. Given the conditions of this study, the ANNs are more suitable than the regression models in the estimation of multivolumes of eucalyptus trees, revealing greater accuracy and practicality.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Schumacher and Hall Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-volume modeling of Eucalyptus trees using regression and artificial neural networks

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Among the tested machine learning methods, RF was slightly better than the other methods and its results were similar to the results obtained with multiple linear regression. The assessment of ANN, k nearest neighbors, and RF for modeling trunk shape and volume in black wattle plantation, [18] showed that ANN and RF presented the best results, with RMSE of 8% and 8.4%, respectively, against the RMSE of 9.15% for the polynomial model. The authors concluded that the machine learning techniques are appropriate for forest modeling, however, their use should be cautious because of the greater possibility of overtraining and overfitting.…”

Section: Introductionmentioning

confidence: 99%

Identification of Significative LiDAR Metrics and Comparison of Machine Learning Approaches for Estimating Stand and Diversity Variables in Heterogeneous Brazilian Atlantic Forest

et al. 2021

View full text Add to dashboard Cite

Data collection and estimation of variables that describe the structure of tropical forests, diversity, and richness of tree species are challenging tasks. Light detection and ranging (LiDAR) is a powerful technique due to its ability to penetrate small openings and cracks in the forest canopy, enabling the collection of structural information in complex forests. Our objective was to identify the most significant LiDAR metrics and machine learning techniques to estimate the stand and diversity variables in a disturbed heterogeneous tropical forest. Data were collected in a remnant of the Brazilian Atlantic Forest with different successional stages. LiDAR metrics were used in three types of transformation: (i) raw data (untransformed), (ii) correlation analysis, and (iii) principal component analysis (PCA). These transformations were tested with four machine learning techniques: (i) artificial neural network (ANN), ordinary least squares (OLS), random forests (RF), and support vector machine (SVM) with different configurations resulting in 27 combinations. The best technique was determined based on the lowest RMSE (%) and corrected Akaike information criterion (AICc), and bias (%) values close to zero. The output forest variables were mean diameter at breast height (MDBH), quadratic mean diameter (QMD), basal area (BA), density (DEN), number of tree species (NTS), as well as Shannon–Waver (H’) and Simpson’s diversity indices (D). The best input data were the new variables obtained from the PCA, and the best modeling method was ANN with two hidden layers for the variables MDBH, QMD, BA, and DEN while for NTS, H’and D, the ANN with three hidden layers were the best methods. For MDBH, QMD, H’and D, the RMSE was 5.2–10% with a bias between −1.7% and 3.6%. The BA, DEN, and NTS were the most difficult variables to estimate, due to their complexity in tropical forests; the RMSE was 16.2–27.6% and the bias between −12.4% and −0.24%. The results showed that it is possible to estimate the stand and diversity variables in heterogeneous forests with LiDAR data.

show abstract

“…Estudos a respeito da espécie acácia-negra apresentam-se em certos trabalhos como: Schneider et al (2000), Schneider;Tonini (2003), Sanquetta et al (2015c), Sanquetta et al (2016b) e Schikowski et al (2018). Demonstrando a importância da espécie e de se abranger maiores conhecimentos sobre acácia-negra.…”

Section: Introductionunclassified

Modelagem Volumétrica De Árvores De Acácia-Negra Em Povoamentos De Regiões Do Rio Grande Do Sul

Martins¹,

Ribeiro²,

Padilha³

et al. 2020

BIOFIX

View full text Add to dashboard Cite

reafirmar-se métodos e técnicas para mensurar volume e buscar melhores informações para as variáveis dendrométricas. A espécie acácia-negra (Acacia mearsii De Wild.) é reconhecida no sul do Brasil como uma espécie de alto valor comercial, apresentando a quarta maior área plantada de povoamentos florestais no Rio Grande do Sul., dessa forma, estudos a respeito da espécie são de grande importância para o setor florestal. O presente trabalho visou à obtenção de estimativas volumétricas individuais para árvores de acácia negra. Os modelos propostos por Hohenadl-Krenn. Kopesky-Gehrhardt, Spurr, Schumacher-Hall (não linear), Spurr (não linear), State (Australia) e Meyer foram ajustados. Foram empregados dados de árvores de acácia-negra com idades entre 1 e 10,75 anos, provenientes de um experimento nas regiões de Cristal, Encruzilhada do Sul e Piratini, estado do Rio Grande do Sul. Os dados foram divididos em 4 grupos distintos, de acordo com sua fase de crescimento (jovem, média-inicial, média-avançada e madura). Utilizou-se de 550 árvores para o ajuste de modelos, além de 30 indivíduos de cada grupo, previamente separados de maneira aleatória, para a validação do modelo de melhor desempenho. Os ajustes foram avaliados pelos seguintes critérios: erro padrão da estimativa em porcentagem (Syx%), coeficientes de determinação múltiplo ajustados (R²aj) e gráficos de dispersão dos resíduos. Os modelos não lineares (Spurr e Schumacher-Hall) foram os que melhor se ajustaram aos dados em todas fases de crescimento, sendo o modelo proposto por Spurr não-linear para a classe Jovem e Schumacher-Hal não-linear para as demais classes de idades foram os que apresentaram os melhores desempenhos, com Syx% variando de 2,87% a 4,48% e R²aj entre 0,9742 e 0,9974. Sua validação apresentou resultados satisfatórios para o erro padrão da estimativa e para o teste de Qui-quadrado, com valores de Syx% variando entre 6,43% e 7,57%, enquanto χ2 variou de 0,0019 a 0,0126. Sendo assim, observou-se que os modelos não lineares apresentaram resultados superiores aos obtidos com os modelos lineares.

show abstract

Modeling of stem form and volume through machine learning

Cited by 14 publications

References 27 publications

Multi-volume modeling of Eucalyptus trees using regression and artificial neural networks

Multi-volume modeling of Eucalyptus trees using regression and artificial neural networks

Identification of Significative LiDAR Metrics and Comparison of Machine Learning Approaches for Estimating Stand and Diversity Variables in Heterogeneous Brazilian Atlantic Forest

Modelagem Volumétrica De Árvores De Acácia-Negra Em Povoamentos De Regiões Do Rio Grande Do Sul

Contact Info

Product

Resources

About