Şahin, AbbasÖzdemir, Gafura AylakOral, OkanAylak, Batin Latifİnce, MuratÖzdemir, Emrah2025-02-062025-02-062023Şahin, A., Özdemir, Gafura A., Oral, O., Aylak, Batin L., İnce, M., Özdemir, E. (2023). Estimation of tree height with machine learning techniques in coppice-originated pure sessile oak (Quercus petraea (Matt.) Liebl.) stands. Scandinavian Journal of Forest Research, 38 (1-2), 87-96.https://hdl.handle.net/20.500.12846/1526In this study, in order to estimate total tree height, three di?erent model structures with di?erentinput variables were produced through the use of 872 tree data points obtained from di?erentdevelopment stages and sites in coppice-originated pure sessile oak (Quercus petraea [Matt.] Liebl.)stands. These models were ?tted with machine learning techniques such as arti?cial neuralnetworks (ANNs), decision trees, support vector machines, and random forests. In addition, themodel based on DBH was ?tted and its parameters were calculated using the ordinary nonlinearleast squares method and this model was selected as the best model in Model 1. In other modelstructures, ANN model was chosen as the best estimation method based on the relative rankingmethod in which the goodness of ?t statistics of the estimation methods were evaluated together.The inclusion of stand variables in addition to the DBH measurement in the model increased theR2 by about 36% and reduced the error rate by 55%.eninfo:eu-repo/semantics/openAccessArtificial neural networksDBHHeight-diametermodelRandom forestArticle381-210.1080/02827581.2023.21680448796WOS:0009197462000012-s2.0-85147021304