Comparison of Modeling Approaches for the Height–diameter Relationship: An Example with Planted Mongolian Pine (Pinus sylvestris var. mongolica) Trees in Northeast China DOI Open Access

Fu-Cheng Lin,

Longfei Xie, Yuanshuo Hao

et al.

Forests, Journal Year: 2022, Volume and Issue: 13(8), P. 1168 - 1168

Published: July 23, 2022

In the process of modeling height–diameter models for Mongolian pine (Pinus sylvestris var. mongolica), fitting abilities six were compared: (1) a basic model with only diameter at breast height (D) as predictor (BM); (2) plot-level mixed-effects (BMM); (3) quantile regression nine quantiles based on BM (BQR); (4) generalized stand or competition covariates (GM); (5) (GMM); and (6) GM (GQR). The prediction bias developed was assessed in cases total tree (H) predictions calibration without calibration. results showed that extending Chapman–Richards function dominant relative size individual trees improved accuracy. Prediction accuracy significantly when H calibrated all models, among which GMM performed best because random effect provided lowest bias. When least 8% selected from new plot, relatively accurate low-cost obtained by models. predicting values stand, BMM preferable if there available measurements calibration; otherwise, GQR choice.

Language: Английский

Incorporating stand parameters in nonlinear height-diameter mixed-effects model for uneven-aged Larix gmelinii forests DOI Creative Commons
Mahamod Ismail, Tika Ram Poudel, Amal E. Ali

et al.

Frontiers in Forests and Global Change, Journal Year: 2025, Volume and Issue: 7

Published: Jan. 7, 2025

Tree attributes, such as height (H) and diameter at breast (D), are essential for predicting forest growth, evaluating stand characteristics developing yield models sustainable management. Measuring tree H is particularly challenging in uneven-aged forests compared to D. To overcome these difficulties, the development of updated reliable H-D crucial. This study aimed develop robust Larix gmelinii by incorporating variables. The dataset consisted 7,069 trees sampled from 96 plots Northeast China, encompassing a wide range densities, age classes, site conditions. Fifteen widely recognized nonlinear functions were assessed model relationship effectively. Model performance was using root mean square error (RMSE), absolute (MAE), coefficient determination (R 2 ). Results identified Ratkowsky (M8) best performer, achieving highest R (0.74), lowest RMSE (16.47%) MAE (12.50%), statistically significant regression coefficients (p < 0.05). Furthermore, M8 modified into 5 generalized (GMs) adding stand-variables (i.e., height, volume their combination), results indicate that GM2 0.82% 13.7%. We employed mixed-effects modeling approach with both fixed random effects account variations individual plot level, enhancing predictive accuracy. explained 71% variability trends residuals. calibrated response calibration method, through EBLUP theory. Our findings suggest stand-level variables representing plot-specific can further improve fit mixed- models. These advancements provide authorities enhanced tools supporting

Language: Английский

Citations

2
Mixed-effects generalized height–diameter model for young silver birch stands on post-agricultural lands DOI Creative Commons
Karol Bronisz, Lauri Mehtätalo

Forest Ecology and Management, Journal Year: 2020, Volume and Issue: 460, P. 117901 - 117901

Published: Jan. 23, 2020

The purpose of creating regression equations is often to predict unmeasured features based upon more easily obtainable ones. Species-specific height–diameter (H–D) models trees are an example this situation and can be defined as either simple or generalized. Simple H–D express height a function tree diameter at the breast height. They applicable without additional measurement but do not take properly into account variability in H-D relationship between stands. Meanwhile, generalized also include stand-level predictors. data sets characterized by grouped structure. mixed-effects modeling approach mainstream method employed for these types forestry data. In study, we created model young silver birch stands on post-agricultural lands central Poland. This was chosen from among 11 nonlinear goodness fit residual behavior. We accounted two predictors that did require measurements beyond height: quadratic mean basal area. Fixed- random-effect predictions were then calculated illustrate increases number measured improves predictions. Moreover, gain predictive power largest if extreme (i.e., extrema range) used prediction.

Language: Английский

Citations

75
A generalized nonlinear mixed-effects height–diameter model for Norway spruce in mixed-uneven aged stands DOI
Albert Ciceu, Juan García-Duro,

Ioan Seceleanu

et al.

Forest Ecology and Management, Journal Year: 2020, Volume and Issue: 477, P. 118507 - 118507

Published: Aug. 20, 2020

Language: Английский

Citations

45
Artificial neural networks as an alternative method to nonlinear mixed-effects models for tree height predictions DOI
Mitja Skudnik, Jernej Jevšenak

Forest Ecology and Management, Journal Year: 2022, Volume and Issue: 507, P. 120017 - 120017

Published: Jan. 13, 2022

Language: Английский

Citations

23
Modelling height-diameter relationships in complex tropical rain forest ecosystems using deep learning algorithm DOI Creative Commons
Friday Nwabueze Ogana, İlker Ercanlı

Journal of Forestry Research, Journal Year: 2021, Volume and Issue: 33(3), P. 883 - 898

Published: July 24, 2021

Abstract Modelling tree height-diameter relationships in complex tropical rain forest ecosystems remains a challenge because of characteristics multi-species, multi-layers, and indeterminate age composition. Effective modelling such systems required innovative techniques to improve prediction heights for use aboveground biomass estimations. Therefore, this study, deep learning algorithm (DLA) models based on artificial intelligence were trained predicting Nigeria. The data consisted 1736 individual trees representing 116 species, measured from 52 0.25 ha sample plots. A K-means clustering was used classify the species into three groups ratios. DLA each species-group which diameter at beast height, quadratic mean number per as input variables. Predictions by compared with those developed nonlinear least squares (NLS) mixed-effects (NLME) using different evaluation statistics equivalence test. In addition, predicted estimate biomass. results showed that 100 neurons 6 hidden layers, 9 layers 7 1, 2, 3, respectively, outperformed NLS NLME models. root square error ranged 1.939 3.887 m. also height estimation brought about more than 30% reduction relative NLME. Consequently, minimal errors created classical methods.

Language: Английский

Citations

32
Regional height growth models for Scots pine in Poland DOI Creative Commons
Jarosław Socha,

Luiza Tymińska-Czabańska,

Karol Bronisz

et al.

Scientific Reports, Journal Year: 2021, Volume and Issue: 11(1)

Published: May 14, 2021

Site productivity remains a fundamental concern in forestry as significant driver of resource availability for tree growth. The site index (SI) reflects the overall impact all environmental factors that determine height growth and is most commonly used indirect proxy forest estimated using stand age height. SI concept challenges are local variations climate, soil, genotype-environmental interactions lead to variable patterns among ecoregions cause inappropriate estimation productivity. Developing regional models allow us more appropriately. This study aimed develop Scots pine Poland, considering natural region effect. For modelling, we trajectory data 855 sample trees, representing entire range geographic locations conditions Poland. We compared development nonlinear-fixed-effects (NFE) nonlinear-mixed-effects (NME) modelling approaches. Our results indicate slightly better fit model built NFE approach. showed differences between regions I, II, III located northern Poland IV, V, VI southern NME developed show pines revealed acknowledgement independent could improve prediction quality estimation. Differences climate soil distinguish affect patterns. Therefore, extending this research directly describe with variables, such properties, topography, can provide valuable management information.

Language: Английский

Citations

30
Mixed-effects generalized height-diameter model: A tool for forestry management of young sweet chestnut stands DOI Creative Commons
Maria do Sameiro Patrício, Cremildo Riba Gouveia Dias,

Luís Nunes

et al.

Forest Ecology and Management, Journal Year: 2022, Volume and Issue: 514, P. 120209 - 120209

Published: April 8, 2022

Height is a key variable for forest management. However, tree height measurements are expensive and time-consuming, requiring more effort to measure in the than diameter breast measurements. Indeed, height-diameter (h-d) models increasingly used overcome difficulty measuring heights. Therefore, accurate h-d needed. The mixed-effects modeling approach mainstream method estimate models. This technique was model relationship first 24 years of growth sweet chestnut (Castanea sativa Mill.) high-forest stands timber production. A dataset 10,868 observations 57 plots local-inventory data were considered individually. Simple considering grouping structure (plot-level) obtained, generalized developed by expanding fixed simple with stand-level variables. Several alternative forms tested terms accuracy, applicability measurement effort. Different alternatives calibrated predictions at plot level analyzed, considerations on trade-off between easy-to-use equations field practice high-accuracy inventory tested. selected Richards M1a simultaneously provides random parameters from variables using same model. analysis showed that inclusion dominant as predictors improved accuracy Draudt one best approaches improve tree-level prediction mixed-effects. applied quite feasible 100–500 m2 plots. use these suggested calibration process will significantly reduce costs fieldwork teams heights management planning while ensuring high accuracy. greater density and, therefore, young adult stands.

Language: Английский

Citations

20
Comparing Traditional Methods and Modern Statistical Techniques for Tree Height Prediction DOI Open Access

Jakob Hobiger,

Ursula Laa, Sonja Vospernik

et al.

Forests, Journal Year: 2025, Volume and Issue: 16(2), P. 271 - 271

Published: Feb. 5, 2025

Forest mensuration is important to gain knowledge and information about forest stands. Because tree height often proves more difficult measure than diameter, different statistical models are used for their estimation instead. In this paper, the data of 986 spruce trees (Picea abies KARST. (L.)), measured in federal states Salzburg Tyrol (Austria), were train compare random with traditional approaches such as linear non-linear mixed a classical uniform curve. For model comparison, RMSE, percent bias, bias used. further visualization differences, residual plots, partial dependence conditional plots shown. The results show that (RMSE 2.23 m) can compete methods, 2.14 2.24 or curves 2.92 m), but not able outperform those especially when it comes extrapolation prediction areas where training sparse available. Furthermore, incorporation additional covariates improve certain models.

Language: Английский

Citations

0
A study on the variation of knot width in Larix olgensis based on a Mixed-Effects model DOI
Zelin Li, Weiwei Jia, Fengri Li

et al.

Computers and Electronics in Agriculture, Journal Year: 2025, Volume and Issue: 234, P. 110215 - 110215

Published: March 10, 2025

Language: Английский

Citations

0
Nonlinear multilevel seemingly unrelated height-diameter and crown length mixed-effects models for the southern Transylvanian forests, Romania DOI Creative Commons
Albert Ciceu, Ștefan Leca, Ovidiu Badea

et al.

Forest Ecosystems, Journal Year: 2025, Volume and Issue: unknown, P. 100322 - 100322

Published: March 1, 2025

Language: Английский

Citations

0