Estimation of forest trees biomass for various purposes is fundamental and substantia l. One method of estimating biomass uses allometric equations that limit the normality of variables and the homogeneity of variances. In this study, artificial neural networks were used as an alternative method to increase biomass estimation accuracy. Fifty three sprout chumps of Brant's Oak (Quercus brantii Lindl) were randomly selected from the Melah Shabanan of Khorramabad in Iran. Diameter at knee height, diameter at breast height, crown diameter, number of sprouts, and height of trees were measured. To calculate the dry weight of the biomass, adisk3-5cm from the trunk and crown was separated and weighed, and with the ratio of dry weight to fresh weight, the dry weight of the crown, trunk, and aboveground biomass of the trees was calculated. Modeling the relationships between variables with linear and nonlinear regression equations and Multilayer Perceptron and Radial Basis Function neural networks showed that both neural networks could increase the coefficient of determination to R2=0.98 and R2=0.96 and reduce the error to RMSE%=11.6 and RMSE%=16.9 and thus the neural network models can increase the quality forest biomass estimates are compared with allometric equations.
| Published in | American Journal of Neural Networks and Applications (Volume 11, Issue 2) |
| DOI | 10.11648/j.ajnna.20251102.14 |
| Page(s) | 66-87 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2025. Published by Science Publishing Group |
MLP and RBF Network, Linear and Nonlinear Regression Equations, Aboveground Biomass
| [1] | Alvarez E, Duque A, Saldarriaga Jet al (2012) Tree above-ground biomass allometries for carbon stocks estimation in the natural forests of Colombia. For EcoloManag 267: 297-308. |
| [2] | Ashraf MI, Zhao Z, Bourque CPA, MacLean DA, Meng FR (2013) Integrating biophysical controls in forest growth and yield predictions with artificial intelligence technology. Can J For Res43(12): 1162-1171. |
| [3] | Bayat M, Bettinger P, Heidari S et al (2020) Estimation of tree heights in an uneven-aged, mixed forest in northern Iran using artificial intelligence and empirical models. Forests 11(3): 324. |
| [4] | Bayat M, Bettinger P, Hassani M, Heidari S (2021) Ten-Year Estimation of Oriental Beech (Fagus orientalisLipsky) Volume Increment in Natural Forests: A Comparison of an Artificial Neural Networks Model, Multiple Linear Regression and Actual Increment. Forestry 94: 598-609. |
| [5] | Benediktsson JA, Swain PH, Erosy OK (1990) Neural network approaches versus statistical methods in classification of multisource remote Sensing data. IEEE Transa. On GeoscieRemo Sensi 28(4): 5 40-551. |
| [6] | Cointe A, Rouger F (2005) Improving the evaluation of multiple-dowel-type connection strength. Wood SciTechnol 39: 259‑269. |
| [7] | Coulson RN, Folse LJ, Loh DK (1987) Artificial intelligence and natural resource management. Science 237: 262-267. |
| [8] | Dai S, Zheng X, Gao Let al (2020) Improving maps of forest aboveground 1 biomass: A combined approach using machine learning with a spatial statistical model. Biogeos Discuss (preprint). |
| [9] | Diamantopoulou MJ (2005) Artificial neural networks as an alternative tool in pine bark volume estimation. ComputAnd Electron In Agricul 48: 235-244. |
| [10] | Diamantopoulou MJ, Özçelik R, Crecente-Campo F, Eler U (2015) Estimation of Weibull function parameters for modelling tree diameter distribution using least squares and artificial neural networks methods. BiosysEng133: 33-45. |
| [11] | Dimobe K, Mensah S, Goetze Det al (2018) Aboveground biomass partitioning and additive models for Com- bretumglutinosumand Terminalia laxiflorain West Africa. BiomBioen 115: 151-159. |
| [12] | Ekoungoulou R, Liu X, Ifo S, LoumetoJ, Folega F (2014) Carbon stock estimation in secondary forest and gallery forest of Congo using allometric equations. Int J SciTechnol Res 3: 465-474. |
| [13] | Forester D, Dumbrell I, Elms Set al (2021) Can crown variable increase the generality of individual tree biomass equations? Trees 35: 15-26. |
| [14] | Gomez-Garcia E, Biging G, Garcia-Villabrlille JDet al (2015) Cumulative continuous predictions for bole and aboveground woody biomass in Eucalyptus globulus plantations in northwestern Spain. BiomBioene 77: 155-164. |
| [15] | Jain AK, Mao J, Mohiuddin K (1996) Artificial Neural Networks: a tutorial. IEEE Comput29: 31-44. |
| [16] | Ketterings QM, Coe R, van Noordwijk M, Ambagau Y, Palm CA (2001) Reducing uncertainty in the use of allometric biomass equations for predicting aboveground tree biomass in mixed secondary forests. Forest EcolManag 146: 199-209. |
| [17] | Kuyah S, Dietz J, Muthuri C, van Noordwijk M, Neufeldt H (2013) Allometry and partitioning of above-and below-ground biomass in farmed eucalyptus species dominant in Western Kenyan agricultural landscapes. Biomass Bioenergy 55: 276-284. |
| [18] | Iranmanesh Y, Sagheb-Talebi K, Sohrabi H (2014) Biomass and carbon stocks of Brant's oak (Quercusbrantii Lindl.) in two vegetation forms in Lordegan, Chaharmahal&Bakhtiari forests. IranJForPopl Res 22(4): 749-762 (in Persian). |
| [19] | Lai J, Yang B, Lin D, Kerkhoff AJ, Ma K (2013) The allometry of coarse root biomass: log-transformed linear regression or nonlinear regression? PLoS One 8(10): e77007. |
| [20] | Löf M, Madsen P, Metslaid M, Witzell J, Jacobs DF (2019) Restoring forests: regeneration and ecosystem function for the future. Ne. For 50: 139-151. |
| [21] | Leduc DJ, Matney TJ, Belli KL, Baldwin VC (2001) Predicting Diameter Distributions of Longleaf Pine Plantations: A Comparison between Artificial Neural Networks and other accepted methodologies.Sout Res Stat Tech Rep, RS 25: 1-17. |
| [22] | Heydari MM, Poorbabaei H, Rostami Tet al (2013) Plant species in Oak (Quercusbrantii Lindl.) understory and their relationship with physical and chemical propertiesof soil in different altitude classes in the Arghvan valley protected area. Iran Casp J EnvirScie11: 97-110. |
| [23] | Houghton RA, Goodale CL (2004) Effects of land- use change on the carbon balance of terrestrial ecosystems, in Ecosystems and Land use Change. DeFries R, AsnerG, HoughtonRA (Eds). Book series: American Geophysical union. |
| [24] | Mahdavi A, Saidi S, Iranmanesh Y, Naderi M (2020) Biomass and carbon stocks in three types of Persian oak (Quercusbrantii var. persica) of Zagros forests in a semi-arid area. Iran JAr La 12: 766-774. |
| [25] | Mascaro J, Litton CM, Hughes RM, Uowolo A, Schnitzer SA (2014) Is logarithmic transformation necessary in allometry? Ten, one-hundred, one-thousand times yes. Biol J Linn Soc 111: 230-233. |
| [26] | Medhurst JL, Battaglia M, Cherry ML, White DA, Beadle CL (1999) Allometric relationships for Eucalyptus nitens (Deane and Maiden) Maiden plantations. Trees 14(2): 91-101. |
| [27] | Mukuralinda A, Kuyah S, Ruzibiza Met al (2021) Allometricequations, wood density and partitioning of aboveground biomass in the arboretum of Ruhande, Rwanda. Tre, Fore and Peopl3(4): 100050. |
| [28] | Navar J (2009) Allometric equations for tree species and carbon stocks for forest of northwestern Mexico. For EcolManag 257: 427-434. |
| [29] | Norusis M (2007) SPSS Neural Networks 17.0. SPSS Inc. Chicago IL. |
| [30] | Osborne JW, Waters E (2002) Four assumptions of multiple regression that researchers should always test. Pract Asses Res Evalu8(2). |
| [31] | Özçelik R, Diamantopoulou MJ, Eker M, Gürlevık N (2017) Artificial Neural Network Models: An Alternative Approach for Reliable Aboveground Pine Tree Biomass Prediction. For Sci63(3): 291-302. |
| [32] | Özçelik R, Diamantopoulou MJ, Crecente-Campo F, Eler U (2013) Estimating Crimean juniper tree height using nonlinear regression and artificial neural network models. For EcolManag306: 52-60. |
| [33] | Özçelik R, Diamantopoulou MJ, Brooks JR, Wiant HV (2010) Estimating tree bole volume using artificial neural network models for four species in Turkey. J Envir Manag. 91(3): 742-753. |
| [34] | Packard GC (2013) Is logarithmic transformation necessary in allometry? Biol J Linn Soc 109: 476-486. |
| [35] | Peng C, Wen X (1999) Recent applications of artificial neural networks in forest resource management: an overview. Tech Rep WS-99-07, American Association for Artificial Intelligence. |
| [36] | Picard N, Rutishauser E, Ploton P, Ngomanda A, Henry M (2015) Should tree biomassallometry be restricted to power models?. For EcolManag 353: 156-163. |
| [37] | Porte A, Trichet P, Bert D, Loustau D (2002) Allometric relationships for branch and tree woody biomass of Maritime pine (Pinuspinaster At¨). For Ecol Manage 158(1): 71-83. |
| [38] | SaghebTalebi K, Sajedi T, Pourhashemi T (2014) Forest of Iran, a Treasure from the Past, a Hope for the Future. Springer press, New York, USA. |
| [39] | Shafabakhsh GH, Fathi F, Zayarzaeh A (2010) Improvement of road eventful points prioritization by artificial neural network. J Model Eng 8(20): 71-81. |
| [40] | Sileshi GW (2014) A critical review of forest biomass estimation models, common mistakes and corrective measures. Fore EcolManag 329: 237-254. |
| [41] | Tiryaki S, Aydin A (2014) An artificial neural network model for predicting compression strength of heat treated woods and comparison with a multiple linear regression model. Constru Build Materia 62: 102-108. |
| [42] | Vahedi AA (2016) Artificial neural network application in comparison with modeling allometric equations for predicting above-ground biomass in the Hyrcanian mixed-beech forests of Iran. BiomaBioen 88: 66-76. |
| [43] | Wang L, Xing Y (2008) Remote sensing estimation of natural forest biomass based on an artificial neural network. J ApplEcol19(2): 261-266 (in Chinese). |
| [44] | Xiao X, White E, Hooten M, Durham M (2011) On the use of log-transformation vs. nonlinear regression for analyzing biological power laws. Ecol 92(10): 1887-1894. |
| [45] | Zewdie M, Olsson M, Verwijst T (2009) Above-ground biomass production and allometric relations of Eucalyptus globulusLabill. coppice plantations along a chronose- quence in the central highlands of Ethiopia. BiomaBioen 33: 421-428. |
APA Style
Fallah, S., Soosani, J., Naghavi, H., Mofrad, M. Y. (2025). Improving the Efficiency of Allometric Equations Using Artificial Neural Networks in Coppicing Stands of Brant's Oak. American Journal of Neural Networks and Applications, 11(2), 66-87. https://doi.org/10.11648/j.ajnna.20251102.14
ACS Style
Fallah, S.; Soosani, J.; Naghavi, H.; Mofrad, M. Y. Improving the Efficiency of Allometric Equations Using Artificial Neural Networks in Coppicing Stands of Brant's Oak. Am. J. Neural Netw. Appl. 2025, 11(2), 66-87. doi: 10.11648/j.ajnna.20251102.14
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ajnna.20251102.14,
author = {Saman Fallah and Javad Soosani and Hamed Naghavi and Mohsen Yousofvand Mofrad},
title = {Improving the Efficiency of Allometric Equations Using Artificial Neural Networks in Coppicing Stands of Brant's Oak
},
journal = {American Journal of Neural Networks and Applications},
volume = {11},
number = {2},
pages = {66-87},
doi = {10.11648/j.ajnna.20251102.14},
url = {https://doi.org/10.11648/j.ajnna.20251102.14},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ajnna.20251102.14},
abstract = {Estimation of forest trees biomass for various purposes is fundamental and substantia l. One method of estimating biomass uses allometric equations that limit the normality of variables and the homogeneity of variances. In this study, artificial neural networks were used as an alternative method to increase biomass estimation accuracy. Fifty three sprout chumps of Brant's Oak (Quercus brantii Lindl) were randomly selected from the Melah Shabanan of Khorramabad in Iran. Diameter at knee height, diameter at breast height, crown diameter, number of sprouts, and height of trees were measured. To calculate the dry weight of the biomass, adisk3-5cm from the trunk and crown was separated and weighed, and with the ratio of dry weight to fresh weight, the dry weight of the crown, trunk, and aboveground biomass of the trees was calculated. Modeling the relationships between variables with linear and nonlinear regression equations and Multilayer Perceptron and Radial Basis Function neural networks showed that both neural networks could increase the coefficient of determination to R2=0.98 and R2=0.96 and reduce the error to RMSE%=11.6 and RMSE%=16.9 and thus the neural network models can increase the quality forest biomass estimates are compared with allometric equations.
},
year = {2025}
}
TY - JOUR T1 - Improving the Efficiency of Allometric Equations Using Artificial Neural Networks in Coppicing Stands of Brant's Oak AU - Saman Fallah AU - Javad Soosani AU - Hamed Naghavi AU - Mohsen Yousofvand Mofrad Y1 - 2025/12/03 PY - 2025 N1 - https://doi.org/10.11648/j.ajnna.20251102.14 DO - 10.11648/j.ajnna.20251102.14 T2 - American Journal of Neural Networks and Applications JF - American Journal of Neural Networks and Applications JO - American Journal of Neural Networks and Applications SP - 66 EP - 87 PB - Science Publishing Group SN - 2469-7419 UR - https://doi.org/10.11648/j.ajnna.20251102.14 AB - Estimation of forest trees biomass for various purposes is fundamental and substantia l. One method of estimating biomass uses allometric equations that limit the normality of variables and the homogeneity of variances. In this study, artificial neural networks were used as an alternative method to increase biomass estimation accuracy. Fifty three sprout chumps of Brant's Oak (Quercus brantii Lindl) were randomly selected from the Melah Shabanan of Khorramabad in Iran. Diameter at knee height, diameter at breast height, crown diameter, number of sprouts, and height of trees were measured. To calculate the dry weight of the biomass, adisk3-5cm from the trunk and crown was separated and weighed, and with the ratio of dry weight to fresh weight, the dry weight of the crown, trunk, and aboveground biomass of the trees was calculated. Modeling the relationships between variables with linear and nonlinear regression equations and Multilayer Perceptron and Radial Basis Function neural networks showed that both neural networks could increase the coefficient of determination to R2=0.98 and R2=0.96 and reduce the error to RMSE%=11.6 and RMSE%=16.9 and thus the neural network models can increase the quality forest biomass estimates are compared with allometric equations. VL - 11 IS - 2 ER -
Forestry Agriculture and Natural Resources Faculty, Lorestan University, Khorramabad, Iran
Forestry Agriculture and Natural Resources Faculty, Lorestan University, Khorramabad, Iran
Forestry Agriculture and Natural Resources Faculty, Lorestan University, Khorramabad, Iran
Forestry Agriculture and Natural Resources Faculty, Lorestan University, Khorramabad, Iran
Information