Open Access
Issue
Published:
03 September 2018
Artificial neural network models predicting the leaf area index: a case study in pure even-aged Crimean pine forests from Turkey
),
Download citation
438
Views
15
Downloads
20
Crossref
N/A
WoS
19
Scopus
0
CSCD
Leaf Area Index (LAI) is an important parameter used in monitoring and modeling of forest ecosystems. The aim of this study was to evaluate performance of the artificial neural network (ANN) models to predict the LAI by comparing the regression analysis models as the classical method in these pure and even-aged Crimean pine forest stands.
One hundred eight temporary sample plots were collected from Crimean pine forest stands to estimate stand parameters. Each sample plot was imaged with hemispherical photographs to detect the LAI. The partial correlation analysis was used to assess the relationships between the stand LAI values and stand parameters, and the multivariate linear regression analysis was used to predict the LAI from stand parameters. Different artificial neural network models comprising different number of neuron and transfer functions were trained and used to predict the LAI of forest stands.
The correlation coefficients between LAI and stand parameters (stand number of trees, basal area, the quadratic mean diameter, stand density and stand age) were significant at the level of 0.01. The stand age, number of trees, site index, and basal area were independent parameters in the most successful regression model predicted LAI values using stand parameters (Radj.2 = 0.5431). As corresponding method to predict the interactions between the stand LAI values and stand parameters, the neural network architecture based on the RBF 4-19-1 with Gaussian activation function in hidden layer and the identity activation function in output layer performed better in predicting LAI (SSE (12.1040), MSE (0.1223), RMSE (0.3497), AIC (0.1040), BIC (-77.7310) and R2 (0.6392)) compared to the other studied techniques.
The ANN outperformed the multivariate regression techniques in predicting LAI from stand parameters. The ANN models, developed in this study, may aid in making forest management planning in study forest stands.
menu
Artificial neural network models predicting the leaf area index: a case study in pure even-aged Crimean pine forests from Turkey
),
Abstract
Leaf Area Index (LAI) is an important parameter used in monitoring and modeling of forest ecosystems. The aim of this study was to evaluate performance of the artificial neural network (ANN) models to predict the LAI by comparing the regression analysis models as the classical method in these pure and even-aged Crimean pine forest stands.
One hundred eight temporary sample plots were collected from Crimean pine forest stands to estimate stand parameters. Each sample plot was imaged with hemispherical photographs to detect the LAI. The partial correlation analysis was used to assess the relationships between the stand LAI values and stand parameters, and the multivariate linear regression analysis was used to predict the LAI from stand parameters. Different artificial neural network models comprising different number of neuron and transfer functions were trained and used to predict the LAI of forest stands.
The correlation coefficients between LAI and stand parameters (stand number of trees, basal area, the quadratic mean diameter, stand density and stand age) were significant at the level of 0.01. The stand age, number of trees, site index, and basal area were independent parameters in the most successful regression model predicted LAI values using stand parameters (Radj.2 = 0.5431). As corresponding method to predict the interactions between the stand LAI values and stand parameters, the neural network architecture based on the RBF 4-19-1 with Gaussian activation function in hidden layer and the identity activation function in output layer performed better in predicting LAI (SSE (12.1040), MSE (0.1223), RMSE (0.3497), AIC (0.1040), BIC (-77.7310) and R2 (0.6392)) compared to the other studied techniques.
The ANN outperformed the multivariate regression techniques in predicting LAI from stand parameters. The ANN models, developed in this study, may aid in making forest management planning in study forest stands.
References(55)
Arias D, Calvo-Alvarado J, Dohrenbusch A (2007) Calibration of LAI-2000 to estimate leaf area index (LAI) and assessment of its relationship with stand productivity in six native and introduced tree species in Costa Rica. Forest Ecol Manage 247:185-193
Ashraf MI, Zhao Z, Bourque A, MacLean DA, Meng F (2013) Integrating biophysical controls in forest growth and yield predictions generated with artificial intelligence technology. Can J For Res 43:1162-1171
Bacour C, Baret F, Béal D, Weiss M, Pavageau K (2006) Neural network estimation of LAI, fAPAR, fCover and LAI×cab, from top of canopy MERIS reflectance data: principles and validation. Remote Sens Environment 105:313-325
Bequet R, Kint V, Campioli M, Vansteenkiste D, Muys B, Ceulemans R (2012) Influence of stand, site and meteorological variables on the maximum leaf area index of beech, oak and scots pine. Eur J Forest Res 131(2):283-295
Chen JM, Black TA, Adams RS (1991) Evaluation of hemispherical photography for determining plant area index and geometry of a forest stand. Agric For Meteorol 56:129-143
Chianucci F, Cutini A (2012) Digital hemispherical photography for estimating forest canopy properties: current controversies and opportunities. iForest 5:290-295
Chianucci F, Macfarlane C, Pisek J, Cutini A, Casa R (2015) Estimation of foliage clumping from the LAI-2000 plant canopy analyzer: effect of view caps. Trees 29:355-366
Dantec VL, Dufrene E, Saugier B (2000) Interannual and spatial variation in maximum leaf area index of temperate deciduous stands. For Ecol Manag 134:71-81
DeRose RJ, Seymour RS (2010) Patterns of leaf area index during stand development in even-aged balsam fir - red spruce stands. Can J For Res 40(4):629-637
Diamantopoulou MJ (2005) Predicting fir trees stem diameters using artificial neural network models, southern forests. J South Afr Forest Assoc 205:39-44
Diamantopoulou MJ, Milios E (2010) Modelling total volume of dominant pine trees in reforestations via multivariate analysis and artificial neural network models. Biosyst Eng 105:306-315
Diamantopoulou MJ, Özçelik R (2012) Evaluation of different modeling approaches for total tree-height estimation in Mediterranean region of Turkey. Forest Syst 21(3):383-397
Frazer GW, Fournier RA, Trofymow JA, Hall JR (2001) A comparison of digital and film fisheye photography for analysis of forest canopy structure and gap light transmission. Agric For Meteorol 109:249-263
Gholz HL (1982) Environmental limits on above ground net primary production, leaf area and biomass in vegetation zones of the Pacific northwest. Ecology 53:469-481
Grier CC, Running SW (1977) Leaf area of mature northwestern coniferous forests: relation to water balance. Ecology 58:893-899
Hale SE, Edwards C (2002) Comparison of film and digital hemispherical photography across a wide range of canopy densities. Agric For Meteorol 112:51-56
Hasenauer H, Merkl D, Weingartner M (2001) Estimating tree mortality of Norway spruce stands with neural networks. Adv Environ Res 5(4):405-414
Hu L, Zhu J (2009) Determination of the tridimensional shape of canopy gaps using two hemispherical photographs. Agric For Meteorol 149:862-872
Jagodziński AM, Kalucka IL (2008) Age-related changes in leaf area index of young scots pine stands. Dendrobiology 59:57-65
Jeleska SD (2004) Analysis of canopy closure in the dinaric silver fir-beech forests in Crotia using hemispherical photography. Hacquetia 3(2):43-49
Jonckheere I, Fleck S, Nackaerts K, Muys B, Coppin P, Weiss M, Baret F (2004) Review of methods for in situ leaf area index determination part I. Theories, sensors and hemispherical photography. Agric For Meteorol 121:19-35
Kashian DM, Turner MG, Romme WH (2005) Variability in leaf area and stemwood increment along a 300-year lodgepole pine chronosequence. Ecosystems 8:48-61
Khosravi S, Namiranian M, Ghazanfari H, Shirvani A (2012) Estimation of leaf area index and assessment of its allometric equations in oak forests: northern Zagros, Iran. J Forest Sci 58(3):116-122
Leblanc SG, Chen JM, Fernandes R, Deering DW, Conley A (2005) Methodology comparison for canopy structure parameters extraction from digital hemispherical photography in boreal forests. Agric For Meteorol 129:187-207
Leite HG, Marques da Silva ML, Binoti DHB, Fardin L, Takizawa FH (2011) Estimation of inside-bark diameter and heartwood diameter for Tectona grandis Linn. Trees using artificial neural networks. Eur J Forest Res 130:263-269
Liang J, Buongiorno J, Monserud RA (2005) Growth and yield of all-aged Douglas-fir western hemlock forest stands: a matrix model with stand diversity effects. Can J For Res 35(10):2368-2381
Macfarlane C, Grigg A, Evangelista C (2007) Estimating forest leaf area using cover and fullframe fisheye photography: thinking inside the circle. Agric For Meteorol 146:1-12
Madugundu R, Nizalapur V, Jha CS (2008) Estimation of LAI and above ground biomass in decisious forests: western Ghats of Karnataka, India. Int J Appl Earth Observ Geoinform 10:211-219
Nowak DJ (1996) Estimating leaf area and leaf biomass of open-grown deciduous urban trees. For Sci 42(4):504-507
Omer G, Mutanga O, Abdel-Rahman EM, Adam E (2016) Empirical prediction of leaf area index (LAI) of endangered tree species in intact and fragmented indigenous forests ecosystems using worldview-2 data and two robust machine learning algorithms. Remote Sens 8:324-350
Özbayram AK, Çiçek E, Yılmaz F (2015) Relationships between leaf area index (lai) and some stand properties in Turkish red pine and black pine stands. Kastamonu Univ J Forest Faculty 15(1):78-85
Özçelik R, Diamantopoulou MJ, Crecente-Campo F, Eler Ü (2013) Estimating Crimean juniper tree height using nonlinear regression and artificial neural network models. For Ecol Manag 306:52-60
Özçelik R, Diamantopoulou MJ, Eker M, Gürlevik N (2017) Artificial neural network models: an alternative approach for reliable above-ground pine-tree biomass prediction. For Sci 63(3):291-302
Özçelik R, Diamantopoulou MJ, Wiant HV, Brooks JR (2008) Comparative study of standard and modern methods for estimating tree bole volume of three species in Turkey. Forest Prod J 58:73-81
Özçelik R, Diamantopoulou MJ, Wiant HV, Brooks JR (2010) Estimating tree bole volume using artificial neural network models for four species in Turkey. J Environ Manag 91(3):742-753
Peng C, Liu J, Dang Q, Apps MJ, Jiang H (2002) TRIPLEX: a generic hybrid model for predicting forest growth and carbon and nitrogen dynamics. Ecol Model 153:109-130
Pokorný R, Stojnič S (2012) Leaf area index of Norway spruce stands in relation to age and defoliation. Beskydy 5(2):173-180
Sonohat G, Balandier P, Ruch AF (2004) Predicting solar radiation transmittance in the understory of even-aged coniferous stands in temperate forests. Ann Forest Sci 61:629-641
Turner DP, Acker SA, Means JE, Garman SL (2000) Assessing alternative allometric algorithms for estimating leaf area of Douglas-fir trees and stands. For Ecol Manag 126:61-76
Verger A, Baret F, Weiss M (2008) Performances of neural networks for deriving LAI estimates from existing CYCLOPES and MODIS products. Remote Sens Environ 112:2789-2803
Vilà M, Vayreda J, Gracia C, Ibáñez JJ (2003) Does tree diversity increase wood production in pine forests? Oecologia 135:299-303
Vose JM, Allen HL (1988) Leaf area, stemwood growth and nutrient relationships in loblolly pine. Forest Science 34:547-563.
Walter JMN, Torquebiau EF (2000) The computation of forest leaf area index on slope using fish-eye sensors. Life Sci 323:801-813
Wang T, Zhiqiang XZ, Liu Z (2017) Performance evaluation of machine learning methods for leaf area index retrieval from time-series MODIS reflectance data. Sensors 17:81-96
Wang W, Lei X, Ma Z, Kneeshaw DD, Peng C (2011) Positive relationship between aboveground carbon stocks and structural diversity in spruce dominated forest stands in New Brunswick. For Sci 57:506-515
Weiss M, Baret F, Smith GJ, Jonckheere I, Coppin P (2004) Review of methods for in situ leaf area index (LAI) determination part Ⅱ. Estimation of LAI, errors and sampling. Agric For Meteorol 121:37-53
Wulder MA, LeDrew EF, Franklin SE, Lavigne MB (1998) Aerial image texture information in the estimation of northern deciduous and mixed wood forest leaf area index (LAI). Remote Sens Environ 64:64-76
Publication history
Copyright
Rights and permissions
Open Access This article is 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, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.
FEEDBACK 
TOP