Robust learning-based prediction for timber-volume of living trees

Applied innovation. It is the first time that the learning-based technique are used to predict timber volume of living trees.MPSO is an interesting modification of PSO, but with the injection of the self-adapted coefficient that makes the optimization problem intractable. In order to obtain a satisfactory solution, an iterative procedure is adopted to solve the proposed problem, which is common used in the fields of pattern recognition. The inertia weight coefficient in MPSO can be self-adapted under the changing of the fitness-function, such that the global searching performance can be improved effectively and the exploration ability can be coordinated preferably.A novel method based on the virtual trees is firstly used to estimate the accuracy of the timbervolume predicted model. Many existing timber volume calculating applications are applied by solving a single or multi-variables formulation, while most of those methods are based on the felled trees, which lead to a number of living trees is cut down yearly in different areas. In this paper, a novel learning-based nonlinear timber volume predicted model is proposed, which based on the least squares support vector machine (LSSVM) algorithm, and a modified particle swarm optimization (MPSO) algorithm is used to optimize the parameters involved in the LSSVM. Specifically, the initial weight coefficient in classical particle swarm optimization (PSO) is modified, such that the global optimal solution can be obtained more fleetly and accurately, meanwhile, the timber volume predicted model is established based on the modified algorithm. The experiments are carried out on our collected data, which are obtained from Xiashu plantation of Jurong in Jiangsu Province of China. Three kinds of trees, named Populus, Liriodendron and Soapberry, are selected as the experiment samples. The historical timber volume data of the same kinds, used as the training set in the proposed MPSO-LSSVM model, are obtained from the management of Xiashu plantation. The two properties from the manually measured data, including tree height and diameter at breast height (DBH), are used as the input parameters in the testing set of MPSO-LSSVM. Furthermore, the virtual trees, generated by computers, provide a novel approach to estimate the predicted accuracy of the learning-based model in forest inventory. The experiment results in comparisons with the solutions from volume equation, taper function, felled trees and the virtual trees demonstrate the availability and efficiency of the proposed model in prediction of timber volume.

[1]  H. Vaux,et al.  Timber: biological and economic potential. , 1976, Science.

[2]  M. D. Nelson,et al.  Mapping U.S. forest biomass using nationwide forest inventory data and moderate resolution information , 2008 .

[3]  Pedro Antonio Gutiérrez,et al.  Projection-Based Ensemble Learning for Ordinal Regression , 2014, IEEE Transactions on Cybernetics.

[4]  Juha M. Hyyppae,et al.  Assessment of forest attributes and single-tree segmentation by means of laser scanning , 2000, Defense, Security, and Sensing.

[5]  Timo Määttä,et al.  The suitability of an electronic information exchange (Puutori) for the timber trade in Finland , 2000 .

[6]  M. Hansen,et al.  Using Traditional Ecological Knowledge as a Basis for Targeted Forest Inventories: Paper Birch (Betula papyrifera) in the US Great Lakes Region , 2014 .

[7]  Chunxia Zhao,et al.  Least squares twin support vector machine classification via maximum one-class within class variance , 2012, Optim. Methods Softw..

[8]  Bhaskaran Gopalakrishnan,et al.  Nondestructive evaluation of wooden logs using ground penetrating radar , 2009 .

[9]  Meng Wang,et al.  Neighborhood Discriminant Hashing for Large-Scale Image Retrieval , 2015, IEEE Transactions on Image Processing.

[10]  E. Baltsavias,et al.  Digital Surface Modelling by Airborne Laser Scanning and Digital Photogrammetry for Glacier Monitoring , 2001 .

[11]  F. Schumacher.  Logarithmic expression of timber-tree volume , 1933 .

[12]  Hong-Yan Zou,et al.  Multiplex protein pattern unmixing using a non-linear variable-weighted support vector machine as optimized by a particle swarm optimization algorithm. , 2016, Talanta.

[13]  Xinlian Liang,et al.  Deriving Merchantable Volume in Poplar through a Localized Tapering Function from Non-Destructive Terrestrial Laser Scanning , 2016 .

[14]  Minglei Shu,et al.  Application of support vector machine and particle swarm optimization in micro near infrared spectrometer , 2016, International Symposium on Advanced Optical Manufacturing and Testing Technologies (AOMATT).

[15]  Fucai Liu,et al.  Nonlinear system identification using least squares support vector machine tuned by an adaptive particle swarm optimization , 2015, Int. J. Mach. Learn. Cybern..

[16]  Jinhui Tang,et al.  Generalized Deep Transfer Networks for Knowledge Propagation in Heterogeneous Domains , 2016, ACM Trans. Multim. Comput. Commun. Appl..

[17]  Shangbing Gao,et al.  1-Norm least squares twin support vector machines , 2011, Neurocomputing.

[18]  J. Navar,et al.  Taper functions and merchantable timber for temperate forests of northern Mexico , 2013 .

[19]  Lichun Jiang,et al.  Compatible taper and volume equations for yellow-poplar in West Virginia , 2005 .

[20]  S. Popescu,et al.  Measuring individual tree crown diameter with lidar and assessing its influence on estimating forest volume and biomass , 2003 .

[21]  Generic and specific stem volume models for three subtropical forest types in southern Brazil , 2015, Annals of Forest Science.

[22]  Keith Crews,et al.  In situ assessment of structural timber using stress-wave measurements , 2014 .

[23]  Philippe Santenoise,et al.  Terrestrial laser scanning for measuring the solid wood volume, including branches, of adult standing trees in the forest environment , 2012 .

[24]  J. H. Smith,et al.  Taper Functions and their Application in Forest Inventory , 1969 .

[25]  Jian Yang,et al.  Recursive robust least squares support vector regression based on maximum correntropy criterion , 2012, Neurocomputing.

[26]  E. Næsset,et al.  Comparison of four types of 3D data for timber volume estimation , 2014 .

[27]  Ramesh C. Jain,et al.  Image annotation by kNN-sparse graph-based label propagation over noisily tagged web images , 2011, TIST.

[28]  Ping Liu,et al.  Application of least square support vector machine based on particle swarm optimization to chaotic time series prediction , 2009, 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems.

[29]  Franck Bourrier,et al.  Experimental and numerical dynamic analysis of a live tree stem impacted by a Charpy pendulum , 2013 .

[30]  Don R. Hush,et al.  An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels , 2006, IEEE Transactions on Information Theory.

[31]  J. Hyyppä,et al.  Estimation of timber volume and stem density based on scanning laser altimetry and expected tree size distribution functions , 2004 .

[32]  Ali Chamkalani,et al.  Integration of LSSVM technique with PSO to determine asphaltene deposition , 2014 .

[33]  P. West.  Tree and Forest Measurement , 2003, Springer International Publishing.

[34]  Francesco Augelli,et al.  In situ assessment of structural timber using non-destructive techniques , 2014 .