A performance comparison of machine learning methods to estimate the fast-growing forest plantation yield based on laser scanning metrics

Machine learning models tackle high-dimensional problems.The machine learning models are not limited to a subset of predictor variables.The random forest had the best RMSE compared to neural network and support vector regression.The coefficient of determination and bias were similar to all modeling techniques. Machine learning models appear to be an attractive route towards tackling high-dimensional problems, particularly in areas where a lack of knowledge exists regarding the development of effective algorithms, and where programs must dynamically adapt to changing conditions. The objective of this study was to evaluate the performance of three machine learning tools for predicting stand volume of fast-growing forest plantations, based on statistical vegetation metrics extracted from an Airborne Laser Scanning (ALS) survey. The forests used in this study were composed of 1138ha of commercial plantations that consisted of hybrids of Eucalyptus grandis and Eucalyptus urophylla, managed for pulp production. Three machine learning tools were implemented: neural network (NN), random forest (RF) and support vector regression (SV); and their performance was compared to a regression model (RM). The RF and the RM presented an RMSE in the leave-one-out cross-validation of 31.80 and 30.56m3ha-1 respectively. The NN and SV presented a higher RMSE than the others, equal to 64.44 and 65.30m3ha-1. The coefficient of determination and bias were similar to all modeling techniques. The ranking of ALS metrics based on their relative importance for the estimation of stand volume showed some differences. Rather than being limited to a subset of predictor variables, machine learning techniques explored the complete metrics set, looking for patterns between them and the dependent variable.

[1]  P. Deschamps,et al.  Evaluation of topographic effects in remotely sensed data , 1989 .

[2]  E. Næsset,et al.  Estimating tree heights and number of stems in young forest stands using airborne laser scanner data , 2001 .

[3]  W. Cohen,et al.  Lidar Remote Sensing of the Canopy Structure and Biophysical Properties of Douglas-Fir Western Hemlock Forests , 1999 .

[4]  E. Næsset.  Predicting forest stand characteristics with airborne scanning laser using a practical two-stage procedure and field data , 2002 .

[5]  T. Dawson,et al.  Quantifying forest above ground carbon content using LiDAR remote sensing , 2004 .

[6]  William N. Venables,et al.  Modern Applied Statistics with S , 2010 .

[7]  Yong Pang,et al.  Characterizing forest canopy structure with lidar composite metrics and machine learning , 2011 .

[8]  Kurt Hornik,et al.  kernlab - An S4 Package for Kernel Methods in R , 2004 .

[9]  M. Nilsson.  Estimation of tree heights and stand volume using an airborne lidar system , 1996 .

[10]  W. Cohen,et al.  Using Landsat-derived disturbance history (1972-2010) to predict current forest structure , 2012 .

[11]  Halbert White,et al.  Learning in Artificial Neural Networks: A Statistical Perspective , 1989, Neural Computation.

[12]  J. Zerubia,et al.  Mapping local density of young Eucalyptus plantations by individual tree detection in high spatial resolution satellite images , 2013 .

[13]  E. Næsset,et al.  Prediction of species specific forest inventory attributes using a nonparametric semi-individual tree crown approach based on fused airborne laser scanning and multispectral data , 2010 .

[14]  David C. Van Essen,et al.  Application of Information Technology: An Integrated Software Suite for Surface-based Analyses of Cerebral Cortex , 2001, J. Am. Medical Informatics Assoc..

[15]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[16]  E. Næsset,et al.  Estimation of above- and below-ground biomass across regions of the boreal forest zone using airborne laser , 2008 .

[17]  S. Reutebuch,et al.  Light detection and ranging (LIDAR): an emerging tool for multiple resource inventory. , 2005 .

[18]  Jocelyn Chanussot,et al.  Optical Remote Sensing: Advances in Signal Processing and Exploitation Techniques , 2011 .

[19]  M. Maltamo,et al.  ALS-based estimation of plot volume and site index in a eucalyptus plantation with a nonlinear mixed-effect model that accounts for the clone effect , 2011, Annals of Forest Science.

[20]  E. Næsset.  Practical large-scale forest stand inventory using a small-footprint airborne scanning laser , 2004 .

[21]  J. Evans,et al.  Quantifying Bufo boreas connectivity in Yellowstone National Park with landscape genetics. , 2010, Ecology.

[22]  Mark O. Kimberley,et al.  Airborne scanning LiDAR in a double sampling forest carbon inventory , 2012 .

[23]  D. R. Cutler,et al.  Utah State University From the SelectedWorks of , 2017 .

[24]  B. Muys,et al.  Comparison and ranking of different modelling techniques for prediction of site index in Mediterranean mountain forests , 2010 .

[25]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[26]  E. Næsset.  Estimating timber volume of forest stands using airborne laser scanner data , 1997 .

[27]  P. Gessler,et al.  Regression modeling and mapping of coniferous forest basal area and tree density from discrete-return lidar and multispectral satellite data , 2006 .

[28]  Saso Dzeroski,et al.  Estimating vegetation height and canopy cover from remotely sensed data with machine learning , 2010, Ecol. Informatics.

[29]  Joanne C. White,et al.  The Utility of Image-Based Point Clouds for Forest Inventory: A Comparison with Airborne Laser Scanning , 2013 .

[30]  K. Lim,et al.  Estimation of above ground forest biomass from airborne discrete return laser scanner data using canopy-based quantile estimators , 2004 .

[31]  Maria J. Diamantopoulou,et al.  Estimating Crimean juniper tree height using nonlinear regression and artificial neural network models , 2013 .

[32]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[33]  Ross Nelson,et al.  Estimating forest biomass and volume using airborne laser data , 1988 .

[34]  M. Diamantopoulou,et al.  Estimating tree bole volume using artificial neural network models for four species in Turkey. , 2010, Journal of environmental management.

[35]  K. Rennolls,et al.  Timber Management-A Quantitative Approach. , 1984 .

[36]  Jungho Im,et al.  Forest biomass estimation from airborne LiDAR data using machine learning approaches , 2012 .

[37]  S. Popescu,et al.  Lidar remote sensing of forest biomass : A scale-invariant estimation approach using airborne lasers , 2009 .

[38]  Bernhard Schölkopf,et al.  A tutorial on support vector regression , 2004, Stat. Comput..

[39]  Geoffrey G. Parker,et al.  The canopy surface and stand development: assessing forest canopy structure and complexity with near-surface altimetry , 2004 .

[40]  S. Durbha,et al.  Support vector machines regression for retrieval of leaf area index from multiangle imaging spectroradiometer , 2007 .

[41]  Eduardo González-Ferreiro,et al.  Assessing the attributes of high-density Eucalyptus globulus stands using airborne laser scanner data , 2011 .

[42]  Jocelyn Chanussot,et al.  Optical Remote Sensing , 2011 .

[43]  S. Popescu,et al.  Bayesian Learning with Gaussian Processes for Supervised Classification of Hyperspectral Data , 2008 .

[44]  C. Atzberger.  Object-based retrieval of biophysical canopy variables using artificial neural nets and radiative transfer models , 2004 .

[45]  Andy Liaw,et al.  Classification and Regression by randomForest , 2007 .

[46]  S. Liang,et al.  Retrieving leaf area index using a genetic algorithm with a canopy radiative transfer model , 2003 .

[47]  S. Gunn.  Support Vector Machines for Classification and Regression , 1998 .

[48]  R. Valbuena,et al.  Patterns of covariance between airborne laser scanning metrics and Lorenz curve descriptors of tree size inequality , 2013 .

[49]  B. Koch,et al.  Non-parametric prediction and mapping of standing timber volume and biomass in a temperate forest: application of multiple optical/LiDAR-derived predictors , 2010 .

[50]  Michele Dalponte,et al.  Airborne laser scanning of forest resources: An overview of research in Italy as a commentary case study , 2013, Int. J. Appl. Earth Obs. Geoinformation.