A Levenberg–Marquardt Backpropagation Neural Network for Predicting Forest Growing Stock Based on the Least-Squares Equation Fitting Parameters

Traditional field surveys are expensive, time-consuming, laborious, and difficult to perform, especially in mountainous and dense forests, which imposes a burden on forest management personnel and researchers. This study focuses on predicting forest growing stock, one of the most significant parameters of a forest resource assessment. First, three schemes were designed—Scheme 1, based on the study samples with mixed tree species; Scheme 2, based on the study samples divided into dominant tree species groups; and Scheme 3, based on the study samples divided by dominant tree species groups—the evaluation factors are fitted by least-squares equations, and the non-significant fitted-factors are removed. Second, an overall evaluation indicator system with 17 factors was established. Third, remote sensing images of Landsat Thematic Mapper, digital elevation model, and the inventory for forest management planning and design were integrated in the same database. Lastly, a backpropagation neural network based on the Levenberg–Marquardt algorithm was used to predict the forest growing stock. The results showed that the group estimation precision exceeded 90%, which is the highest standard of total sampling precision of inventory for forest management planning and design in China. The prediction results for distinguishing dominant tree species were better than for mixed dominant tree species. The results also showed that the performance metrics for prediction could be improved by least-squares equation fitting and significance filtering of the evaluation factors.

[1]  Piermaria Corona,et al.  Non-parametric and parametric methods using satellite images for estimating growing stock volume in alpine and Mediterranean forest ecosystems , 2008 .

[2]  A. Pekkarinen,et al.  Estimation of forest stand volumes by Landsat TM imagery and stand-level field-inventory data , 2004 .

[3]  Shaban Shataee,et al.  Estimation of forest stand volume, tree density and biodiversity using Landsat ETM+ Data, comparison of linear and regression tree analyses , 2011 .

[4]  J. Fernández-Martínez,et al.  Tree height prediction approaches for uneven-aged beech forests in northwestern Spain , 2013 .

[5]  Gu Li.  Application of improved LM-BP neural network in water quality evaluation , 2008 .

[6]  E. Tomppo.  National Forest Inventories : pathways for common reporting , 2010 .

[7]  Min Fenga.  BP Neural Network Based on LM Algorithm for the Forecasting of Vehicle Emission , 2012 .

[8]  Hong Wei.  A STUDY ON THE MODEL OF FOREST RESOURCES MANAGEMENT BASED ON THE ARTIFICIAL NEURAL NETWORK , 1998 .

[9]  Chen Ming-hua.  Dynamic visualization of Chinese fir volume driven by site condition and growth model , 2011 .

[10]  A. Hudak.  INTEGRATION OF LIDAR AND LANDSAT ETM + DATA , 2004 .

[11]  Dasheng Wu,et al.  Dynamic Estimation of Forest Volume Based on Multi-Source Data and Neural Network Model , 2015 .

[12]  Jiang Huiyu.  K /S value prediction of reactive dyes with improved LM-BP algorithm , 2010 .

[13]  Du Xiaowen.  Application of LM-BP neural network in predicting dam deformation , 2011 .

[14]  Marko Debeljak,et al.  Modelling forest growing stock from inventory data: A data mining approach , 2014 .

[15]  T. Sharik,et al.  Practical field methods of estimating canopy cover, PAR, and LAI in Michigan Oak and pine stands , 1999 .

[16]  Xinhong Wang,et al.  Earthquake Prediction Based on Levenberg-Marquardt Algorithm Constrained Back-Propagation Neural Network Using DEMETER Data , 2010, KSEM.

[17]  Terje Gobakken,et al.  Inference for lidar-assisted estimation of forest growing stock volume , 2013 .

[18]  Christiane Schmullius,et al.  Growing stock volume estimation from L-band ALOS PALSAR polarimetric coherence in Siberian forest , 2014 .

[19]  Andrew P. Robinson,et al.  Criteria for comparing the adaptability of forest growth models , 2003 .

[20]  Shaban Shataeea,et al.  Plot-level Forest Volume Estimation Using Airborne Laser Scanner and TM Data, Comparison of Boosting and Random Forest Tree Regression Algorithms , 2011 .

[21]  M. Bauer,et al.  Estimation and mapping of forest stand density, volume, and cover type using the k-nearest neighbors method , 2001 .

[22]  Sandra A. Brown,et al.  Spatial distribution of biomass in forests of the eastern USA , 1999 .

[23]  Jari Liski,et al.  Scenario analysis of the impacts of forest management and climate change on the European forest sector carbon budget , 2003 .

[24]  A. S. Mahiny,et al.  Modelling forest stand volume and tree density using Landsat ETM+ data , 2010 .

[25]  Sovan Lek,et al.  Artificial neural networks as a tool in ecological modelling, an introduction , 1999 .

[26]  M. Wei.  A height growth model for Cunninghamia lanceolata based on Richards' equation , 2012 .

[27]  E. Næsset,et al.  Post-stratified estimation of forest area and growing stock volume using lidar-based stratifications , 2012 .

[28]  T. Tokola,et al.  Improving Satellite Image Based Forest Inventory by Using A Priori Site Quality Information , 1997 .

[29]  Fei Huang,et al.  Brief Introduction of Back Propagation (BP) Neural Network Algorithm and Its Improvement , 2012 .

[30]  G. Scrinzi,et al.  Development of a neural network model to update forest distribution data for managed alpine stands , 2007 .

[31]  Chris R. Hennigar,et al.  Forecasting Forest Inventory Using Imputed Tree Lists for LiDAR Grid Cells and a Tree-List Growth Model , 2018 .

[32]  P. Lohmander,et al.  Estimation of a basal area growth model for individual trees in uneven-aged Caspian mixed species forests , 2017, Journal of Forestry Research.