Deep Learning in Forest Structural Parameter Estimation Using Airborne LiDAR Data

Accurately estimating and mapping forest structural parameters are essential for monitoring forest resources and understanding ecological processes. The novel deep learning algorithm has the potential to be a promising approach to improve the estimation accuracy while combining with advanced remote sensing technology. Airborne light detection and ranging (LiDAR) has the preferable capability to characterize 3-D canopy structure and estimate forest structural parameters. In this study, we developed a deep learning-based algorithm (Deep-RBN) that combined the fully connected network (FCN) deep learning algorithm with the optimized radial basis neural network (RBN) algorithm for forest structural parameter estimation using airborne LiDAR data. The multiple iterations were used to constantly update the internal weights to achieve the optimized accuracy of model fitting, and the optimized RBN algorithm was developed for the limited training sets. We assessed the efficiency and capability of the Deep-RBN in the estimation of forest structural parameters in a subtropical planted forest of southern China, by comparing the traditional FCN algorithm and multiple linear regression. We found that Deep-RBN had the strongest capability in estimates of forest structural parameters (R2 = 0.67–0.86, rRMSE = 6.95%–20.34%). The sensitivity analysis of the key hyperparameters of Deep-RBN algorithm showed that the learning rate is one of the most important parameters that influence the performance of predictive models, and while its value equal is to 0.001, the predictive models had the highest accuracy (mean DBH: RMSE = 1.01, mean height: RMSE = 1.45, volume: RMSE = 26.49, stem density: RMSE = 121.06). With the increase of training samples added in Deep-RBN model, the predictive models performed better; however, no significant improvements of accuracy were observed while the number of training set is larger than 80. This study demonstrates the benefits of jointly using the Deep-RBN algorithm and airborne LiDAR data to improve the accuracy of forest structural parameter estimation and mapping, which provides a promising methodology for sustainable forest resources monitoring.

[1]  François Chollet,et al.  Keras: The Python Deep Learning library , 2018 .

[2]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  Virpi Junttila,et al.  Linear Models for Airborne-Laser-Scanning-Based Operational Forest Inventory With Small Field Sample Size and Highly Correlated LiDAR Data , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[5]  İlker Ercanli.  Innovative deep learning artificial intelligence applications for predicting relationships between individual tree height and diameter at breast height , 2020, Forest Ecosystems.

[6]  J. W. Thomas.  Forest Service Perspective on Ecosystem Management , 1996 .

[7]  Shiming Xiang,et al.  Vehicle Detection in Satellite Images by Hybrid Deep Convolutional Neural Networks , 2014, IEEE Geoscience and Remote Sensing Letters.

[8]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[9]  J. Holmgren.  Prediction of tree height, basal area and stem volume in forest stands using airborne laser scanning , 2004 .

[10]  Xiao Xiang Zhu,et al.  Unsupervised Spectral–Spatial Feature Learning via Deep Residual Conv–Deconv Network for Hyperspectral Image Classification , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Qi Zhang,et al.  Deep learning-based tree classification using mobile LiDAR data , 2015 .

[12]  Jason W. Osbourne,et al.  Four Assumptions of Multiple Regression That Researchers Should Always Test. , 2002 .

[13]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[14]  Pierre Baldi,et al.  Learning Activation Functions to Improve Deep Neural Networks , 2014, ICLR.

[15]  Juha Hyyppä,et al.  Combination of individual tree detection and area-based approach in imputation of forest variables using airborne laser data , 2012 .

[16]  Maggi Kelly,et al.  A New Method for Segmenting Individual Trees from the Lidar Point Cloud , 2012 .

[17]  Pascual Campoy Cervera,et al.  A Review of Deep Learning Methods and Applications for Unmanned Aerial Vehicles , 2017, J. Sensors.

[18]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[19]  Nicholas C. Coops,et al.  Digital aerial photogrammetry for assessing cumulative spruce budworm defoliation and enhancing forest inventories at a landscape-level , 2018 .

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

[21]  Wang Jiamin,et al.  Individual Rubber Tree Segmentation Based on Ground-Based LiDAR Data and Faster R-CNN of Deep Learning , 2019, Forests.

[22]  K. Lim,et al.  Operational implementation of a LiDAR inventory in Boreal Ontario , 2011 .

[23]  Eric Eaton,et al.  Deep Transfer Learning for Few-Shot SAR Image Classification , 2019, Remote. Sens..

[24]  Anil K. Jain,et al.  Artificial Neural Networks: A Tutorial , 1996, Computer.

[25]  Martial Hebert,et al.  Learning to Learn: Model Regression Networks for Easy Small Sample Learning , 2016, ECCV.

[26]  Joanne C. White,et al.  Remote Sensing Technologies for Enhancing Forest Inventories: A Review , 2016 .

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

[28]  Mohammed Bennamoun,et al.  Forest Change Detection in Incomplete Satellite Images With Deep Neural Networks , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[29]  Douglas K. Bolton,et al.  Characterizing residual structure and forest recovery following high-severity fire in the western boreal of Canada using Landsat time-series and airborne lidar data , 2015 .

[30]  Ting Hu,et al.  Deep Learning on Point Clouds and Its Application: A Survey , 2019, Sensors.

[31]  Kim-Kwang Raymond Choo,et al.  SVM or deep learning? A comparative study on remote sensing image classification , 2016, Soft Computing.

[32]  Leonidas J. Guibas,et al.  PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space , 2017, NIPS.

[33]  R. Keenan,et al.  A proposed framework for assessing ecosystem goods and services from planted forests , 2016 .

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

[35]  Amy J. Symstad,et al.  Species diversity, functional diversity, and ecosystem functioning , 2002 .

[36]  Changhui Peng,et al.  Application of machine-learning methods in forest ecology: recent progress and future challenges , 2018, Environmental Reviews.

[37]  Joanne C. White,et al.  The role of LiDAR in sustainable forest management , 2008 .

[38]  Tamás D. Gedeon,et al.  Data Mining of Inputs: Analysing Magnitude and Functional Measures , 1997, Int. J. Neural Syst..

[39]  Fan Zhang,et al.  Deep Convolutional Neural Networks for Hyperspectral Image Classification , 2015, J. Sensors.

[40]  Juan A. Blanco,et al.  Significant Increase in Ecosystem C Can Be Achieved with Sustainable Forest Management in Subtropical Plantation Forests , 2014, PloS one.

[41]  Colin P. Schwegmann,et al.  Very deep learning for ship discrimination in Synthetic Aperture Radar imagery , 2016, 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[42]  Ronald E. McRoberts,et al.  The enhanced forest inventory and analysis program , 2005 .

[43]  Nicholas C. Coops,et al.  Estimation of forest biomass dynamics in subtropical forests using multi-temporal airborne LiDAR data , 2016 .

[44]  Alicia Troncoso Lora,et al.  A comparison of machine learning regression techniques for LiDAR-derived estimation of forest variables , 2015, Neurocomputing.

[45]  E. B. Görgens,et al.  Artificial Intelligence Procedures for Tree Taper Estimation within a Complex Vegetation Mosaic in Brazil , 2016, PloS one.

[46]  Jungho Im,et al.  ISPRS Journal of Photogrammetry and Remote Sensing , 2022 .

[47]  Xiao Xiang Zhu,et al.  Deep Recurrent Neural Networks for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[48]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[49]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[50]  Timothy Marler,et al.  Neural network for regression problems with reduced training sets , 2017, Neural Networks.

[51]  Leonidas J. Guibas,et al.  PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[52]  Yanjun Su,et al.  Improved progressive TIN densification filtering algorithm for airborne LiDAR data in forested areas , 2016 .

[53]  Gang Wan,et al.  Deep Few-Shot Learning for Hyperspectral Image Classification , 2019, IEEE Transactions on Geoscience and Remote Sensing.

[54]  W. Cohen,et al.  Lidar Remote Sensing for Ecosystem Studies , 2002 .

[55]  Ming Zhu,et al.  A Review of Researches on Deep Learning in Remote Sensing Application , 2019, International Journal of Geosciences.

[56]  E. Næsset.  ESTIMATION OF ABOVE-AND BELOW-GROUND BIOMASS IN BOREAL FOREST ECOSYSTEMS , 2004 .

[57]  J. Means,et al.  Predicting forest stand characteristics with airborne scanning lidar , 2000 .

[58]  Nikolaos Doulamis,et al.  Deep supervised learning for hyperspectral data classification through convolutional neural networks , 2015, 2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS).

[59]  Xiao Xiang Zhu,et al.  Deep Learning in Remote Sensing: A Comprehensive Review and List of Resources , 2017, IEEE Geoscience and Remote Sensing Magazine.

[60]  Joanne C. White,et al.  A best practices guide for generating forest inventory attributes from airborne laser scanning data using an area-based approach , 2013 .

[61]  William A. Bechtold,et al.  The enhanced forest inventory and analysis program - national sampling design and estimation procedures , 2005 .

[62]  Shihong Du,et al.  Learning multiscale and deep representations for classifying remotely sensed imagery , 2016 .

[63]  Lei Guo,et al.  Object Detection in Optical Remote Sensing Images Based on Weakly Supervised Learning and High-Level Feature Learning , 2015, IEEE Transactions on Geoscience and Remote Sensing.

[64]  Brandon M. Greenwell,et al.  A Simple and Effective Model-Based Variable Importance Measure , 2018, ArXiv.

[65]  Xiao Xiang Zhu,et al.  RiFCN: Recurrent Network in Fully Convolutional Network for Semantic Segmentation of High Resolution Remote Sensing Images , 2018, ArXiv.

[66]  M. Maltamo,et al.  The k-MSN method for the prediction of species-specific stand attributes using airborne laser scanning and aerial photographs , 2007 .

[67]  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 .

[68]  Paolo Frasconi,et al.  Learning without local minima in radial basis function networks , 1995, IEEE Trans. Neural Networks.

[69]  Christian Messier,et al.  Thinking and acting differently for sustainable management of the boreal forest , 1999 .

[70]  J. Eitel,et al.  Quantifying aboveground forest carbon pools and fluxes from repeat LiDAR surveys , 2012 .

[71]  Achille Fokoue,et al.  An effective algorithm for hyperparameter optimization of neural networks , 2017, IBM J. Res. Dev..

[72]  Qingshan Liu,et al.  Cascaded Recurrent Neural Networks for Hyperspectral Image Classification , 2017, IEEE Transactions on Geoscience and Remote Sensing.

[73]  Hang Zhou,et al.  Deep learning based multi-temporal crop classification , 2019, Remote Sensing of Environment.

[74]  N. Coops,et al.  Estimating canopy structure of Douglas-fir forest stands from discrete-return LiDAR , 2007, Trees.

[75]  Göran Ståhl,et al.  Model-assisted regional forest biomass estimation using LiDAR and InSAR as auxiliary data: A case study from a boreal forest area , 2011 .

[76]  Yao Yu,et al.  Ensemble Learning for Hyperspectral Image Classification Using Tangent Collaborative Representation , 2020, IEEE Transactions on Geoscience and Remote Sensing.

[77]  Sebastian Ruder,et al.  An Overview of Multi-Task Learning in Deep Neural Networks , 2017, ArXiv.