Tree Species Classification Based on ASDER and MALSTM-FCN

Tree species classification based on multi-source remote sensing data is essential for ecological evaluation, environmental monitoring, and forest management. The optimization of classification features and the performance of classification methods are crucial to tree species classification. This paper proposes Angle-weighted Standard Deviation Elliptic Cross-merge Rate (ASDER) as a separability metric for feature optimization. ASDER uses mutual information to represent the separability metric and avoids the difficulty of differentiation caused by multiple ellipse centers and coordinate origins forming straight lines by angle weighting. In classification method, Multi-head Self-attention Long Short-Term Memory—Full Convolution Network (MALSTM-FCN) is constructed in this paper. MALSTM-FCN enhances the global correlation in time series and improves classification accuracy through a multi-head self-attention mechanism. This paper takes Beijing Olympic Forest Park (after this, referred to as Aosen) as the research area, constructs a tree species classification dataset based on an actual ground survey, and obtains a classification accuracy of 95.20% using the above method. This paper demonstrates the effectiveness of ASDER and MALSTM-FCN by comparing temporal entropy and LSTM-FCN and shows that the method has some practicality for tree species classification.

[1]  Xiaohui Lin,et al.  A new feature selection method based on feature distinguishing ability and network influence , 2022, J. Biomed. Informatics.

[2]  R. Pu.  Mapping Tree Species Using Advanced Remote Sensing Technologies: A State-of-the-Art Review and Perspective , 2021, Journal of Remote Sensing.

[3]  Hui Yu,et al.  A review on the attention mechanism of deep learning , 2021, Neurocomputing.

[4]  Salvatore Praticò,et al.  Machine Learning Classification of Mediterranean Forest Habitats in Google Earth Engine Based on Seasonal Sentinel-2 Time-Series and Input Image Composition Optimisation , 2021, Remote. Sens..

[5]  Jacek Rapinski,et al.  A Review of Tree Species Classification Based on Airborne LiDAR Data and Applied Classifiers , 2021, Remote. Sens..

[6]  M. Onishi,et al.  Explainable identification and mapping of trees using UAV RGB image and deep learning , 2021, Scientific Reports.

[7]  Bin Zhang,et al.  Three-dimensional convolutional neural network model for tree species classification using airborne hyperspectral images , 2020, Remote Sensing of Environment.

[8]  Pedro Walfir M. Souza Filho,et al.  Reconstructing Three Decades of Land Use and Land Cover Changes in Brazilian Biomes with Landsat Archive and Earth Engine , 2020, Remote. Sens..

[9]  Hongzhang Xu,et al.  Deep learning in environmental remote sensing: Achievements and challenges , 2020, Remote Sensing of Environment.

[10]  Eija Honkavaara,et al.  A Novel Deep Learning Method to Identify Single Tree Species in UAV-Based Hyperspectral Images , 2020, Remote. Sens..

[11]  Kaili Cao,et al.  An Improved Res-UNet Model for Tree Species Classification Using Airborne High-Resolution Images , 2020, Remote. Sens..

[12]  Weiwei Jiang,et al.  Time series classification: nearest neighbor versus deep learning models , 2020, SN Applied Sciences.

[13]  Shaukat Ali Shahee,et al.  An effective distance based feature selection approach for imbalanced data , 2019, Applied Intelligence.

[14]  Peng Gao,et al.  Landslide mapping with remote sensing: challenges and opportunities , 2020, International Journal of Remote Sensing.

[15]  J. Oviedo,et al.  Income and Ecosystem Service Comparisons of Refined National and Agroforestry Accounting Frameworks: Application to Holm Oak Open Woodlands in Andalusia, Spain , 2020, Forests.

[16]  Sebastian Böck,et al.  Optimal Input Features for Tree Species Classification in Central Europe Based on Multi-Temporal Sentinel-2 Data , 2019, Remote. Sens..

[17]  Ping Zhang,et al.  Distinguishing two types of labels for multi-label feature selection , 2019, Pattern Recognit..

[18]  Guangpeng Fan,et al.  Development and Testing of a New Ground Measurement Tool to Assist in Forest GIS Surveys , 2019, Forests.

[19]  Jiancheng Luo,et al.  Long-short-term-memory-based crop classification using high-resolution optical images and multi-temporal SAR data , 2019, GIScience & Remote Sensing.

[20]  Michele Dalponte,et al.  Tree Species Classification in a Highly Diverse Subtropical Forest Integrating UAV-Based Photogrammetric Point Cloud and Hyperspectral Data , 2019, Remote. Sens..

[21]  Dirk Pflugmacher,et al.  Forest Stand Species Mapping Using the Sentinel-2 Time Series , 2019, Remote. Sens..

[22]  Agata Hoscilo,et al.  Mapping Forest Type and Tree Species on a Regional Scale Using Multi-Temporal Sentinel-2 Data , 2019, Remote. Sens..

[23]  Maitiniyazi Maimaitijiang,et al.  Urban Tree Species Classification Using a WorldView-2/3 and LiDAR Data Fusion Approach and Deep Learning , 2019, Sensors.

[24]  Houshang Darabi,et al.  Insights Into LSTM Fully Convolutional Networks for Time Series Classification , 2019, IEEE Access.

[25]  Lu Xu,et al.  Farmland Extraction from High Spatial Resolution Remote Sensing Images Based on Stratified Scale Pre-Estimation , 2019, Remote. Sens..

[26]  Yongwha Chung,et al.  Resource-Efficient Pet Dog Sound Events Classification Using LSTM-FCN Based on Time-Series Data , 2018, Sensors.

[27]  Min Wang,et al.  Very high resolution remote sensing image classification with SEEDS-CNN and scale effect analysis for superpixel CNN classification , 2018, International Journal of Remote Sensing.

[28]  Heather Reese,et al.  Tree Species Classification with Multi-Temporal Sentinel-2 Data , 2018, Remote. Sens..

[29]  Dirk Tiede,et al.  Evaluation of Different Machine Learning Algorithms for Scalable Classification of Tree Types and Tree Species Based on Sentinel-2 Data , 2018, Remote. Sens..

[30]  Shutao Li,et al.  Remote Sensing Scene Classification Using Multilayer Stacked Covariance Pooling , 2018, IEEE Transactions on Geoscience and Remote Sensing.

[31]  Houshang Darabi,et al.  Multivariate LSTM-FCNs for Time Series Classification , 2018, Neural Networks.

[32]  K-R Müller,et al.  SchNet - A deep learning architecture for molecules and materials. , 2017, The Journal of chemical physics.

[33]  Michael Dixon,et al.  Google Earth Engine: Planetary-scale geospatial analysis for everyone , 2017 .

[34]  Muhammad Attique Khan,et al.  A framework of human detection and action recognition based on uniform segmentation and combination of Euclidean distance and joint entropy-based features selection , 2017, EURASIP J. Image Video Process..

[35]  Ferran Gascon,et al.  Sen2Cor for Sentinel-2 , 2017, Remote Sensing.

[36]  Houshang Darabi,et al.  LSTM Fully Convolutional Networks for Time Series Classification , 2017, IEEE Access.

[37]  Baofeng Su,et al.  Significant Remote Sensing Vegetation Indices: A Review of Developments and Applications , 2017, J. Sensors.

[38]  Junliang Liu,et al.  Convolutional neural networks for time series classification , 2017 .

[39]  Daoqiang Zhang,et al.  Feature selection with effective distance , 2016, Neurocomputing.

[40]  Xiang Li,et al.  Deep learning architecture for air quality predictions , 2016, Environmental Science and Pollution Research.

[41]  Mathieu Fauvel,et al.  Tree Species Classification in Temperate Forests Using Formosat-2 Satellite Image Time Series , 2016, Remote. Sens..

[42]  Fang Liu,et al.  Unsupervised feature selection based on maximum information and minimum redundancy for hyperspectral images , 2016, Pattern Recognit..

[43]  A. Hovi,et al.  LiDAR waveform features for tree species classification and their sensitivity to tree- and acquisition related parameters , 2016 .

[44]  Bin Wang,et al.  Confidence Analysis of Standard Deviational Ellipse and Its Extension into Higher Dimensional Euclidean Space , 2015, PloS one.

[45]  Haider Banka,et al.  A Hamming distance based binary particle swarm optimization (HDBPSO) algorithm for high dimensional feature selection, classification and validation , 2015, Pattern Recognit. Lett..

[46]  Michele Dalponte,et al.  Tree Species Classification in Boreal Forests With Hyperspectral Data , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[47]  Zheng Zhao,et al.  Massively parallel feature selection: an approach based on variance preservation , 2012, Machine Learning.

[48]  Clement Atzberger,et al.  Tree Species Classification with Random Forest Using Very High Spatial Resolution 8-Band WorldView-2 Satellite Data , 2012, Remote. Sens..

[49]  L. Bruzzone,et al.  Tree species classification in the Southern Alps based on the fusion of very high geometrical resolution multispectral/hyperspectral images and LiDAR data , 2012 .

[50]  Barbara Koch,et al.  Investigating multiple data sources for tree species classification in temperate forest and use for single tree delineation , 2012, Int. J. Appl. Earth Obs. Geoinformation.

[51]  H. Alexander,et al.  Refining the oak-fire hypothesis for management of oak-dominated forests of the eastern United States , 2012 .

[52]  Hujun Bao,et al.  A Variance Minimization Criterion to Feature Selection Using Laplacian Regularization , 2011, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[53]  Barbara Koch,et al.  Exploring full-waveform LiDAR parameters for tree species classification , 2011, Int. J. Appl. Earth Obs. Geoinformation.

[54]  Paul Mangiameli,et al.  The Effects and Interactions of Data Quality and Problem Complexity on Classification , 2011, JDIQ.

[55]  R. Tibshirani,et al.  Covariance‐regularized regression and classification for high dimensional problems , 2009, Journal of the Royal Statistical Society. Series B, Statistical methodology.

[56]  Adam C. Winstanley,et al.  Invariant optimal feature selection: A distance discriminant and feature ranking based solution , 2008, Pattern Recognit..

[57]  Benoit Rivard,et al.  Intra- and inter-class spectral variability of tropical tree species at La Selva, Costa Rica: Implications for species identification using HYDICE imagery , 2006 .

[58]  A. Gelman.  Discussion of "Analysis of variance--why it is more important than ever" by A. Gelman , 2005, math/0508530.

[59]  Jianxin Gong,et al.  Clarifying the Standard Deviational Ellipse , 2002 .

[60]  D. Massart,et al.  The Mahalanobis distance , 2000 .

[61]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[62]  Lorenzo Bruzzone,et al.  An extension of the Jeffreys-Matusita distance to multiclass cases for feature selection , 1995, IEEE Trans. Geosci. Remote. Sens..

[63]  I. Csiszár.  $I$-Divergence Geometry of Probability Distributions and Minimization Problems , 1975 .

[64]  R. S. Yuill.  The Standard Deviational Ellipse; An Updated Tool for Spatial Description , 1971 .

[65]  D. Welty Lefever,et al.  Measuring Geographic Concentration by Means of the Standard Deviational Ellipse , 1926, American Journal of Sociology.

[66]  Osslan Osiris Vergara-Villegas,et al.  Auto-adaptive multilayer perceptron for univariate time series classification , 2021, Expert Syst. Appl..

[67]  Qingjiu Tian,et al.  Exploitation of Time Series Sentinel-2 Data and Different Machine Learning Algorithms for Detailed Tree Species Classification , 2021, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[68]  M. Weiss,et al.  Remote sensing for agricultural applications: A meta-review , 2020 .

[69]  Jiří Šťastný,et al.  Time series classification using k-Nearest neighbours, Multilayer Perceptron and Learning Vector Quantization algorithms , 2012 .

[70]  Wu Yi-xi.  Ecological Concepts of Plants Planning in Beijing Olympic Forest Park , 2006 .

[71]  Jerome H. Friedman,et al.  On Bias, Variance, 0/1—Loss, and the Curse-of-Dimensionality , 2004, Data Mining and Knowledge Discovery.

[72]  Alexandre Carleer,et al.  Exploitation of Very High Resolution Satellite Data for Tree Species Identification , 2004 .

[73]  M. Lane,et al.  Converging global indicators for sustainable forest management , 2004 .

[74]  Yannis Manolopoulos,et al.  Feature-based classification of time-series data , 2001 .