Tree Species Classification with Multi-Temporal Sentinel-2 Data

The Sentinel-2 program provides the opportunity to monitor terrestrial ecosystems with a high temporal- and spectral resolution. In this study, the utilization of multi-temporal Sentinel-2 imagery and it’s spectral variation due to phenology for classification of common tree species is evaluated at the forest estate Remningstorp in central Sweden. The tree species classes to be classified were: Norway Spruce (Picea abies), Scots Pine (Pinus silvestris), Hybrid Larch (Larix × marschlinsii), Silver Birch (Betula pendula) and Pedunculate Oak (Quercus rubur). The Random Forest classifier (RF) was fitted to four Sentinel-2 images taken during the vegetation period of 2017. The RF classifier was also coupled with the feature selection algorithm Recursive Feature Elimination to form a model with an optimal subset of bands. In addition to the classification, spectral profile plots were constructed for each species to visualize the possibility for identifying the less represented tree species. The use of four satellite images from April 7th, May 27th, July 9th and October 19th resulted in a higher overall accuracy (86.4 %) compared to using single images (71.5 % – 79.4 %). The late spring image (May 27th) was found to be important since it always was included in the most accurate classifications, independently of the number of images. The best combination of bands resulted in a model with 87.6 % in overall accuracy and included 37 of 40 bands. The highest ranked bands were all May bands except the red band, the SWIR 1-2 and red bands from April, July and October. The 5 tree species classes were classified with satisfying results and the Producer’s Accuracy ranged from 73.7 % to 97.4 %.

[1]  Michael E. Schaepman,et al.  Retrieval of foliar information about plant pigment systems from high resolution spectroscopy , 2009 .

[2]  F. M. Danson,et al.  Satellite remote sensing of forest resources: three decades of research development , 2005 .

[3]  Marc Nelson,et al.  Evaluating Multitemporal Sentinel-2 data for Forest Mapping using Random Forest , 2017 .

[4]  M. Nilsson,et al.  Countrywide Estimates of Forest Variables Using Satellite Data and Field Data from the National Forest Inventory , 2003, Ambio.

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

[6]  Heather Reese,et al.  Classification of Sweden's Forest and Alpine Vegetation Using Optical Satellite and Inventory Data , 2011 .

[7]  R. Hill,et al.  Mapping tree species in temperate deciduous woodland using time‐series multi‐spectral data , 2010 .

[8]  Peter T. Wolter,et al.  Improved forest classification in the northern Lake States using multi-temporal Landsat imagery , 1995 .

[9]  R. Congalton,et al.  Evaluating seasonal variability as an aid to cover-type mapping from Landsat Thematic Mapper data in the Northeast , 1995 .

[10]  Matthias Drusch,et al.  Sentinel-2: ESA's Optical High-Resolution Mission for GMES Operational Services , 2012 .

[11]  John A. Silander,et al.  Delineating forest canopy species in the northeastern united states using multi-temporal TM imagery , 1998 .

[12]  Clement Atzberger,et al.  How much does multi-temporal Sentinel-2 data improve crop type classification? , 2018, Int. J. Appl. Earth Obs. Geoinformation.

[13]  Dar A. Roberts,et al.  Species-Level Differences in Hyperspectral Metrics among Tropical Rainforest Trees as Determined by a Tree-Based Classifier , 2012, Remote. Sens..

[14]  Chao Chen,et al.  Using Random Forest to Learn Imbalanced Data , 2004 .

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

[16]  Zhe Zhu,et al.  Optimizing selection of training and auxiliary data for operational land cover classification for the LCMAP initiative , 2016 .

[17]  Thomas M. Lillesand,et al.  Statewide land cover derived from multiseasonal Landsat TM data: A retrospective of the WISCLAND project , 2002 .

[18]  Clement Atzberger,et al.  First Experience with Sentinel-2 Data for Crop and Tree Species Classifications in Central Europe , 2016, Remote. Sens..

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

[20]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .

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

[22]  D. Roberts,et al.  Hyperspectral discrimination of tropical rain forest tree species at leaf to crown scales , 2005 .

[23]  G. Asner.  Biophysical and Biochemical Sources of Variability in Canopy Reflectance , 1998 .

[24]  Xiaolin Zhu,et al.  Accurate mapping of forest types using dense seasonal Landsat time-series , 2014 .

[25]  G. F. Hughes,et al.  On the mean accuracy of statistical pattern recognizers , 1968, IEEE Trans. Inf. Theory.