Exploiting machine learning algorithms for tree species classification in a semiarid woodland using RapidEye image

Abstract Classification of different tree species in semiarid areas can be challenging as a result of the change in leaf structure and orientation due to soil moisture constraints. Tree species mapping is, however, a key parameter for forest management in semiarid environments. In this study, we examined the suitability of 5-band RapidEye satellite data for the classification of five tree species in mopane woodland of Botswana using machine leaning algorithms with limited training samples.We performed classification using random forest (RF) and support vector machines (SVM) based on EnMap box. The overall accuracies for classifying the five tree species was 88.75 and 85% for both SVM and RF, respectively. We also demonstrated that the new red-edge band in the RapidEye sensor has the potential for classifying tree species in semiarid environments when integrated with other standard bands. Similarly, we observed that where there are limited training samples, SVM is preferred over RF. Finally, we demonstrated that the two accuracy measures of quantity and allocation disagreement are simpler and more helpful for the vast majority of remote sensing classification process than the kappa coefficient. Overall, high species classification can be achieved using strategically located RapidEye bands integrated with advanced processing algorithms.

[1]  P. Treitz,et al.  Canopy chlorophyll concentration estimation using hyperspectral and lidar data for a boreal mixedwood forest in northern Ontario, Canada , 2008 .

[2]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[3]  Wu Tie-jun.  Support vector machines for pattern recognition , 2003 .

[4]  Onisimo Mutanga,et al.  A Review of Remote Sensing of Insect Defoliation and its Implications for the Detection and Mapping of Imbrasia belina Defoliation of Mopane Woodland , 2012 .

[5]  Milenov Pavel,et al.  Analysis of rapieye imagery for annual landcover mapping as an aid to European Union (EU) common agricultural policy , 2010 .

[6]  Shagan Sah,et al.  A multi-temporal fusion-based approach for land cover mapping in support of nuclear incident response , 2013 .

[7]  Wolter Arnberg,et al.  Interpretation of mopane woodlands using air photos with implications on satellite image classification , 2002 .

[8]  C van der Waal,et al.  Induced chemical defences in Colophospermum mopane trees , 2007 .

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

[10]  Jonathan Cheung-Wai Chan,et al.  Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery , 2008 .

[11]  Susan Ringrose,et al.  The darkening effect in drought affected savanna woodland environments relative to soil reflectance in Landsat and SPOT wavebands , 1989 .

[12]  Patrick Hostert,et al.  Urban vegetation classification: Benefits of multitemporal RapidEye satellite data , 2013 .

[13]  Agustin Lobo,et al.  Image segmentation and discriminant analysis for the identification of land cover units in ecology , 1997, IEEE Trans. Geosci. Remote. Sens..

[14]  Lindi J. Quackenbush,et al.  INVESTIGATING NEW ADVANCES IN FOREST SPECIES CLASSIFICATION , 2007 .

[15]  A. Gitelson,et al.  Quantitative estimation of chlorophyll-a using reflectance spectra : experiments with autumn chestnut and maple leaves , 1994 .

[16]  Benoit Stoll,et al.  A Comparison of Machine Learning Algorithms for Classification of Tropical EcosystemsObserved by Multiple Sensors at Multiple Scales , 2011, IGARSS 2011.

[17]  Johannes R. Sveinsson,et al.  Random Forest classification of multisource remote sensing and geographic data , 2004, IGARSS 2004. 2004 IEEE International Geoscience and Remote Sensing Symposium.

[18]  Jeff Czapla-Myers,et al.  Absolute radiometric calibration of the RapidEye multispectral imager using the reflectance-based vicarious calibration method , 2011 .

[19]  S. Franklin.  Remote Sensing for Sustainable Forest Management , 2001 .

[20]  O. Mutanga,et al.  Discriminating the papyrus vegetation (Cyperus papyrus L.) and its co-existent species using random forest and hyperspectral data resampled to HYMAP , 2012 .

[21]  Rick L. Lawrence,et al.  Mapping invasive plants using hyperspectral imagery and Breiman Cutler classifications (RandomForest) , 2006 .

[22]  W. Mojeremane,et al.  Seed Treatments for Enhancing Germination of Colophospermum mopane Seeds: A Multipurpose Tree in Botswana , 2005 .

[23]  Kadim Tasdemir,et al.  ANALYSIS OF RAPIDEYE IMAGERY FOR ANNUAL LANDCOVER MAPPING A S AN AID TO EUROPEAN UNION (EU) COMMON AGRICULTURAL POLICY , 2010 .

[24]  Gregory Asner,et al.  Improving Discrimination of Savanna Tree Species Through a Multiple-Endmember Spectral Angle Mapper Approach: Canopy-Level Analysis , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[25]  George P. Petropoulos,et al.  Support vector machines and object-based classification for obtaining land-use/cover cartography from Hyperion hyperspectral imagery , 2012, Comput. Geosci..

[26]  A. Skidmore,et al.  Red edge shift and biochemical content in grass canopies , 2007 .

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

[28]  B. Kleinschmit,et al.  Testing the red edge channel for improving land-use classifications based on high-resolution multi-spectral satellite data , 2012 .

[29]  Youn-Soo Kim,et al.  Agricultural land cover classification using rapideye satellite imagery in South Korea - first result - , 2011, Remote Sensing.

[30]  Onisimo Mutanga,et al.  DETERMINING THE OPTIMAL SPATIAL RESOLUTION OF REMOTELY SENSED DATA FOR THE DETECTION OF SIREX NOCTILIO INFESTATIONS IN PINE PLANTATIONS IN KWAZULU-NATAL, SOUTH AFRICA , 2008 .

[31]  R. Pontius,et al.  Death to Kappa: birth of quantity disagreement and allocation disagreement for accuracy assessment , 2011 .

[32]  Giles M. Foody,et al.  The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM , 2006 .

[33]  Akin Ozçift,et al.  Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosis. , 2011, Computers in biology and medicine.

[34]  B. Lundén,et al.  MAPPING OF COLOPHOSPERMUM MOPANE USING LANDSAT TM IN EASTERN BOTSWANA , 2008 .

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

[36]  S. Franklin,et al.  Remote sensing of forest environments : concepts and case studies , 2003 .

[37]  Juergen Rossmann,et al.  Using Decision Tree Based Multiclass Support Vector Machines for Forest Mapping , 2011 .

[38]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote sensing images with support vector machines , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[39]  Tiho Ancev,et al.  Improving the Accuracy of Land Use and Land Cover Classification of Landsat Data Using Post-Classification Enhancement , 2009, Remote. Sens..

[40]  Andrew C. Millington,et al.  A hybrid approach to mapping land-use modification and land-cover transition from MODIS time-series data: A case study from the Bolivian seasonal tropics , 2011 .

[41]  Venceslas Goudiaby,et al.  Stable annual pattern of water use by Acacia tortilis in Sahelian Africa. , 2008, Tree physiology.

[42]  Ingmar Nitze,et al.  COMPARISON OF MACHINE LEARNING ALGORITHMS RANDOM FOREST, ARTIFICIAL NEURAL NETWORK AND SUPPORT VECTOR MACHINE TO MAXIMUM LIKELIHOOD FOR SUPERVISED CROP TYPE CLASSIFICATION , 2012 .

[43]  O. Mutanga,et al.  Spectral discrimination of papyrus vegetation (Cyperus papyrus L.) in swamp wetlands using field spectrometry , 2009 .