Co-Orbital Sentinel 1 and 2 for LULC Mapping with Emphasis on Wetlands in a Mediterranean Setting Based on Machine Learning

This study aimed at evaluating the synergistic use of Sentinel-1 and Sentinel-2 data combined with the Support Vector Machines (SVMs) machine learning classifier for mapping land use and land cover (LULC) with emphasis on wetlands. In this context, the added value of spectral information derived from the Principal Component Analysis (PCA), Minimum Noise Fraction (MNF) and Grey Level Co-occurrence Matrix (GLCM) to the classification accuracy was also evaluated. As a case study, the National Park of Koronia and Volvi Lakes (NPKV) located in Greece was selected. LULC accuracy assessment was based on the computation of the classification error statistics and kappa coefficient. Findings of our study exemplified the appropriateness of the spatial and spectral resolution of Sentinel data in obtaining a rapid and cost-effective LULC cartography, and for wetlands in particular. The most accurate classification results were obtained when the additional spectral information was included to assist the classification implementation, increasing overall accuracy from 90.83% to 93.85% and kappa from 0.894 to 0.928. A post-classification correction (PCC) using knowledge-based logic rules further improved the overall accuracy to 94.82% and kappa to 0.936. This study provides further supporting evidence on the suitability of the Sentinels 1 and 2 data for improving our ability to map a complex area containing wetland and non-wetland LULC classes.

[1]  R. Valentini,et al.  Discrimination of tropical forest types, dominant species, and mapping of functional guilds by hyperspectral and simulated multispectral Sentinel-2 data , 2016 .

[2]  Sang-Hoon Hong,et al.  Evaluation of Polarimetric SAR Decomposition for Classifying Wetland Vegetation Types , 2015, Remote. Sens..

[3]  Mohammed Dabboor,et al.  A Collection of SAR Methodologies for Monitoring Wetlands , 2015, Remote. Sens..

[4]  Thomas Blaschke,et al.  Land cover change assessment using decision trees, support vector machines and maximum likelihood classification algorithms , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[5]  C. Hopkinson,et al.  A Physically Based Terrain Morphology and Vegetation Structural Classification for Wetlands of the Boreal Plains, Alberta, Canada , 2016 .

[6]  George P. Petropoulos,et al.  Landscape transform and spatial metrics for mapping spatiotemporal land cover dynamics using Earth Observation data-sets , 2016 .

[7]  Arzu Erener,et al.  Classification method, spectral diversity, band combination and accuracy assessment evaluation for urban feature detection , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[8]  David T. Sandwell,et al.  Accuracy and resolution of shuttle radar topography mission data , 2003 .

[9]  David A. Seal,et al.  The Shuttle Radar Topography Mission , 2007 .

[10]  George P. Petropoulos,et al.  Change detection of surface mining activity and reclamation based on a machine learning approach of multi-temporal Landsat TM imagery , 2013 .

[11]  Na Li,et al.  Textural and knowledge-based lithological classification of remote sensing data in southwestern Prieska sub-basin, Transvaal Supergroup, South Africa , 2011 .

[12]  Xuefeng Niu,et al.  Information Extraction of High-Resolution Remotely Sensed Image based on Multiresolution Segmentation , 2013 .

[13]  P. Vlek,et al.  Global Inventory of Wetlands and their Role in the Carbon Cycle , 2003 .

[14]  D. Russi,et al.  The Economics of Ecosystems and Biodiversity for Wetlands and Water , 2010 .

[15]  Timothy A. Warner,et al.  Predicting Palustrine Wetland Probability Using Random Forest Machine Learning and Digital Elevation Data-Derived Terrain Variables , 2016 .

[16]  Linda Aune-Lundberg,et al.  Comparison of variance estimation methods for use with two-dimensional systematic sampling of land use/land cover data , 2014, Environ. Model. Softw..

[17]  S. Robeson,et al.  Mapping spatial distribution and biomass of coastal wetland vegetation in Indonesian Papua by combining active and passive remotely sensed data , 2016 .

[18]  Kaishan Song,et al.  Mapping Wetland Areas Using Landsat-Derived NDVI and LSWI: A Case Study of West Songnen Plain, Northeast China , 2014, Journal of the Indian Society of Remote Sensing.

[19]  Nobuyuki Kobayashi,et al.  Parameter tuning in the support vector machine and random forest and their performances in cross- and same-year crop classification using TerraSAR-X , 2014 .

[20]  Michael G. Madden,et al.  The Effect of Principal Component Analysis on Machine Learning Accuracy with High Dimensional Spectral Data , 2005, SGAI Conf..

[21]  George C. Zalidis,et al.  Mapping irrigated area in Mediterranean basins using low cost satellite Earth Observation , 2008 .

[22]  Ingmar Nitze,et al.  Assessment of multi-temporal, multi-sensor radar and ancillary spatial data for grasslands monitoring in Ireland using machine learning approaches , 2014 .

[23]  N. Davidson.  How much wetland has the world lost? Long-term and recent trends in global wetland area , 2014 .

[24]  Amr H. Abd-Elrahman,et al.  Analyzing fine-scale wetland composition using high resolution imagery and texture features , 2013, Int. J. Appl. Earth Obs. Geoinformation.

[25]  Hongsheng Zhang,et al.  Improving the impervious surface estimation with combined use of optical and SAR remote sensing images , 2014 .

[26]  P. Srivastava,et al.  Quantifying land use/land cover spatio-temporal landscape pattern dynamics from Hyperion using SVMs classifier and FRAGSTATS® , 2018 .

[27]  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..

[28]  George P. Petropoulos,et al.  Burnt area delineation from a uni-temporal perspective based on Landsat TM imagery classification using Support Vector Machines , 2011, Int. J. Appl. Earth Obs. Geoinformation.

[29]  Fan Xia,et al.  Assessing object-based classification: advantages and limitations , 2009 .

[30]  Riyad Ismail,et al.  Land cover and land use mapping of the iSimangaliso Wetland Park, South Africa: comparison of oblique and orthogonal random forest algorithms , 2016 .

[32]  F. Visser,et al.  Optical remote sensing of submerged aquatic vegetation: Opportunities for shallow clearwater streams , 2013 .

[33]  Rick L. Lawrence,et al.  Change detection of wetland ecosystems using Landsat imagery and change vector analysis , 2007, Wetlands.

[34]  R. Tiner,et al.  Introduction to Wetland Mapping and Its Challenges , 2015 .

[35]  Volker C. Radeloff,et al.  The Impact of Phenological Variation on Texture Measures of Remotely Sensed Imagery , 2009, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[36]  Qi Chen,et al.  A comparison of classification techniques to support land cover and land use analysis in tropical coastal zones , 2011 .

[37]  L. Boschetti,et al.  Combining ASTER multispectral imagery analysis and support vector machines for rapid and cost-effective post-fire assessment: a case study from the Greek wildland fires of 2007 , 2010 .

[38]  B. Robson,et al.  Automated classification of debris-covered glaciers combining optical, SAR and topographic data in an object-based environment , 2015 .

[39]  Eric Pottier,et al.  An entropy based classification scheme for land applications of polarimetric SAR , 1997, IEEE Trans. Geosci. Remote. Sens..

[40]  Yeqiao Wang,et al.  Remote sensing change detection tools for natural resource managers: Understanding concepts and tradeoffs in the design of landscape monitoring projects , 2009 .

[41]  Qihao Weng,et al.  A survey of image classification methods and techniques for improving classification performance , 2007 .

[42]  Zoltan Szantoi,et al.  Classifying spatially heterogeneous wetland communities using machine learning algorithms and spectral and textural features , 2015, Environmental Monitoring and Assessment.

[43]  Rongqun Zhang,et al.  Study of land cover classification based on knowledge rules using high-resolution remote sensing images , 2011, Expert Syst. Appl..

[44]  P. Srivastava,et al.  Assessing the influence of atmospheric and topographic correction and inclusion of SWIR bands in burned scars detection from high-resolution EO imagery: a case study using ASTER , 2015, Natural Hazards.

[45]  Kristian Zarb Adami,et al.  A Machine Learning approach for automatic land cover mapping from DSLR images over the Maltese Islands , 2018, Environ. Model. Softw..

[46]  C. Samara,et al.  Phosphorus fractionation in lake sediments--lakes Volvi and Koronia, N. Greece. , 2002, Chemosphere.

[47]  Caiyun Zhang,et al.  Object-based Vegetation Mapping in the Kissimmee River Watershed Using HyMap Data and Machine Learning Techniques , 2013, Wetlands.

[48]  George P. Petropoulos,et al.  Evaluation of diverse classification approaches for land use/cover mapping in a Mediterranean region utilizing Hyperion data , 2014, Int. J. Digit. Earth.

[49]  Shengjie Hu,et al.  Global wetlands: Potential distribution, wetland loss, and status. , 2017, The Science of the total environment.

[50]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[51]  Knut Conradsen,et al.  Short-Term Change Detection in Wetlands Using Sentinel-1 Time Series , 2016, Remote. Sens..

[52]  Senén Barro,et al.  Do we need hundreds of classifiers to solve real world classification problems? , 2014, J. Mach. Learn. Res..

[53]  George P. Petropoulos,et al.  Flooding extent cartography with Landsat TM imagery and regularized kernel Fisher's discriminant analysis , 2013, Comput. Geosci..

[54]  Hankui K. Zhang,et al.  Finer resolution observation and monitoring of global land cover: first mapping results with Landsat TM and ETM+ data , 2013 .

[55]  Taskin Kavzoglu,et al.  A kernel functions analysis for support vector machines for land cover classification , 2009, Int. J. Appl. Earth Obs. Geoinformation.

[56]  C. Wright,et al.  Improved wetland remote sensing in Yellowstone National Park using classification trees to combine TM imagery and ancillary environmental data , 2007 .

[57]  George P. Petropoulos,et al.  Hyperion hyperspectral imagery analysis combined with machine learning classifiers for land use/cover mapping , 2012, Expert Syst. Appl..

[58]  Heiko Balzter,et al.  Evaluating Sentinel-2 for Lakeshore Habitat Mapping Based on Airborne Hyperspectral Data , 2015, Sensors.

[59]  George P. Petropoulos,et al.  Remote sensing and GIS analysis for mapping spatio-temporal changes of erosion and deposition of two Mediterranean river deltas: The case of the Axios and Aliakmonas rivers, Greece , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[60]  Qing Zhu,et al.  An integrated flood management system based on linking environmental models and disaster-related data , 2017, Environ. Model. Softw..

[61]  Patrick Matgen,et al.  Flood detection from multi-temporal SAR data using harmonic analysis and change detection , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[62]  Jungho Im,et al.  Support vector machines in remote sensing: A review , 2011 .

[63]  Dionissios P. Kalivas,et al.  Urban vegetation cover extraction from hyperspectral imagery and geographic information system spatial analysis techniques: case of Athens, Greece , 2015 .

[64]  Craig A. Coburn,et al.  A multiscale texture analysis procedure for improved forest stand classification , 2004 .

[65]  M.,et al.  Statistical and Structural Approaches to Texture , 2022 .

[66]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.