A Unifying Approach to Classifying Wetlands in the Ontonagon River Basin, Michigan, Using Multi-temporal Landsat-8 OLI Imagery

Abstract Accurate spatial information is critical to the assessment and protection of wetlands in the context of human intervention and global climate change. However, it is challenging to map and monitor wetland vegetation classes with satisfactory results because of their highly seasonal dynamics, spatial heterogeneity, and spectral similarity. This paper examines the effectiveness of various classification approaches commonly employed in wetland mapping, including the support vector machine (SVM) algorithm, maximum likelihood classifier (MLC), classification and regression tree (CART) and other remote sensing indices, by using multi-temporal Landsat-8 Operational Land Imager (OLI) spectral data and end-member fraction data as well as terrain data. These different mapping approaches were compared in the Ontonagon River drainage basin in upper Michigan, USA, where easily-confused wetland types such as forested wetland, palustrine scrub/shrub wetland, and palustrine emergent wetland are extensively distributed. The results show that multi-temporal data sets can reduce the classification omission caused by the highly seasonal dynamic of wetlands. The spatial heterogeneity can partly be characterized by using end-member fraction maps. Classification of the fraction maps had better results than that using the original spectral data, which implies that the selection of data inputs could be more important than the selection of classifiers. While each algorithm has its own capability of discriminating specific wetland types, CART showed relatively better classification results than the others due to its compatibility and lack of assumptions about data normal distribution. Finally, the authors developed a decision tree method (called DTM), which adopted the satisfactory resultant classification of specific wetland types using MLC and SVM classification, to update the wetland map of Ontonagon River Basin with acceptable accuracy (overall accuracy of 89% and kappa coefficients of 0.89).

[1]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[2]  E. Work,et al.  Utilization of satellite data for inventorying prairie ponds and lakes , 1976 .

[3]  K. Beven,et al.  A physically based, variable contributing area model of basin hydrology , 1979 .

[4]  E. Gorham.  Northern Peatlands: Role in the Carbon Cycle and Probable Responses to Climatic Warming. , 1991, Ecological applications : a publication of the Ecological Society of America.

[5]  J. Settle,et al.  Linear mixing and the estimation of ground cover proportions , 1993 .

[6]  M. Barson,et al.  Remote sensing of Australian wetlands: An evaluation of Landsat TM data for inventory and classification , 1993 .

[7]  Alberto Maria Segre,et al.  Programs for Machine Learning , 1994 .

[8]  B. Wilen,et al.  THE US FISH AND WILDLIFE SERVICE'S NATIONAL WETLANDS INVENTORY PROJECT , 1995 .

[9]  Yong Wang,et al.  Delineation of inundated area and vegetation along the Amazon floodplain with the SIR-C synthetic aperture radar , 1995, IEEE Trans. Geosci. Remote. Sens..

[10]  John B. Adams,et al.  Classification of multispectral images based on fractions of endmembers: Application to land-cover change in the Brazilian Amazon , 1995 .

[11]  Ramakrishna R. Nemani,et al.  A remote sensing based vegetation classification logic for global land cover analysis , 1995 .

[12]  J. Boardman,et al.  Mapping target signatures via partial unmixing of AVIRIS data: in Summaries , 1995 .

[13]  S. Tompkins,et al.  Optimization of endmembers for spectral mixture analysis , 1997 .

[14]  Margaret E. Gardner,et al.  Mapping Chaparral in the Santa Monica Mountains Using Multiple Endmember Spectral Mixture Models , 1998 .

[15]  Vladimir Vapnik,et al.  An overview of statistical learning theory , 1999, IEEE Trans. Neural Networks.

[16]  John A. Richards,et al.  Remote Sensing Digital Image Analysis: An Introduction , 1999 .

[17]  Ross S. Lunetta,et al.  Application of multi-temporal Landsat 5 TM imagery for wetland identification , 1999 .

[18]  W. Mitsch,et al.  The value of wetlands: importance of scale and landscape setting. , 2000 .

[19]  Chein-I Chang,et al.  Fully constrained least squares linear spectral mixture analysis method for material quantification in hyperspectral imagery , 2001, IEEE Trans. Geosci. Remote. Sens..

[20]  Philip A. Townsend,et al.  Mapping Seasonal Flooding in Forested Wetlands Using Multi-Temporal Radarsat SAR , 2001 .

[21]  J. K. Cronk,et al.  Wetland Plants: Biology and Ecology , 2001 .

[22]  Marc Simard,et al.  Mapping tropical coastal vegetation using JERS-1 and ERS-1 radar data with a decision tree classifier , 2002 .

[23]  Haydee Karszenbaum,et al.  Mapping wetlands using multi-temporal RADARSAT-1 data and a decision-based classifier , 2002 .

[24]  P. Maillard.  Comparing Texture Analysis Methods through Classification , 2003 .

[25]  Alan T. Murray,et al.  Estimating impervious surface distribution by spectral mixture analysis , 2003 .

[26]  A. Skidmore,et al.  Spectral discrimination of vegetation types in a coastal wetland , 2003 .

[27]  Stacy L. Ozesmi,et al.  Satellite remote sensing of wetlands , 2002, Wetlands Ecology and Management.

[28]  P. Mausel,et al.  Application of spectral mixture analysis to Amazonian land-use and land-cover classification , 2004 .

[29]  Giles M. Foody,et al.  Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification , 2004 .

[30]  Junhua Li,et al.  A rule-based method for mapping Canada's wetlands using optical, radar and DEM data , 2005 .

[31]  John R. Jensen,et al.  Fuzzy learning vector quantization for hyperspectral coastal vegetation classification , 2006 .

[32]  Gerald J. Niemi,et al.  Land Use Land Cover Change in the U.S. Great Lakes Basin 1992 to 2001 , 2006 .

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

[34]  K. Todd,et al.  Automated discrimination of upland and wetland using terrain derivatives , 2007 .

[35]  Wetland and Water Resource Modeling and Assessment: A Watershed Perspective , 2007 .

[36]  M. Bauer,et al.  Comparison of impervious surface area and normalized difference vegetation index as indicators of surface urban heat island effects in Landsat imagery , 2007 .

[37]  Yichun Xie,et al.  Remote sensing imagery in vegetation mapping: a review , 2008 .

[38]  L. Zhang,et al.  Using a hybrid fuzzy classifier (HFC) to map typical grassland vegetation in Xilin River Basin, Inner Mongolia, China , 2008 .

[39]  C. Johnston,et al.  Wetland types and wetland maps differ in ability to predict dissolved organic carbon concentrations in streams. , 2008, The Science of the total environment.

[40]  K. Clint Slatton,et al.  Modeling temporal variations in multipolarized radar scattering from intertidal coastal wetlands , 2008 .

[41]  C. Scott Findlay,et al.  The effects of adjacent land use on wetland species richness and community composition , 2006, Wetlands.

[42]  Zhang Rongqun,et al.  Classification of wetland from TM imageries based on decision tree , 2009 .

[43]  O. Mutanga,et al.  Multispectral and hyperspectral remote sensing for identification and mapping of wetland vegetation: a review , 2010, Wetlands Ecology and Management.

[44]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[45]  Jin-quan Ai,et al.  Spectral discrimination of an invasive species (Spartina alterniflora) in Min River wetland using field spectrometry , 2013, Other Conferences.

[46]  Joseph F. Knight,et al.  Influence of Multi-Source and Multi-Temporal Remotely Sensed and Ancillary Data on the Accuracy of Random Forest Classification of Wetlands in Northern Minnesota , 2013, Remote. Sens..

[47]  Prashant K. Srivastava,et al.  Appraisal of land use/land cover of mangrove forest ecosystem using support vector machine , 2014, Environmental Earth Sciences.

[48]  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.

[49]  Wenge Ni-Meister,et al.  Mapping wetlands in the Hudson Highlands ecoregion with ALOS PALSAR: an effort to identify potential swamp forest habitat for golden-winged warblers , 2014, Wetlands Ecology and Management.

[50]  Jinsong Deng,et al.  Monitoring Urban Greenness Dynamics Using Multiple Endmember Spectral Mixture Analysis , 2014, PloS one.

[51]  Anup Saikia,et al.  Land-Use Land-Cover Change , 2014 .

[52]  Merryl Alber,et al.  Classification of salt marsh vegetation using edaphic and remote sensing-derived variables , 2014 .

[53]  Xiaoling Chen,et al.  Four decades of winter wetland changes in Poyang Lake based on Landsat observations between 1973 and 2013 , 2015 .

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

[55]  Graham Ferrier,et al.  Automated lithological mapping using airborne hyperspectral thermal infrared data: A case study from Anchorage Island, Antarctica , 2016 .

[56]  L. M. Cowardin,et al.  Classification of Wetlands and Deepwater Habitats of the United States , 2017 .

[57]  Poonam,et al.  Wetland Plants , 2020, Contaminants and Clean Technologies.