A Method for Application of Classification Tree Models to Map Aquatic Vegetation Using Remotely Sensed Images from Different Sensors and Dates

In previous attempts to identify aquatic vegetation from remotely-sensed images using classification trees (CT), the images used to apply CT models to different times or locations necessarily originated from the same satellite sensor as that from which the original images used in model development came, greatly limiting the application of CT. We have developed an effective normalization method to improve the robustness of CT models when applied to images originating from different sensors and dates. A total of 965 ground-truth samples of aquatic vegetation types were obtained in 2009 and 2010 in Taihu Lake, China. Using relevant spectral indices (SI) as classifiers, we manually developed a stable CT model structure and then applied a standard CT algorithm to obtain quantitative (optimal) thresholds from 2009 ground-truth data and images from Landsat7-ETM+, HJ-1B-CCD, Landsat5-TM and ALOS-AVNIR-2 sensors. Optimal CT thresholds produced average classification accuracies of 78.1%, 84.7% and 74.0% for emergent vegetation, floating-leaf vegetation and submerged vegetation, respectively. However, the optimal CT thresholds for different sensor images differed from each other, with an average relative variation (RV) of 6.40%. We developed and evaluated three new approaches to normalizing the images. The best-performing method (Method of 0.1% index scaling) normalized the SI images using tailored percentages of extreme pixel values. Using the images normalized by Method of 0.1% index scaling, CT models for a particular sensor in which thresholds were replaced by those from the models developed for images originating from other sensors provided average classification accuracies of 76.0%, 82.8% and 68.9% for emergent vegetation, floating-leaf vegetation and submerged vegetation, respectively. Applying the CT models developed for normalized 2009 images to 2010 images resulted in high classification (78.0%–93.3%) and overall (92.0%–93.1%) accuracies. Our results suggest that Method of 0.1% index scaling provides a feasible way to apply CT models directly to images from sensors or time periods that differ from those of the images used to develop the original models.

[1]  P. Chow-Fraser,et al.  Mapping Floating and Emergent Aquatic Vegetation in Coastal Wetlands of Eastern Georgian Bay, Lake Huron, Canada , 2010, Wetlands.

[2]  Christopher D. Elvidge,et al.  Comparison of relative radiometric normalization techniques , 1996 .

[3]  Xiaojun Yang,et al.  Relative Radiometric Normalization Performance for Change Detection from Multi-Date Satellite Images , 2000 .

[4]  Weiping Hu,et al.  [Spatial distribution characteristics and ecological significance of alkaline phosphatase in water column of Taihu Lake]. , 2009, Huan jing ke xue= Huanjing kexue.

[5]  P. Chavez.  Image-Based Atmospheric Corrections - Revisited and Improved , 1996 .

[6]  Dehua Zhao,et al.  Remote sensing of aquatic vegetation distribution in Taihu Lake using an improved classification tree with modified thresholds. , 2012, Journal of environmental management.

[7]  F. Dahdouh-Guebas.  The Use of Remote Sensing and GIS in the Sustainable Management of Tropical Coastal Ecosystems , 2002 .

[8]  Gu Xiao-hong,et al.  Aquatic macrophytes in East Lake Taihu and its interaction with water environment , 2008 .

[9]  S. K. McFeeters.  The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features , 1996 .

[10]  B. M. El Leithy,et al.  Application of remote sensing to site characterisation and environmental change analysis of North African coastal lagoons , 2009, Hydrobiologia.

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

[12]  M. Kelly,et al.  Mapping changes to vegetation pattern in a restoring wetland: Finding pattern metrics that are consistent across spatial scale and time , 2011 .

[13]  P. Chambers,et al.  Global diversity of aquatic macrophytes in freshwater , 2007, Hydrobiologia.

[14]  J. Liira,et al.  Two decades of macrophyte expansion on the shores of a large shallow northern temperate lake-A retrospective series of satellite images , 2010 .

[15]  Guofeng Wu,et al.  Concurrent monitoring of vessels and water turbidity enhances the strength of evidence in remotely sensed dredging impact assessment. , 2007, Water research.

[16]  M. Bauer,et al.  Application of Landsat imagery to regional-scale assessments of lake clarity. , 2002, Water research.

[17]  Peter Bauer-Gottwein,et al.  Hydrologic Dynamics of the Ground-Water-Dependent Sian Ka’an Wetlands, Mexico, Derived from InSAR and SAR Data , 2010, Wetlands.

[18]  T. Heege,et al.  High-resolution satellite remote sensing of littoral vegetation of Lake Sevan (Armenia) as a basis for monitoring and assessment , 2011, Hydrobiologia.

[19]  Ronghua Ma,et al.  Detecting Aquatic Vegetation Changes in Taihu Lake, China Using Multi-temporal Satellite Imagery , 2008, Sensors.

[20]  Dehua Zhao,et al.  Estimation of water clarity in Taihu Lake and surrounding rivers using Landsat imagery , 2011 .

[21]  B. Lundén,et al.  Assessment of changes in the seagrass-dominated submerged vegetation of tropical Chwaka Bay (Zanzibar) using satellite remote sensing , 2006 .

[22]  Charlotte MacAlister,et al.  Mapping wetlands in the Lower Mekong Basin for wetland resource and conservation management using Landsat ETM images and field survey data. , 2009, Journal of environmental management.

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

[24]  Zuhal Akyurek,et al.  Identification and mapping of submerged plants in a shallow lake using Quickbird satellite data. , 2009, Journal of environmental management.

[25]  R. Carignan,et al.  An evaluation of approaches used to determine the distribution and biomass of emergent and submerged aquatic macrophytes over large spatial scales , 2003 .

[26]  K. Bjorndal,et al.  Historical Overfishing and the Recent Collapse of Coastal Ecosystems , 2001, Science.

[27]  K. Moore,et al.  Chesapeake Bay: An Unprecedented Decline in Submerged Aquatic Vegetation , 1983, Science.

[28]  S. Goetz.  Multi-sensor analysis of NDVI, surface temperature and biophysical variables at a mixed grassland site , 1997 .

[29]  Brigitte Poulin,et al.  Wetland monitoring using classification trees and SPOT-5 seasonal time series , 2010 .

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

[31]  John M. Melack,et al.  Remote sensing of aquatic vegetation: theory and applications , 2008, Environmental monitoring and assessment.

[32]  Yong Q. Tian,et al.  Differentiating aquatic plant communities in a eutrophic river using hyperspectral and multispectral remote sensing , 2010 .

[33]  Thomas P. Albright,et al.  Monitoring the dynamics of an invasive emergent macrophyte community using operational remote sensing data , 2011, Hydrobiologia.

[34]  John M. Melack,et al.  Spatial and temporal variability of macrophyte cover and productivity in the eastern Amazon floodplain: A remote sensing approach , 2010 .

[35]  J. Kämäri,et al.  Detection of water quality using simulated satellite data and semi-empirical algorithms in Finland. , 2001, The Science of the total environment.

[36]  Patricia Chow-Fraser,et al.  Use of IKONOS Imagery to Map Coastal Wetlands of Georgian Bay , 2007 .

[37]  Frédéric Baret,et al.  Intercalibration of vegetation indices from different sensor systems , 2003 .

[38]  R. Flower,et al.  Environmental science and management of coastal lagoons in the Southern Mediterranean Region: key issues revealed by the MELMARINA Project , 2009, Hydrobiologia.

[39]  Duan Hongtao,et al.  Cyanobacteria bloom monitoring with remote sensing in Lake Taihu , 2008 .

[40]  M. Kennish.  Environmental threats and environmental future of estuaries , 2002, Environmental Conservation.

[41]  Gérard Dedieu,et al.  Relative Radiometric Normalization and Atmospheric Correction of a SPOT 5 Time Series , 2008, Sensors.

[42]  R. Lawrence,et al.  Mapping wetlands and riparian areas using Landsat ETM+ imagery and decision-tree-based models , 2006, Wetlands.

[43]  E Brown de Colstoun,et al.  National Park vegetation mapping using multitemporal Landsat 7 data and a decision tree classifier , 2003 .

[44]  Vittorio E. Brando,et al.  Retrospective seagrass change detection in a shallow coastal tidal Australian lake , 2005 .

[45]  S. Fyfe,et al.  Spatial and temporal variation in spectral reflectance: Are seagrass species spectrally distinct? , 2003 .

[46]  Boqiang Qin,et al.  Lake eutrophication: Control countermeasures and recycling exploitation , 2009 .

[47]  P. M. Teilleta,et al.  A generalized approach to the vicarious calibration of multiple Earth observation sensors using hyperspectral data , 2001 .

[48]  Paul Whitehead,et al.  Flow controls on lowland river macrophytes: a review. , 2008, The Science of the total environment.