Mapping Coastal Vegetation Using an Expert System and Hyperspectral Imagery

Mapping and monitoring salt marshes in the Netherlands are important activities of the Ministry of Public Works (Rijkswaterstaat). The Survey Department (Meetkundige Dienst) produces vegetation maps using aerial photographs. However, it is a time-consuming and expensive activity. The accuracy of the conventional vegetation map derived using aerial photograph interpretation (API) is estimated to be approximately 43%. An alternative method is demonstrated that uses an expert system to combine airborne hyperspectral imagery with terrain data derived from radar altimetry. The accuracy of the vegetation map generated by the expert system increased to 66%. When hyperspectral imagery alone was used to classify coastal wetlands, an accuracy of 40% was achieved - comparable to the accuracy of the API-derived vegetation map. An analysis of the efficiency of the proposed expert system showed that the speed of map production is increased by using the new method. This means that digital image classification using the expert system is an objective and repeatable method superior to the conventional API method.

[1]  John F. O'Callaghan,et al.  The extraction of drainage networks from digital elevation data , 1984, Comput. Vis. Graph. Image Process..

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

[3]  A. Skidmore,et al.  An Operational GIS Expert System for Mapping Forest Soils , 1996 .

[4]  Andrew K. Skidmore,et al.  Use of an expert system to map forest soils from a geographical information system , 1991, Int. J. Geogr. Inf. Sci..

[5]  J. Leeuw,et al.  Salt marshes along the coast of The Netherlands , 1993, Hydrobiologia.

[6]  P. Adam.  Saltmarshes in a time of change , 2002, Environmental Conservation.

[7]  Tong Lee,et al.  Probabilistic and Evidential Approaches for Multisource Data Analysis , 1987, IEEE Transactions on Geoscience and Remote Sensing.

[8]  Chris Naylor,et al.  How to build an inferencing engine , 1989 .

[9]  J. Bakker,et al.  Nature Management by Grazing and Cutting , 1989, Geobotany.

[10]  A. Skidmore.  Terrain position as mapped from a gridded digital elevation model , 1990 .

[11]  J. Janssen.  Monitoring of salt-marsh vegetation by sequential mapping , 2001 .

[12]  Wim Bakker,et al.  Hyperspectral edge filtering for measuring homogeneity of surface cover types , 2002 .

[13]  A. Skidmore.  An expert system classifies eucalypt forest types using thematic mapper data and a digital terrain model , 1989 .

[14]  Russell G. Congalton,et al.  Assessing the accuracy of remotely sensed data : principles and practices , 1998 .

[15]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[16]  Richard Forsyth,et al.  Expert systems: Principles and case studies , 1984 .

[17]  Emmanuel P. Baltsavias,et al.  Airborne laser scanning: existing systems and firms and other resources , 1999 .

[18]  B. Turner,et al.  Performance of a neural network: mapping forests using GIS and remotely sensed data , 1997 .