Land use and land cover change detection using satellite remote sensing techniques in the mountainous Three Gorges Area, China

The Three Gorges Area (TGA), along the Yangtze River, China has been experiencing drastic land use and land cover (LU/LC) changes since the commencement of the construction of the Three Gorges Dam in 1994. These changes may have environmental impacts. However, information about the changes is limited and difficult to obtain. In this paper, optical satellite imagery is used to detect LU/LC changes during the study period 1987–2006 for the complicated, high-relief environment. A case study was conducted in Zigui County of Hubei Province within the TGA. A site-specific procedure using a decision rule-based classification method and a post classification change detection technique is developed to combine spectral and spatial knowledge in the classification of multi-temporal images. Using the decision rule-based classification method, overall accuracies of LU/LC maps of seven classes between 73.4% and 89.5% were obtained, increased by 4–5% over that using the traditional method. The results show that the main trend in LU/LC change in the study area throughout the monitoring period was a steady reduction in natural vegetation areas. About 32% of the total area of natural vegetation, including forest, shrub and grass, was lost to built up areas, crop fields and orchards.

[1]  Yi-Tao Cai,et al.  Weathering Characteristics of Sloping Fields in the Three Gorges Reservoir Area, China 1 1 Project supported by the National Natural Science Foundation of China (No. 40272126) and the Nanjing University Startup Foundation for Young Scholar (No. 0209005116). , 2006 .

[2]  D. Peddle,et al.  Classification of SPOT HRV imagery and texture features , 1990 .

[3]  R. Richter.  A fast atmospheric correction algorithm applied to Landsat TM images , 1990 .

[4]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[5]  Jinfei Wang,et al.  Deriving terrain and textural information from stereo RADARSAT data for mountainous land cover mapping , 2005 .

[6]  R. Congalton,et al.  Sampling Method and Sample Placement: How Do They Affect the Accuracy of Remotely Sensed Maps? , 2003 .

[7]  Peng Gong,et al.  A comparison of spatial feature extraction algorithms for land-use classification with SPOT HRV data , 1992 .

[8]  Johannes R. Sveinsson,et al.  Feature extraction for multisource data classification with artificial neural networks , 1997 .

[9]  T. M. Lillesand,et al.  Remote Sensing and Image Interpretation , 1980 .

[10]  B. Xu,et al.  Remote Sensing of Forests Over Time , 2003 .

[11]  Russell G. Congalton,et al.  A review of assessing the accuracy of classifications of remotely sensed data , 1991 .

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

[13]  J. G. Liu,et al.  Smoothing Filter-based Intensity Modulation : a spectral preserve image fusion technique for improving spatial details , 2001 .

[14]  A. C. Seijmonsbergen,et al.  Improved landsat-based forest mapping in steep mountainous terrain , 2003 .

[15]  Patrick Hostert,et al.  Cross-border comparison of land cover and landscape pattern in Eastern Europe using a hybrid classification technique , 2006 .

[16]  T. M. Lillesand,et al.  Rule-based classification models: flexible integration of satellite imagery and thematic spatial data , 1992 .

[17]  Barry Haack,et al.  Radar spatial considerations for land cover extraction , 2005 .

[18]  Thierry Toutin,et al.  Review article: Geometric processing of remote sensing images: models, algorithms and methods , 2004 .

[19]  Pol Coppin,et al.  Review ArticleDigital change detection methods in ecosystem monitoring: a review , 2004 .

[20]  P. Gong,et al.  Urban built-up land change detection with road density and spectral information from multi-temporal Landsat TM data , 2002 .

[21]  P. Mather,et al.  Classification Methods for Remotely Sensed Data , 2001 .

[22]  J. G. Liu,et al.  Smoothing Filter-based Intensity Modulation: A spectral preserve image fusion technique for improving spatial details , 2000 .

[23]  Dhruba Pikha Shrestha,et al.  Land use classification in mountainous areas : integration of image processing, digital elevation data and field knowledge : application to Nepal , 2001 .

[24]  R. Richter,et al.  Correction of satellite imagery over mountainous terrain. , 1998, Applied optics.

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

[26]  Z. Shia,et al.  Soil conservation planning at the small watershed level using RUSLE with GIS : a case study in the Three Gorge Area of China , 2003 .

[27]  R. Lawrence.  Rule-Based Classification Systems Using Classification and Regression Tree (CART) Analysis , 2001 .

[28]  Amy E. Daniels,et al.  Incorporating domain knowledge and spatial relationships into land cover classifications: a rule‐based approach , 2006 .