Xiangnan Liu

Visualizing the uncertainty of geo-information from Landsat ETM+ imagery by fuzzy reasoning

Uncertainty is one important feature of spatial information quality and attracting much more attentions recently. The visualization is an effective way to express the magnitude, pattern and propagation of the uncertainty. In this paper, the visualization method of geospatial information uncertainty in Landsat ETM+ imagery is put forward and described. Firstly, an improved fuzzy reasoning classification method is proposed, and farmland and grassland information are extracted from the ETM+ imagery respectively based on the algorithm. Then the uncertainty of the classification is analyzed, measured and visualized supported by GIS. The uncertainty can be expressed and visualized by different spatial distribution range of cropland and grassland when adjusting their membership values setting. The uncertainty threshold supplies a visual cognition for data users to know the data quality better and make full use of the data more correctly. At the same time, aiming at the overlay areas with similar membership values, other ancillary information can help to improve the classification accuracy and conquer the difficulties in distinguishing cropland from grassland in Landsat ETM+.

Framework for Multi-Sources Spatial Data Integration Analysis

Importance of integrating multi-sources spatial data is widely acknowledged. It is indispensable especially for interdisciplinary projects. This paper brings forward the framework for multi-sources spatial data integration analysis. Types, sources and other issues of the spatial data are discussed, which can bring potential advantages after integration, and data integration issues are summarized. The multiple sources spatial data integration methods are analyzed in detail. Taking land use change study in Changling County as example, the difference between two data sets is analyzed. And through the linkage of semantics LUT and spectral LUT, the originally incomparable data sets become comparable, and the real change can be found out more accurately.

Design and implementation of spatial knowledge grid for integrated spatial analysis

Supported by spatial information grid(SIG), the spatial knowledge grid (SKG) for integrated spatial analysis utilizes the middleware technology in constructing the spatial information grid computation environment and spatial information service system, develops spatial entity oriented spatial data organization technology, carries out the profound computation of the spatial structure and spatial process pattern on the basis of Grid GIS infrastructure, spatial data grid and spatial information grid (specialized definition). At the same time, it realizes the complex spatial pattern expression and the spatial function process simulation by taking the spatial intelligent agent as the core to establish space initiative computation. Moreover through the establishment of virtual geographical environment with man-machine interactivity and blending, complex spatial modeling, network cooperation work and spatial community decision knowledge driven are achieved. The framework of SKG is discussed systematically in this paper. Its implement flow and the key technology with examples of overlay analysis are proposed as well.

Estimating chlorophyll content of rice under soil contamination stress using BPNN

Estimating chlorophyll content of plant exactly is meaningful in precision agriculture because of its ability in indicating photosynthesis activity, stress and nutritional state of plant. Heavy mental contamination in agricultural field has been one of vital ecological environment issues which threaten global environment quality, human being subsistence and food security as well. The soil contamination will damage the plant and change the chlorophyll content of rice. Sometimes the soil contamination stress is weak and there is no obvious and visual symptom, though the plant has been injured. In this study, a back propagation neural-network (BPNN) will be tried to estimate the subtle variations in leaf chlorophyll content of rice under potential contamination stress with hyperspectral data in field conditions. Field works were conducted in seven rice fields with different heavy mental contamination stress level in central part of northeast China during the summer of 2008 and 2009. Hyperspectral data, samples of rice and soil were acquired and analyzed. The hyperspectral data were processed using continuum removal, differential computation and binary encoding. Eleven hyperspectral variables were derived and the correlation between them and contamination was analyzed. Stepwise multiple linear regression methods were investigated to ascertain their performances in the prediction of rice leaf comparative chlorophyll content respectively. Models established by the linear regression analysis indicated the lower feasibility for estimating rice leaf chlorophyll content associated with soil contamination. Neural-network models provide more robust results for complicated system analysis than conventional mathematical models. The higher coefficients of determination (R2=0.912) and lower prediction errors (RMSE=2.34) was obtained using a BPNN model of 11-9-5-1 with an ideal performance.

Vegetation cover change in semi-arid Northeast China using SPOT VEGETATION data

A time series of SPOT-VEGETATION Normalized Difference Vegetation Index (NDVI) data with 1×1 km2 spatial resolution are used to detect the vegetation cover change in west Songnen plain, Northeast China during the period of 1998 to 2006. The MVC (Maximum Value Composites) method and difference value method were used to analyze the inter-annual changes. Principal component analysis (PCA) of the time-series NDVI imageries was performed effectively for discriminating land covers. During the last 9 years, the vegetation degradation is popular in most regions of the study area. Though there are some regions where vegetation cover is increasing, the increasing amplitude is smaller than the decreasing amplitude on the whole.

Cell-based representation and analysis of social-economic data in grid-city construction

Grid-city management currently attracts a wider audience globally. Socio-economic data is an essential part of grid-city management system. Social-economic data of an urban is characterized by discrete, time-varying, statistical, distributed and complicated. Most of data are with no exactly spatial location or from various statistical units. There is obvious gap while matching social-economic data with existing grid map of natural geographical elements emerges. It may cause many difficulties in data input, organization, processing and analysis while the grid system constructing and executing. The issue of how to allocate and integrate the huge social-economic data into each grid effectively is crucial for grid-city construction. In this paper, we discussed the characteristics of social-economic data in a grid-city systematically, thereafter a cell-based model for social-economic data representing and analyzing is presented in this paper. The kernel issues of the cell-based model establishment include cell size determining, cell capabilities developing for multi-dimension representation and evaluation, and cell dynamic simulation functions designing. The cell-based model supplements the methods system of spatial data mining, and is also promising in application to the spatialization of statistical data obtained from other researches including environmental monitoring, hydrological and meteorological observation.

Study on Urban House Information Extraction Automatically from Quick Bird Images based on Space Semantic Model

Based on the introduction to the characters and constructing flow of space semantic model, the feature space and context of house information in high resolution remote sensing image are analyzed, and the house semantic network model of Quick Bird image is also constructed. Furthermore, after region segmentation and the edge extraction to the image taking advantage of window threshold value method and Hough transformation, house information is extracted automatically from Quick Bird image through the whole space semantic model.

Texture pattern analysis of main geographical objects in QuickBird imagery

With the development of the high-resolution remote sensing image, it is important to identify and extract the image information automatically. Texture analysis has been recognized as a useful method of improving the target identification and its accuracy. In this paper we mainly discussed texture patterns analysis of main geographical objects in QuickBird image. We analyze the textures characteristic using Gray Level Co-occurrence Matrix (GLCM) and the Texture Measure of Gray Level Co-occurrence Matrix (TMGLCM). The texture pattern analysis takes TMGLCM as the main method. We establish a unify texture pattern use the TMGLCM parameter. The method is available after experiment.

Multilevel spatial semantic model for urban house information extraction automatically from QuickBird imagery

Based on the introduction to the characters and constructing flow of space semantic model, the feature space and context of house information in high resolution remote sensing image are analyzed, and the house semantic network model of Quick Bird image is also constructed. Furthermore, the accuracy and practicability of space semantic model are checked up through extracting house information automatically from Quick Bird image after extracting candidate semantic nodes to the image by taking advantage of grey division method, window threshold value method and Hough transformation. Sample result indicates that its type coherence, shape coherence and area coherence are 96.75%, 89.5 % and 88 % respectively. Thereinto the effect of the extraction of the houses with rectangular roof is the best and that with herringbone and the polygonal roofs is just ideal. However, the effect of the extraction of the houses with round roof is not satisfied and thus they need the further perfection to the semantic model to make them own higher applied value.

Heterogeneous data integration of vector data and imagery based on fuzzy reasoning in GIS

Integrated analysis of Heterogeneous spatial data sets is becoming an increasing focused and important issue in geographical information sciences at present. More and more interdisciplinary projects need the integrated analysis of heterogeneous spatial data sets from multi-sources with different quality. Especially with the development of remote sensing technology, how to make full use of the huge spatial data and how to integrate them with available history data and statistical data attract more and more attention. In this paper, the heterogeneous data integration of vector data and imagery is discussed, and a new method using fuzzy reasoning in GIS is put forwards to integrate the former vector land use data and present remote sensing imagery. One example experiment for Changling County in Northeast China with the above-mentioned method is described in detail. In the example, the real change information of earth surface is extracted exactly because the uncertainty imported by other factors is removed.