Search

Debris flow susceptibility evaluation plays a crucial role in the prevention and control of debris flow disasters. Therefore, this paper proposes a convolutional neural network model named multi-level feature extraction network (MFENet). First, a dual-channel CNN architecture incorporating the Embedding Channel Attention mechanism is used to extract shallow features from both digital elevation model images and multispectral images. Subsequently, channel shuffle and feature concatenation are applied to the features from the two channels to obtain fused feature sets. Following this, a deep feature extraction is performed on the fused feature sets using a residual module improved by maximum pooling. Finally, the susceptibility index of gullies to debris flows is calculated based on the similarity scores. Experimental results demonstrate that the model exhibits favorable classification performance, with an accuracy of 73.45%. Furthermore, the percentage of debris flow valleys in high and very high susceptibility zones reaches 93.97%. [ABSTRACT FROM AUTHOR]

The primary prerequisite for sustainable urban development is to accurately grasp the development of the city. The dynamic changes in the urban area can reflect the urban expansion process and spatial development model. Carrying out urban expansion monitoring and extracting urban areas is of great importance for grasping the law of urban development and promoting the sustainable development of cities. However, the related research reveals several problems such as insufficient accuracy and low intelligence of urban boundary extraction. In response to these problems, this paper proposes a new method for urban area extraction based on the progressive learning model. By combining prior knowledge and image features, the number of training samples required for machine learning is reduced, and the problem of using high-level semantic information expression in the process of urban areas is avoided by using the classification method, and thus the accuracy of urban area extraction is improved. The method uses urban road network data to divide the city into blocks. It applies the scene classification method to extract the urban areas and uses the pyramid layer-by-layer to carry out the space constraint method to integrate the urban extraction principle into the machine learning process, which can be obtained and kept artificial under a small sample condition. Extracting the effect of the urban area is very close, greatly reducing the workload and providing a new solution for high-precision automatic extraction of urban areas. Through the analysis of urban expansion, the following results were obtained: (1) from 2000 to 2015, China's provincial capital cities maintained a high-speed growth trend with a total area increased by 90%; (2) urban expansion showed significant regional differences. The eastern expansion rate gradually slowed down, the western and northeast regions accelerated their expansion, and the central region expanded steadily; (3) 61% of the provincial capital cities expanded exponentially; (4) the development of China's provincial capital cities was highly correlated with national urban development policies and regional development strategies. [ABSTRACT FROM AUTHOR]

Information on the county level population distribution is essential for supporting a wide variety of local planning processes. Previous researchers found that impervious surfaces had a strong linear relationship with population. But few studies have reported estimating population in a county area of China with impervious surfaces. In this paper, a population distribution model for a county area in China was established using demographic information at the county level (i.e., total population, non-agricultural population, and agricultural population) and impervious surfaces derived from Landsat TM images. The model was conducted to distribute the population of Fujin County, Heilongjiang Province, China. Population data of 123 villages and 11 towns of Fujin County were used to evaluate the model. The results indicated that the model performs better than area-based approaches, particularly in the estimation of town populations (17.86 percent mean relative error). The results of village population estimation were acceptable, with a mean relative error of 25.3 percent. As a result, impervious surfaces cannot provide height information and identify non-residential areas in developed areas of zhens (urban cores of towns). The model suggests the difficulty of non-agricultural population estimation. [ABSTRACT FROM AUTHOR]

In this paper the distribution of 3-second elevation error in the data from the Shuttle Radar Topography Mission (SRTM) over the whole of China and its associations with topographic and land cover factors were systematically evaluated. The landscape features extracted from different datasets at more than 500,000 sites were used to determine the variation pattern in the errors by the method of single factor analysis. The results showed that the topographic attributes derived from SRTM data could adequately represent the terrain of China. However, there were extended and observable areas with abnormalities in a small proportion of the data. Slope was the dominant factor affecting elevation error compared with other landscape features (aspect, vegetation, etc.). The mean errors in glaciers, deserts and wetlands were -1.05 m, -2.03 m and -2.43 m, and 1.05 m in built-up areas. In general the elevation errors in the SRTM data formed a complex pattern of variation across China. [ABSTRACT FROM AUTHOR]

Urban villages (UVs) are a typical informal settlement in China resulting from the rapid urbanization in recent decades. Their formation and demolition are attracting increasing interest. In the remote sensing community, UVs have been detected based on hand-crafted features. However, the hand-crafted features just consider one or several characteristics of UVs, and ignore many effective cues hiding in the image. Recently, deep learning has been used to automatically learn suitable feature representations from a huge amount of data, without much expertise or effort in designing features. Motivated by its great success, this paper aims to use deep learning for detecting UVs. Because of the scarce labeled samples, this paper presents a novel unsupervised deep learning method to learn a data-driven feature. Experiments show the data-driven feature obtained with the proposed method outperform the existing unsupervised deep neural networks, and achieve results comparable to that obtained using the best hand-crafted features. [ABSTRACT FROM AUTHOR]

As an important indicator of cropping intensity, Cropping Index (CI) is defined as the number of peaks in the Vegetation Index (VI) time-series curve in a year. The existing CI mapping algorithms (e.g., the cross-fitting and the second order difference algorithm) are vulnerable to noise contained in the VI time series and need a priori knowledge and some extra constraints which could not be directly derived from the VI time-series data. In this paper, a shape-matching method is developed which can map CI directly from the preprocessed VI time-series data without the de-noising processes. This shape-matching method utilizes a decision-making process to find out the true peaks in the VI time-series curve based on a rank order mathematical morphology algorithm. The processing procedure involves five steps: (a) determination of the temporal moving window size, (b) detection of local maximum/minimum points, (c) exclusion of false maximum/minimum points, (d) determination of the threshold for the minimum growth amplitude, and (e) mapping of CI. This shape-matching method only needs two input parameters, the temporal moving window size and the threshold for the minimum growth amplitude, which can be both directly derived from the VI time-series data with some selected test pixels. Moreover, the response of the shape-matching method is relatively insensitive to the exact values of its design parameters, making it more flexible and effective in adapting to other regions. This new method is applied to map the CIS in Jiangsu Province, China, in 2010, based on the Enhanced Vegetation Index (EVI) time-series data derived from the Moderate Resolution Imaging Spectroradiometer (MODIS) product. The overall CI mapping accuracy for the shape-matching method is 80 percent, which is much higher than the CI mapping accuracy of 60 percent for the second order difference algorithm. This shape-matching method can be further applied to other regions with a grid-search for its optimal parameters using some test pixels. [ABSTRACT FROM AUTHOR]

This paper proposes a technique to extract urban built-up land features from Landsat Thematic Mapper (TM) and Enhanced Thematic Mapper Plus (ETM+) imagery taking two cities in southeastern China as examples. The study selected three indices, Normalized Difference Built-up Index (NDBI), Modified Normalized Difference Water Index (MNDWI), and Soil Adjusted Vegetation Index (SAVI) to represent three major urban land-use classes, built-up land, open water body, and vegetation, respectively. Consequently, the seven bands of an original Landsat image were reduced into three thematic-oriented bands derived from above indices. The three new bands were then combined to compose a new image. This considerably reduced data correlation and redundancy between original multispectral bands, and thus significantly avoided the spectral confusion of the above three land-use classes. As a result, the spectral signatures of the three urban land-use classes are more distinguishable in the new composite image than in the original seven-band image as the spectral clusters of the classes are well separated. Through a supervised classification, a principal components analysis, or a logic calculation on the new image, the urban built-up lands were finally extracted with overall accuracy ranging from 91.5 to 98.5 percent. Therefore, the technique is effective and reliable. In addition, the advantages of SAVI over NDVI and MNDWI over NDWI in the urban study are also discussed in this paper. [ABSTRACT FROM AUTHOR]

In this paper, we evaluate the impacts of land-use/cover changes (LUCC) on sediment loads at the outlets office sub-watersheds of the Poyang Lake watershed by integrating remote sensing and GIS with statistical analysis. The intensively formed watershed is characterized by a mountainous and hilly topography and a rainy climate. The primary goal of this paper is to help a better understanding of land-use/cover change and its driving forces. We discuss spatio-temporal variations in rainfall and sediment loads and identify factors contributing to those variations, analyze the comprehensive impacts of land-use/cover change on changing climate and human activities, and conclude that the changing rates of forest cover and climate regimes are primary factors for sediment discharges in the Poyang Lake watershed. Our results suggest that the eco-system still have large capacities to support human activities in the area. [ABSTRACT FROM AUTHOR]

Distributed virtual environments (DVEs) are environments that are not only used for managing and delivering multi-source, multi-dimensional, geographical information, but also enable geographically distributed users to navigate in a 3D space, and to interact with objects and with other online users. In this paper, we design DVEs to disseminate 2D and 3D data and to implement public participation in the management of the country parks in Hang Kong. The system framework, geo-data model, and user's interface are discussed for designing DVEs. Based on the virtual reality modeling language (VRML), Java, and VRML External Authoring Interface (EAI) classes, a balanced client/server architecture is employed. In view of multi-source and multi-dimensional data, the object-oriented approach is utilized to design 3D geo-object models for webbased distribution. Considering the Internet bandwidth and performance of client computers, we adopt multi-block and multi-level approaches to the design of 3D geo-objects. The user's interface provides capabilities for implementing 2D and 3D view, data query and analysis, object addition/removal, and 3D avatar-based and text-based communication. This paper presents a case study of the Shing Mun Country Park in Hong Kong, where a prototype DVE, called "VirtualPark," was developed. [ABSTRACT FROM AUTHOR]

The development of predictive models of the spatial distribution of schistosomiasis are hampered by the existence of different regional subspecies of the Oncomelania hupensis snail that serve as intermediate hosts for the disease in China. The habitats associated with these different subspecies vary considerably, with mountainous habitats in the west and floodplain habitats in the east. Despite these challenges, con tin uing environmental change resulting from the construction of the Three Gorges Dam and global warming that threaten to increase snail habitat, as well as limited public health resources, require the ability to accurately map and prioritize areas at risk for schistosomiasis. This paper describes a series of ongoing studies that rely on remotely sensed data to predict schistosomiasis risk in two regions of China. The first study is a classification of Landsat TM image~yto identify snail habitats in mountainous regions of Sichuan Province. The accuracy of this classification was assessed in an independent field study, which revealed that seasonal flooding may have contributed to misclassification, and that the incorporation of soil maps may greatly improve classification accuracy A second study presents the use of Landsat TM and water level data to understand seasonal differences in Oncomelania hupensis habitat in the lower Yangtze River region. [ABSTRACT FROM AUTHOR]

The social-economic statistics collected from local governments are the main access for the central government to achieve national economic circumstance, especially for China. However, the statistics of almost 10% of national counties are missing or inconsistent due to the statistical caliber change in the wave of urbanization during economic development. Some researchers proposed to apply a night luminosity product to solve such issue. However, it lacks the ability to distinguish between the wealthy populations with a dense distribution and the less developed places. In this paper, the publicly available daytime Landsat images are used to estimate economic statistics. An end-to-end multitask deep learning framework is constructed to estimate the county-level economy of Mainland China and the overall accuracy of this model achieves higher than 85%. The experiments show that our model provides a potential strategy to make up for the missing statistics and examines the reliability of the statistics collected for the central government. [ABSTRACT FROM AUTHOR]

Wall painting plays an important role in the culture relics of the Mogao Caves in Dunhuang, P.R. China. A novel approach of generating a high-resolution orthoimage of the wall painting is proposed. Since the photographic object is nearly flat and also the forward overlap between adjacent images is smaller than 60 percent, the main difficulty to be resolved is the high correlation problem among the unknowns. Improved models of relative orientation and bundle adjustment with virtual constraints have been developed to resolve the high correlation problem. A Voronoi diagram of projective footprints is applied to automatically determine the mosaic lines of ortho-rectified images. The color quality of the generated orthoimage is improved through global minimization of the color differences among overlapped images. The experimental results show that the proposed approach has great potential for conservation of wall paintings with sub-millimeter to millimeter precision. [ABSTRACT FROM AUTHOR]

The fast urban expansion has led to replacement of natural vegetation-dominated land surfaces by various impervious materials. This has a significant impact on the environment due to modification of heat energy balance. Timely understanding of spatiotemporal information of impervious surface has become more urgent as conventional methods for estimating impervious surface are very limited. In response to this need, this paper proposes a new index, normalized difference impervious surface index (NDISI), for estimating impervious surface. The application of the index to the Landsat ETM+ image of Fuzhou City and the ASTER image of Xiamen City in Chin? has shown that the new index can efficiently enhance and extract impervious surfaces from satellite imagery, and the normalized NDISI can represent the real percentage of impervious surface. The index was further used as an indicator to investigate the impact of impervious surface on urban heat environment by examination of its quantitative relationship with land surface temperature (LST), vegetation, and water using multivariate statistical analysis. The result reveals that impervious surface has a positive exponential relationship with LST rather than a simple linear one. This suggests that the areas with high percent impervious surface will accelerate LST rise and urban heat island development. [ABSTRACT FROM AUTHOR]

The differential INSAR technique has the potential for monitoring centimeter-scale ground motion in an accurate and cost-effective manner. Probably the most important limiting factor in the application of INSAR is temporal change in the complex refiectivity of the ground surface during the period between radar acquisitions. This can be due to changes in such parameters as moisture content or vegetation. The stable artificial corner reflectors can be identified from long temporal series of interferometric SAR images even with large baselines, and therefore decrease the risk of image decorrelation. This paper will discuss the following questions: 1) how to obtain the true phase ora corner reflector in a SAR complex image; 2) how to co-register the corner reflector pixels when the coherence of its surrounding area is extremely low; 3) how to select the interpolation kernel to resample the SAR image; and, 4) how to compute the interferometric phase of two co-registered corner reflectors without fiat earth term and corners' height contribution. In order to demonstrate the results, a practical example of landslide monitoring in the Three Gorges area in China is presented. [ABSTRACT FROM AUTHOR]

This paper applies SAR Interferometry for ground deformation in two cases: the 1998 Zhangbei-Shangyi Earthquake in Northern China and the urban subsidence in Suzhou City from 1993 to 2000. It is concluded that SAR interferometry may provide valuable information for understanding the spatial patterns and progress of natural hazards. SAR interferometry is also critical for mechanism studies and hazard mitigation. [ABSTRACT FROM AUTHOR]

Change-vector analysis (CVA) is a valuable technique for landuse/land-cover change detection. However, how to reasonably determine thresholds of change magnitude and change direction is a bottleneck to its proper application. In this paper, a new method is proposed to improve CVA. The method (the improved CVA) consists of two stages, Double-Window Flexible Pace Search (DFPS), which aims at determining the threshold of change magnitude, and direction cosines of change vectors for determining change direction (category) that combines single-date image classification with a minimum-distance categorizing technique. When the improved CVA was applied to the detection of the land-use/land-cover changes in the Haidian District, Beijing, China, Kappa coefficients of "change/ no-change" detection and "from-to" types of change detection were 0.87 and greater than 0.7, respectively, for all kinds of land-use changes. The experimental results indicate that the improved CVA has good potential in land-use/land-cover change detection. [ABSTRACT FROM AUTHOR]

As the most populated country on Earth, China has experienced a rapid growth in the GIS industry in the last decade. The development of made-in-China GIS software has been listed as the most important initiative in the Chinese information technology industry by the central government, aiming to gain a "fair share" in the potentially enormous domestic GIS market, where the adoption of international software is dominant. This paper reports the authors' observations on domestic GIS software development in China in the past years. The progress in software research and development and the special nature of Chinese GIS software are reviewed. Based on this review, an attempt is made to compare Chinese and international GIS software packages. The potential impact on the Chinese GIS software market is also discussed. [ABSTRACT FROM AUTHOR]

Geographic information systems (GISs) were introduced into China (Mainland) in the 1970s. This paper provides an overview of the advances in GISs in Mainland China (not including Taiwan, Hong Kong, and Macau) during the past more than 20 years. It covers the developments of operational application systems, national geospatial databases, and technical systems. It also reviews the advances in research, education, and institutional development. [ABSTRACT FROM AUTHOR]

Image fusion is important in the synthetic application of multisource remotelv sensed images, and image registration is the basis of image fusion. The traditional method of manual registration is a laborious, tedious, and complex task. For improving the efficiency of image fusion, automatic methods of image registration must be used. In this paper, automatic registration based on the theory and methods of image matching is presented. The main contents include extraction of single point matching, reliability strategy based on a hierarchical pyramid image structure, and global image matching. The automatic registration of multi-source remote sensing images is then discussed, the presentation being based on global image matching. Finally, the successful results of the automated registration and fusion of TM and SPOT images are presented. [ABSTRACT FROM AUTHOR]

The new generation of geographic information systems (GIS) demand the integrated management of vector, image, and DEM data. This paper brings forward a vector, image, and DEM integrated spatial data model on the basis of the objectoriented idea. It also discusses the implementation method of this integrated spatial database management system. The spatial database management system has been used in the construction of the China Spatial Data Infrastructure as the base of a GIS software package, GeoStar. It reveals that the system has high efficiency and the feasibility to manage national, provincial, and city spatial data of multiple-scales and multiple-sources. [ABSTRACT FROM AUTHOR]

Discusses the use of geographical information systems (GIS) in China from 1980 to 2002. Early development of GIS in China; Establishment of the first GIS laboratory in China at the Institute of Remote Sensing Applications of the Chinese Academy of Sciences in January 1980; Introduction to papers in the April 2002 issue of the journal 'Photogrammetric Engineering and Remote Sensing.'

The vegetation water content (VWC) quantitative is useful for monitoring vegetation physiological growth. The relationship between VWC and vegetation water indices was analyzed. The optimal estimation model was established. The results show that: (1) Absorption bands primarily fell within 380 to 400 nm, 680 to 720 nm, 1420 to 1450 nm, 1900 to 1940 nm, and 2450 to 2500 nm; (2) comparing published vegetation water indices and developed vegetation indices, it showed that DVI(1712,1382), NDSI(2201,1870) and RSI(2259,1870) had a better correlation with VWC than the published vegetation water; and (3) NDSI(2201,1870) and RSI(2259,1870) performed well in estimating vegetation water content, DVI(1712,1382) had a rough estimate of its water content. Moreover, the linear combination of DVI(1712,1382), NDSI(2201,1870) and RSI(2259,1870) improved the estimation of VWC. The best vegetation indices for estimating VWC were found to be the linear combination of DVI(1712,1382), NDSI(2201,1870) and RSI(2259,1870) in arid area of northwestern China. [ABSTRACT FROM AUTHOR]

Introduces a series of papers on the advancements in China's photogrammetry, remote sensing, geographic information systems and other geospatial techniques. Launch of the country's meteorological satellite FY-1C; Establishment of remote sensing related professional organizations and institutions; Government support for the sector.

Soil degradation by expansion-driven sealing increases at an unexpected rate globally, but the dynamics of agricultural soil sealing in peri-urban areas remain poorly understood. This study used aerial photographs to monitor patterns of built-up land expansion and subsequent agricultural soil sealing between 1994 and 2006 in peri-urban areas of Shanghai, China. Results indicated that a total of 152,706.5 ha of agricultural soils were sealed. In particular, residential land and industrial land were the major contributors. Buffer analysis demonstrated that agricultural soils with high proximity to roads and urban centers are more vulnerable to be sealed. Percentage of sealed agricultural soils of total agricultural soils had linear relationships with population growth and economic development. These results quantitatively document the impacts of urbanization on agricultural soil seating. From a management perspective, we argue that the protection of agricultural softs should be integrated with urban planning efforts in China. [ABSTRACT FROM AUTHOR]

The article provides information on CASMSAR, China's first airborne synthetic aperture radar mapping system, developed by the Chinese Academy of Surveying & Mapping in collaboration with several institutes in China. The SAR system onboard CASMSAR includes a dual-antenna X-band interferometer and a fully polarimetric SAR at P-band. The system features a SAR data acquisition system and a SAR mapping workstation.