<p><strong>Abstract.</strong> The demand for timely information about earth’s surface such as land cover and land use (LC/LU), is consistently increasing. Machine learning method shows its advantage on collecting such information from remotely sensed images while requiring sufficient training sample. For satellite remote sensing image, however, sample datasets covering large scope are still limited. Most existing sample datasets for satellite remote sensing image built based on a few frames of image located on a local area. For large scope (national level) view, choosing a sufficient unbiased sampling method is crucial for constructing balanced training sample dataset. Dependable spatial sample locations considering spatial heterogeneity of land cover are needed for choosing sample images. This paper introduces an ongoing work on establishing a national scope sample dataset for high spatial-resolution satellite remote sensing image processing. Sample sites been chosen sufficiently using spatial sampling method, and divided sample patches been grouped using clustering method for further uses. The neural network model for road detection trained our dataset subset shows an increased performance on both completeness and accuracy, comparing to two widely used public dataset.</p>

Abstract. The research and compilation of new century version of the National Huge Atlas of the People's Republic of China is the special basic work project by Ministry of Science and Technology of the People's Republic of China from June 2013 to May 2018. The National Fundamental Geographic Atlas is one of the important achievements, which represents the spatial distribution of basic geographic elements such as water system, landform, residential area, transportation, boundary, soil and vegetation in detail by relative balance. In order to meet the requirements of the construction of ecological civilization and the development of new urbanization, the set of surface coverage maps and the set of urban maps are added, and the new structure model of the National Fundamental Geographic Atlas is constructed. The Atlas is in 4-forma size, it is made up of five parts: group of sequence maps, group of topography and terrain maps, group of surface coverage maps, group of city maps and index of place names. This paper mainly discusses and studies the theory of compilation and research and content planning, the principle of topic selection and taking account of factors, structure design and map arrangement of Atlas.

The research and compilation of new century version of the National Huge Atlas of the People's Republic of China is the special basic work project by Ministry of Science and Technology of the People's Republic of China. Among them, the research and compilation of the National Geomatics Atlas of the People's Republic of China is its main content. The National Geomatics Atlas of China consists of 4 groups of maps and place name index. The 4 groups of maps are separately nationwide thematic map group, provincial fundamental geographical map group, landcover map group and city map group. The city map group is an important component part of the National Geomatics Atlas of China and mainly shows the process of urbanization in China. This paper, aim at design and compilation of 39 city-wide maps, briefly introduces mapping area research and scale design, mapping technical route, content selection and cartographic generalization, symbol design and visualization of map, etc.