With the development of earth observation technologies, the acquired remote sensing images are increasing dramatically, and a new era of big data in remote sensing is coming. How to effectively mine these massive volumes of remote sensing data are new challenges. Deep learning provides a new approach for analyzing these remote sensing data. As one of the deep learning models, convolutional neural networks (CNNs) can directly extract features from massive amounts of imagery data and is good at exploiting semantic features of imagery data. CNNs have achieved remarkable success in computer vision. In recent years, quite a few researchers have studied remote sensing image classification using CNNs, and CNNs can be applied to realize rapid, economical and accurate analysis and feature extraction from remote sensing data. This paper aims to provide a survey of the current state-of-the-art application of CNN-based deep learning in remote sensing image classification. We first briefly introduce the principles and characteristics of CNNs. We then survey developments and structural improvements on CNN models that make CNNs more suitable for remote sensing image classification, available datasets for remote sensing image classification, and data augmentation techniques. Then, three typical CNN application cases in remote sensing image classification: scene classification, object detection and object segmentation are presented. We also discuss the problems and challenges of CNN-based remote sensing image classification, and propose corresponding measures and suggestions. We hope that the survey can facilitate the advancement of remote sensing image classification research and help remote-sensing scientists to tackle classification tasks with the state-of-art deep learning algorithms and techniques.

Effective integration and wide sharing of geospatial data is an important and basic premise to facilitate the research and applications of geographic information science. However, the semantic heterogeneity of geospatial data is a major problem that significantly hinders geospatial data integration and sharing. Ontologies are regarded as a promising way to solve semantic problems by providing a formalized representation of geographic entities and relationships between them in a manner understandable to machines. Thus, many efforts have been made to explore ontology-based geospatial data integration and sharing. However, there is a lack of a specialized ontology that would provide a unified description for geospatial data. In this paper, with a focus on the characteristics of geospatial data, we propose a unified framework for geospatial data ontology, denoted GeoDataOnt, to establish a semantic foundation for geospatial data integration and sharing. First, we provide a characteristics hierarchy of geospatial data. Next, we analyze the semantic problems for each characteristic of geospatial data. Subsequently, we propose the general framework of GeoDataOnt, targeting these problems according to the characteristics of geospatial data. GeoDataOnt is then divided into multiple modules, and we show a detailed design and implementation for each module. Key limitations and challenges of GeoDataOnt are identified, and broad applications of GeoDataOnt are discussed.

Historical maps contain rich geographic information about the past of a region. They are sometimes the only source of information before the availability of digital maps. Despite their valuable content, it is often challenging to access and use the information in historical maps, due to their forms of paper-based maps or scanned images. It is even more time-consuming and labor-intensive to conduct an analysis that requires a synthesis of the information from multiple historical maps. To facilitate the use of the geographic information contained in historical maps, one way is to build a geographic knowledge graph (GKG) from them. This paper proposes a general workflow for completing one important step of building such a GKG, namely aligning the same geographic entities from different maps. We present this workflow and the related methods for implementation, and systematically evaluate their performances using two different datasets of historical maps. The evaluation results show that machine learning and deep learning models for matching place names are sensitive to the thresholds learned from the training data, and a combination of measures based on string similarity, spatial distance, and approximate topological relation achieves the best performance with an average F-score of 0.89.

Geographic knowledge bases (GKBs) with multiple sources and forms are of obvious heterogeneity, which hinders the integration of geographic knowledge. Entity alignment provides an effective way to find correspondences of entities by measuring the multidimensional similarity between entities from different GKBs, thereby overcoming the semantic gap. Thus, many efforts have been made in this field. This paper initially proposes basic definitions and a general framework for the entity alignment of GKBs. Specifically, the state-of-the-art of algorithms of entity alignment of GKBs is reviewed from the three aspects of similarity metrics, similarity combination, and alignment judgement; the evaluation procedure of alignment results is also summarized. On this basis, eight challenges for future studies are identified. There is a lack of methods to assess the qualities of GKBs. The alignment process should be improved by determining the best composition of heterogeneous features, optimizing alignment algorithms, and incorporating background knowledge. Furthermore, a unified infrastructure, techniques for aligning large-scale GKBs, and deep learning-based alignment techniques should be developed. Meanwhile, the generation of benchmark datasets for the entity alignment of GKBs and the applications of this field need to be investigated. The progress of this field will be accelerated by addressing these challenges.

Linked Data is known as one of the best solutions for multisource and heterogeneous web data integration and discovery in this era of Big Data. However, data interlinking, which is the most valuable contribution of Linked Data, remains incomplete and inaccurate. This study proposes a multidimensional and quantitative interlinking approach for Linked Data in the geospatial domain. According to the characteristics and roles of geospatial data in data discovery, eight elementary data characteristics are adopted as data interlinking types. These elementary characteristics are further combined to form compound and overall data interlinking types. Each data interlinking type possesses one specific predicate to indicate the actual relationship of Linked Data and uses data similarity to represent the correlation degree quantitatively. Therefore, geospatial data interlinking can be expressed by a directed edge associated with a relation predicate and a similarity value. The approach transforms existing simple and qualitative geospatial data interlinking into complete and quantitative interlinking and promotes the establishment of high-quality and trusted Linked Geospatial Data. The approach is applied to build data intra-links in the Chinese National Earth System Scientific Data Sharing Network (NSTI-GEO) and data -links in NSTI-GEO with the Chinese Meteorological Data Network and National Population and Health Scientific Data Sharing Platform.