Classification with a few labeled samples has always been a longstanding problem in the field of hyperspectral image (HSI) processing and analysis. Aiming at the small sample characteristics of HSI classification, a novel ensemble self-supervised feature-learning (ES${}^2$FL) method is proposed in this paper. The proposed method can automatically learn deep features conducive to classification without any annotation information, significantly reducing the dependence of deep-learning models on massive labeled samples. Firstly, to utilize the spatial–spectral information in HSIs more fully and effectively, EfficientNet-B0 is introduced and used as the backbone to model input samples. Then, through constraining the cross-correlation matrix of different distortions of the same sample to the identity matrix, the designed model can extract the latent features of homogeneous samples gathering together and heterogeneous samples separating from each other in a self-supervised manner. In addition, two ensemble learning strategies, feature-level and view-level ensemble, are proposed to further improve the feature-learning ability and classification performance by jointly utilizing spatial contextual information at different scales and feature information at different bands. Finally, the concatenations of the learned features and the original spectral vectors are inputted into classifiers such as random forest or support vector machine to complete label prediction. Extensive experiments on three widely used HSI data sets show that the proposed ES${}^2$FL method can learn more discriminant deep features and achieve better classification performance than existing advanced methods in the case of small samples.

Information resources have increased rapidly in the big data era. Geospatial data plays an indispensable role in spatially informed analyses, while data in different areas are relatively isolated. Therefore, it is inadequate to use relational data in handling many semantic intricacies and retrieving geospatial data. In light of this, a heterogeneous retrieval method based on knowledge graph is proposed in this paper. There are three advantages of this method: (1) the semantic knowledge of geospatial data is considered; (2) more information required by users could be obtained; (3) data retrieval speed can be improved. Firstly, implicit semantic knowledge is studied and applied to construct a knowledge graph, integrating semantics in multi-source heterogeneous geospatial data. Then, the query expansion rules and the mappings between knowledge and database are designed to construct retrieval statements and obtain related spatial entities. Finally, the effectiveness and efficiency are verified through comparative analysis and practices. The experiment indicates that the method could automatically construct database retrieval statements and retrieve more relevant data. Additionally, users could reduce the dependence on data storage mode and database Structured Query Language syntax. This paper would facilitate the sharing and outreach of geospatial knowledge for various spatial studies.

To address the issue of data integrity and reliability caused by sparse vessel trajectory data, this paper proposes a multi-step restoration method for sparse vessel trajectory based on feature correlation. First, we preserved the overall trend of the trajectory by detecting and marking the sparse and abnormal vessel trajectories points and using the cubic spline interpolation method for preliminary restoration. Then, we established a composite indicator of feature correlation for selecting highly correlated trajectory features as inputs to the model, reducing data redundancy while improving the key correlation between trajectory features. Finally, we developed a vessel trajectory restoration model based on the Seq2Seq network for secondary restoration of the trajectory to ensure the accurate restoration of the vessel trajectory. Through comparison and ablation experiments, we demonstrate that the method can efficiently extract highly correlated features from vessel trajectories and combines the advantages of the interpolation method and neural network model to effectively improve the accuracy of trajectory restoration and ensure the integrity and accuracy of trajectory data. The research results could provide crucial technical support for the subsequent mining of vessel behavior patterns and assisted decision-making, which holds significant application prospects and potential value.

Predicting user activity intensity is crucial for various applications. However, existing studies have two main problems. First, as user activity intensity is nonstationary and nonlinear, traditional methods can hardly fit the nonlinear spatio-temporal relationships that characterize user mobility. Second, user movements between different areas are valuable, but have not been utilized for the construction of spatial relationships. Therefore, we propose a deep learning model, the geographical interactions-weighted graph convolutional network-gated recurrent unit (GGCN-GRU), which is good at fitting nonlinear spatio-temporal relationships and incorporates users’ geographic interactions to construct spatial relationships in the form of graphs as the input. The model consists of a graph convolutional network (GCN) and a gated recurrent unit (GRU). The GCN, which is efficient at processing graphs, extracts spatial features. These features are then input into the GRU, which extracts their temporal features. Finally, the GRU output is passed through a fully connected layer to obtain the predictions. We validated this model using a social media check-in dataset and found that the geographical interactions graph construction method performs better than the baselines. This indicates that our model is appropriate for fitting the complex nonlinear spatio-temporal relationships that characterize user mobility and helps improve prediction accuracy when considering geographic flows.

Urban mobility structure detection and functional distribution learning are significant for urban planning and management. However, existing methods have limitations in handling complex urban data and capturing global spatial structure features. To deal with these challenges, we proposed a multi-scale feature-aware urban mobility structure embedding method based on contrastive learning. First, we designed a multi-scale contrastive learning strategy to effectively learn local human activity features and global spatial structure features, determine the community affiliation of regions, and generate regional embedding vectors. Next, we introduced a correlation matrix to encode the functional synergy and competition of Point of Interests (POIs) and construct the complex correlation between urban mobility structure and urban functional distribution to evaluate the quality of regional embedding vectors. Experiments in Haikou City show that the proposed method can accurately detect the urban mobility structure and functional distribution. The analysis reveals that the central urban area of Haikou exhibits concentrated functions and significant traffic tidal effects, while the suburban areas have relatively weaker functions, with residents displaying a high level of dependence on the central area. Therefore, urban planning needs to optimize the functional layout, improve the functions of the suburbs, and promote the balance of urban space.