Geographic entity representation learning (GERL) is an emerging method that represents natural, administrative divisions, road networks, and points of interest (POIs) in a low-dimensional continuous vector space. GERL provides a fundamental approach for geographic entities to underpin a variety of intelligent applications by learning their representation vectors to capture the semantics and interactions of the entities. Previous GERL methods mainly focus on the representation learning of the geographic entities that are seen at the time of training, which struggle to accurately generate representation vectors for the growing number of unseen geographic entities that were not involved in model training. To address this issue, this article proposes spatial meta-learning-based representation learning (SMRL), which integrates spatial subgraphs and meta-learning to improve the representation vectors of unseen geographic entities. Specifically, SMRL first designs a spatial-aware subgraph sampling module based on attributes and relationships of geographic entities to divide entities into spatial subgraphs. It develops a local-level representation module to learn entity features at the subgraph level. Finally, SMRL proposes a meta-learning-driven representation strategy that integrates meta-learning to learn the representation of unseen geographic entities. Extensive experiments show that the proposed SMRL method outperforms baselines with both higher accuracy and higher computational efficiency. This study provides new explorations for the representation of unseen geographic entities and offers methodological References for the various geographic applications.

Text geolocation prediction aims to infer the geographic location of text with text semantics, serving as a fundamental task for various geographic applications. As the mainstream approach, the deep learning-based methods follow the supervised learning paradigms, which rely heavily on a large amount of labeled samples to train model parameters. To address this limitation, this paper presents a method for text geolocation prediction without labeled samples, namely GeoSG (Geographic Self-Supervised Geolocation) model, which leverages self-supervised learning to improve text geolocation prediction in situations where labeled samples are unavailable. Specifically, GeoSG integrates spatial distance and hierarchical constraints to characterize the interactions of POIs and text in a geographic relationship graph. And it designs two self-supervised tasks to train a shared network to learn the relationships among POIs and texts. Finally, the text geolocations are inferred based on the trained shared network. Experimental results on two datasets show that the proposed method outperforms the state-of-the-art baselines and is robust. This study provides a methodological reference for geolocating various text documents and offers a solution for numerous geographic intelligence tasks that lack labeled samples.

Generating the description of a trajectory is called trajectory captioning. Previous trajectory captioning methods are derived from rule-based templates or deep-learning models. The former suffers from limited flexibility and low-quality description text, and the latter involves training or fine-tuning models with large-scale annotated trajectory-text pairs that are difficult and costly to obtain in real-world scenarios. To address these issues, this paper proposes a pseudo-label guided trajectory captioning model. The model first designs a pseudo-label generation module to automatically construct multi-view textual pseudo-labels from raw trajectory data, aiming to alleviates the problem of insufficient labeled samples. In addition, it introduces a cross-modal trajectory representation module that learns the semantic mapping between the trajectory modality and the text modality, facilitating modality alignment within a unified representation space. Finally, the trajectory description generation module integrates LLM with supervised fine-tuning and multi-source semantic fusion to generate better trajectory descriptions. Extensive experiments demonstrate that the proposed method outperforms baseline methods in both description quality and semantic expressiveness. This study provides a new technical paradigm for trajectory captioning under weakly supervised setting, and offers insights for semantic modeling and cross-modal understanding of spatiotemporal data.