Automated geospatial code generation is increasingly essential for complex spatial analysis and interdisciplinary GIS applications. However, existing large language models (LLMs) often fail to meet demands for interpretation, syntax adaptation, path retrieval, and validation, frequently producing ‘code hallucinations’—unreadable or non-functional code. To address this, we propose GeoCogent, the first intelligent framework for geospatial code generation powered by LLMs. GeoCogent integrates planning, tool-augmented reasoning, and memory mechanisms to support demand interpretation, dynamic knowledge retrieval, and consistent context maintenance, tackling core challenges in geospatial coding. We also developed and open-sourced GeoCodes, a benchmark dataset with evaluation metrics, and conducted comparative experiments, ablation studies, and case demonstrations. Results show GeoCogent achieves high efficiency across explicit, incomplete, and open-ended requirements, with each mechanism contributing significantly. Moreover, the prototype system supports local deployment and LLM integration, offering a low-barrier, efficient tool for geospatial development. By lowering technical thresholds and improving code reliability, GeoCogent advances intelligent geospatial analysis and enables interdisciplinary users to address complex analytical challenges.

With floods being among the most frequent disasters of the 21st century, timely prediction of flood risks is crucial for early alerts to governments and residents, thereby reducing potential losses. Owing to the uneven spatiotemporal distribution of disaster data and limited sharing, assessing risks in blind spots without monitoring is challenging. In this paper, we propose a flood risk prediction method that integrates spatial neighbors on the basis of geographic similarity. Considering the correlation between surrounding environments and flood occurrence, this method introduces high-order neighborhoods to model internal and external environments of spatial units. Given the sparse spatiotemporal coverage of monitoring data, we used a semi-supervised approach and graph attention to aggregate many unlabeled spatial units to achieve comprehensive representations of these environments. Subsequently, we constructed a semantic space association graph and established local and global features. Through multistage label propagation, we accounted for changes in spatial unit attributes when predicting flood risks. Applied to the “7.20” Zhengzhou extreme rainstorm event, this approach achieved a micro ROC-AUC of 0.7374 for spatial risk prediction and an accuracy of 0.7888 for temporal risk prediction, proving its effectiveness in identifying risks in data-sparse regions and addressing gaps in flood monitoring.

The widespread use of online geoinformation platforms, such as Google Earth Engine (GEE), has produced numerous scripts. Extracting domain knowledge from these crowdsourced scripts supports understanding of geoprocessing workflows. Small Language Models (SLMs) are effective for semantic embedding but struggle with complex code; Large Language Models (LLMs) can summarize scripts, yet lack consistent geoscience terminology to express knowledge. In this paper, we propose Geo-CLASS, a knowledge extraction framework for geospatial analysis scripts that coordinates large and small language models. Specifically, we designed domain-specific schemas and a schema-aware prompt strategy to guide LLMs to generate and associate entity descriptions, and employed SLMs to standardize the outputs by mapping these descriptions to a constructed geoscience knowledge base. Experiments on 237 GEE scripts, selected from 295,943 scripts in total, demonstrated that our framework outperformed LLM baselines, including Llama-3, GPT-3.5 and GPT-4o. In comparison, the proposed framework improved accuracy in recognizing entities and relations by up to 31.9% and 12.0%, respectively. Ablation studies and performance analysis further confirmed the effectiveness of key components and the robustness of the framework. Geo-CLASS has the potential to enable the construction of geoprocessing modeling knowledge graphs, facilitate domain-specific reasoning and advance script generation via Retrieval-Augmented Generation (RAG).

The rapid advancement of urbanization in recent decades has attracted extensive application of cellular automata (CA)-based models to simulate urban growth for planning and decision-making. However, the inaccurate representation of heterogeneous spatial interactions between urban units and the neglect of autocorrelated growth patterns in urbanization lead to unreliable simulation results of CA-based models. To address these two limitations, this study proposes a novel CA-based model integrated with Transformer network and Local Moran’s I, namely TL-CA. The Transformer network is built to quantify heterogeneous interaction between neighbors using the self-attention mechanism. Subsequently, Local Moran’s I is employed to implicitly guide the network in learning spatially autocorrelated patterns of urban growth through auxiliary learning. Finally, the development potential estimated from driving factors, i.e. the network output, is incorporated into CA to simulate urban growth. Land use data from Wuhan (2000–2020) are selected to verify TL-CA’s performance. The results demonstrate that TL-CA achieves the highest simulation accuracy, with an average increase in the figure of merit (FoM) of 9.97%. Attention visualization and residual analysis explain the model’s effectiveness in modeling heterogeneous interactions and autocorrelated growth. Additionally, TL-CA exhibits high computational efficiency and low resource consumption, with sufficient potential to support larger-scale research.

Effective retrieval is essential for finding resources in demand handily amidst extensive data records in data warehouse. Mainstream map retrieval methods suffer from intention gap problem and are incapable to describe sophisticated user demands precisely due to the limits of low- and middle-level text or visual feature matching, resulting in unsatisfactory retrieval results. Such limitations are more marked when map retrieval demands were characterized with joint constraints of geographic concepts. To address this issue, we propose a map retrieval intention recognition method to perceive user demands with relevance feedback samples and geographic semantics guidance. Specifically, we construct a hierarchical intention expression model to describe retrieval goals and their multi-dimensional attribute constrains; incorporate geographic ontologies to provide semantic guidance and facilitate recognition; utilize the frequent itemset mining (FIM) algorithm Apriori to generate intention candidates from relevance feedback samples, and search for the optimal intention set by adopting the minimum description length (MDL) principle. The experiments verify the effectiveness of Apriori algorithm and MDL principle on intention recognition. The proposed method outperforms the FIM algorithm Gene Ontology (RuleGO) and the Decision Tree algorithm with Hierarchical Features (DTHF) with higher recognition accuracy and noise tolerance. Furthermore, through our sample augmentation strategy, the method yields promising recognition accuracy even when the feedback sample size is as low as ten, substantially reducing the feedback burden in human-computer interactions. We envision that the application of our method in spatial data infrastructures (SDIs), such as geoportals and catalogue services, could enhance the quality of service and user experience in geospatial data discovery.

Kernel Density Estimation (KDE) is a classic algorithm for analyzing the spatial distribution of point data, and widely applied in spatial humanities analysis. A heat-map permits intuitive visualization of spatial point patterns estimated by KDE without any overlapping. To achieve a suitable heat-map, KDE bandwidth parameter selection is critical. However, most generally applicable bandwidth selectors of KDE with relatively high accuracy encounter intensive computation issues that impede or limit the applications of KDE in big data era. To solve the complex computation problems, as well as make the bandwidths adaptively suitable for spatially heterogenous distributions, we propose a new Quad-tree-based Fast and Adaptive KDE (QFA-KDE) algorithm for heat-map generation. QFA-KDE captures the aggregation patterns of input point data through a quad-tree-based spatial segmentation function. Different bandwidths are adaptively calculated for locations in different grids calculated by the segmentation function; and density is estimated using the calculated adaptive bandwidths. In experiments, through comparisons with three mostly used KDE methods, we quantitatively evaluate the performance of the proposed method in terms of correctness, computation efficiency and visual effects. Experimental results demonstrate the power of the proposed method in computation efficiency and heat-map visual effects while guaranteeing a relatively high accuracy.

Group-user intensive access to WebGIS exhibits spatiotemporal behaviour patterns with aggregation features and regularity distributions when geospatial data are accessed repeatedly over time and aggregated in certain spatial areas. We argue that these observable group-user access patterns provide a foundation for improved optimization of WebGIS so that it can respond to volume intensive requests with a higher quality of service and improve performance. Subsequently, a measure of access popularity distribution must precisely reflect the access aggregation and regularity features found in group-user intensive access. In our research, we considered both the temporal distribution characteristics and spatial correlation in the access popularity of tiled geospatial data (tiles). Based on the observation that group-user access follows a Zipf-like law, we built a tile-access popularity distribution based on time-sequence, to express the access aggregation of group-users with heavy-tailed characteristics. Considering the spatial locality of user-browsed tiles, we built a quantitative expression for the correlation between tile-access popularities and the distances to hotspot tiles, reflecting the attenuation of tile-access popularity to distance. Moreover, given the geographical spatial dependency and scale attribute of tiles, and the time-sequence of tile-access popularity, we built a Poisson regression model to express the degree of correlation among the accesses to adjacent tiles at different scales, reflecting the spatiotemporal correlation in tile access patterns. Experiments verify the accuracy of our Poisson regression model, which we then applied to a cluster-based cache-prefetching scenario. The results show that our model successfully reflects the spatiotemporal aggregation features of group-user intensive access and group-user behaviour patterns in WebGIS. The refined mathematical method in our model represents a time-sequence distribution of intensive access to tiles and the spatial aggregation and correlation in access to tiles at different scales, quantitatively expressing group-user spatiotemporal behaviour patterns with aggregation features and a regular distribution. Our proposed model provides a precise and empirical basis for performance-optimization strategies in WebGIS services, such as planning computing resource allocation and utilization, distributed storage of geospatial data, and providing distributed services so as to respond rapidly to geospatial data requests, thus addressing the challenges of volume-intensive user access.

Issues of accuracy, uncertainty, and spatial data quality have been on the top of most GIScience research agendas around the world from the late 1980s. Ever since then, growing research efforts have been directed toward uncertainty characterization in spatial information, analysis, and applications, aiming for better understanding of spatial uncertainty and thus improved methods and techniques for assessing and managing data quality. Impressive progress has been made in various issues concerning data quality. In addition, growing research on extensions to the conventional norms of data quality, such as the quality aspects of geospatial information services, has been observed. Chinese researchers have contributed to this great cause by keeping abreast with the developments abroad and striving for their own innovative work. This paper reviews the past research on data quality-related issues and provides a perspective on future developments. These will be seen not only in continued research on theoretical and technical issues concerning data quality, but also in developments of tools for quality assessment and decision-making under uncertainty through geospatial information processing and applications.

OGC Web Services (OWS) are essential building blocks for the national and global spatial data infrastructure (NSDI and GSDI) and the geospatial cyberinfrastructure (GCI). Web Map Service (WMS), Web Feature Service (WFS), Web Coverage Service (WCS), and Catalogue Service for Web (CSW) have been increasingly adopted to serve scientific data. Interoperable services can facilitate the integration of different scientific applications by searching, finding, and utilizing the large number of scientific data and Web services. However, these services are widely dispersed and hard to be found and utilized with acceptable performance. This is especially true when developing a science application to seamlessly integrate multiple geographically dispersed services. Focusing on the integration of distributed OWS resources, we propose a layer-based service-oriented integration framework and relevant optimization technologies to search and utilize relevant resources. Specifically, (1) an AJAX (Asynchronous JAvaScript and eXtensible Markup Language)-based synchronous multi-catalogue search is proposed and utilized to enhance the multi-catalogue searching performance; (2) a layer-based search engine with spatial, temporal, and performance criteria is proposed and used for identifying better services; (3) a service capabilities clearinghouse (SCCH) is proposed and developed to address the service issues identified by a statistical experiment. A science application of data correlation analysis is used as an example to demonstrate the performance enhancement of the proposed framework.