SPARK 2026 seeks to support knowledge exchange on innovative approaches for representing, integrating, and reasoning over spatial and spatiotemporal data, bridging symbolic methods with sub-symbolic techniques, including machine learning, graph representation learning, and graph embeddings. The workshop invites research contributions that explore methods for modeling spatial and spatiotemporal information in knowledge graphs, advanced spatial reasoning, and the adoption of standards, vocabularies, and best practices to ensure interoperable geospatial and spatiotemporal data.

Furthermore, the workshop will highlight practical applications in domains such as smart cities, environmental monitoring, mobility, crisis management, and digital twins, demonstrating how the integration of knowledge graphs and spatial intelligence can enable advanced analytics and real-world decision-making.

Submissions are welcome in the following categories:

• Full research papers (up to 12 pages)
• Short research papers (up to 6 pages)
• Vision/Position papers (up to 6 pages)

All submissions may include unlimited pages for appendices and references.

The workshop calls for novel and cross-over research contributions, addressing the growing use of geospatial data, geospatial knowledge graphs, and geospatial foundation models across a wide range of applications. Thei sincludes research in advanced spatial reasoning, knowledge management, and the development of intelligent, data-driven applications as well as aplied research that demonstrates the use of spatial intelligence and knowledge graphs in real-world scenarios such as smart city, environmental monitoring, mobility, and crisis management.

Following Open Science principles, research papers may also be submitted as data resource papers or software papers. Data resource papers should describe the background and methodology used to create the spatial data sources and demonstrate their value to the community. Similarly, software papers should explain the motivation, methodology, and provide a detailed description of the spatial intelligence aspects, clearly justifying their relevance and usefulness for the community. To support reproducibility and transparent peer review, authors are requested to provide the DOIs of the datasets and software products described in their articles.

SPARK also welcomes vision and position papers that offer perspectives on emerging research directions, novel or high-risk approaches, or new application areas that may require advances beyond the current state of the art. Vision papers are not required to present empirical results, but they should clearly articulate the motivation, significance, and open challenges within the proposed research area.

The workshop proceedings will be published in the joint ISWC 2026 workshop proceedings as a volume of CEUR-WS.org. Submissions must adhere to the CEUART Formatting Guidelines.

Submissions for review must be in PDF format. They must be self-contained and written in English. Submissions that do not follow these guidelines, or do not view or print properly, will be rejected without review. Please also note that adherence to the CEUR-WS Policy on AI-Assisting Tools is required.

SPARK will adopt a single-anonymous review process, and each paper will be reviewed by at least three Program Committee members.