This paper introduces an innovative, lightweight GitOps-based architecture for metadata management, leveraging Data-as-Code principles, Continuous Integration/Continuous Deployment (CI/CD) pipelines, and Static Site Generation (SSG), which establishes a seamless, developer-centric workflow.
Abstract
Automatic train operation (ATO) at grade of automation 3 and above (GoA3-GoA4) requires robust AI-based perception systems capable of reliably detecting obstacles and railway-specific objects under real-world conditions. The effectiveness of these modern artificial intelligence approaches depends heavily on large-scale, high-quality, and highly dynamic annotated datasets. However, managing metadata, maintaining provenance, and tracking the iterative evolution of these annotations impose significant infrastructural and regulatory requirements. Existing monolithic data catalogs often suffer from massive operational overhead, poor integration into developer workflows, and severe documentation drift. This paper introduces an innovative, lightweight GitOps-based architecture for metadata management. By leveraging Data-as-Code principles, Continuous Integration/Continuous Deployment (CI/CD) pipelines, and Static Site Generation (SSG), the proposed approach establishes a seamless, developer-centric workflow. This ensures an traceability, enforces strict regulatory compliance, and automatically generates a highly performant dataset overview.
Metadata are fundamental components of spatial data infrastructures, enabling the discovery, evaluation, and reuse of datasets. Their creation and maintenance, typically performed manually, can be costly, time-consuming, and prone to inconsistencies. This work investigates the feasibility of using Generative AI (GenAI) to assist human operators working for data producers in creating structured dataset descriptions compliant with GeoDCAT-AP standards. We address the following research question: to what extent can layered prompt engineering strategies improve the quality of metadata descriptions generated through Large Language Models (LLMs), and how do individual prompt components-role definition, content rules, template structure, and few-shot examples-interact with model selection to affect structural compliance, semantic similarity, and factual reliability? We propose a six-layer prompting framework and evaluate seven ablation strategies, each selectively disabling specific layers, using two LLMs (qwen3-32b and qwen3-coder-30b-a3b-instruct) and eight geospatial datasets. Generated descriptions are assessed using eight automated metrics spanning lexical quality, structural compliance, and semantic similarity, complemented by targeted expert evaluation of factual accuracy. Results reveal a clear hierarchy of layer impact. The input template, used as the reference structure of the description, is the most influential component, driving both structural compliance and readability. Few-shot examples are the second most impactful layer, substantially reducing redundancy and improving semantic alignment. Content rules do not measurably improve surface-level output quality, but serve as critical safeguards, encouraging models to flag missing information rather than fabricate content. Expert role definition contributes the least measurable effect. Both LLMs produce semantically comparable outputs under full guidance but diverge without structural constraints. We recommend the full prompting configuration for production use and provide practical guidelines for balancing prompt complexity, output quality, and factual reliability in LLM-assisted metadata generation workflows.
M. Di Leo, Ilyas Tiouassiouine-Maes, Jordi Escriu et al.· Open Research Europe· 0 citations
The refurbishment and energy-efficient renovation of existing buildings, specifically those before 1945, with complex architectural building elements, require a level of building information that is often unavailable, incomplete or imprecise. As they represent a large percentage of current building stock (up to 25% of all buildings), it is crucial to address such an issue, as such buildings are ideal targets for renovation and energy retrofitting projects. This paper presents a conceptual pipeline, developed through the NERF2BIM research project, focusing on an Artificial Intelligence (AI)-supported holistic pipeline for the creation of as-is Building Information Modeling (BIM) models of existing buildings, expanding upon existing methodologies with the embedding of knowledge-driven semi-automatic detailing-on-demand task. The proposed pipeline integrates uncertainty-aware spatial capture, semantic interpretation and reconstruction, and knowledge-based reasoning within a BIM-oriented workflow. The paper provides an overview of current advancements in the respective aspects of the pipeline, highlighting current gaps. The proposed conceptual pipeline aims at addressing these issues through novel applications of AI and knowledge-driven solutions. Key contributions include: (1) a conceptual approach in addressing the imprecision of more sustainable data gathering approaches; (2) a context-aware BIM reconstruction process, providing multiple data output types; and (3) a formalization of architectural and construction knowledge and its utilization in a detailing-on-demand approach of the reconstructed BIM models. Through the integration of uncertainty-aware data gathering, context-aware reconstructions and domain expertise into existing reconstruction pipelines, the proposed pipeline bridges the data gap for existing buildings, enabling more efficient and knowledge-driven renovation processes.
Ivan Bratoev, Omar Faig Orujlu, Ziyang Xu et al.· Buildings· 0 citations
This review paper argues that Vision-Language Models (VLMs), a paradigm whose rapid maturation is evidenced by recent comprehensive surveys offer a transformative solution for rail asset management, and provides a focused overview of the limitations of current CV systems.
Ashley Varghese, Mohammadjavad Ghorbanalivaki, Gunho Sohn· The International Archives o...· 0 citations
SysName, a production-oriented pipeline that automates device configuration end-to-end for Modbus RTU, OPC-UA, Profibus DP, and CANopen, builds a hybrid dense-sparse retrieval index augmented by an ontology graph derived from ECLASS, AAS, and SOSA/SSN, using a BGE-M3 encoder with a cross-encoder reranker to surface relevant manual passages.
A. Ganie, Saad Ezzini, Naveed Farooz Marazi· 0 citations
Analysis of well plug and abandonment operations in the oil and gas industry requires comprehensive interpretation of historical data distributed across numerous heterogeneous sources, including daily drilling reports, well completion reports, cementing data, intervention reports, schematics, and well integrity assessment materials. In conventional practice, this process is largely performed manually, takes from several days to several weeks, and depends heavily on the individual experience of the engineer. Variations in document structure, data incompleteness, inconsistencies between sources, and limited traceability of engineering conclusions introduce risks of error and hinder the scalability of analysis.
This paper presents an agent-oriented approach to automating the analysis of well P&A operations. The proposed system transforms fragmented processing of historical documentation into a structured and traceable workflow, including document ingestion, parsing, data extraction, reconstruction of well state, validation, well schematic generation, and regulatory compliance assessment. Unlike monolithic solutions based on large language models (LLMs), the system decomposes a complex engineering task into a set of specialized agents coordinated by a central orchestration mechanism. This approach ensures modularity, controllability, reproducibility, and auditability of each processing stage.
The system was applied to representative sets of historical well documentation, including the Petrel-1 case study. The results demonstrate a significant reduction in initial analysis time: data extraction and consolidation were completed in 30–45 minutes compared to 1–3 working days, while a preliminary full P&A analysis required 60–90 minutes instead of 3–5 working days. At the same time, 85–95% of the required engineering parameters were automatically extracted from the documents, depending on input data quality, and all extracted values were linked to their original sources. The system also identified inter-document inconsistencies, missing data, and ambiguous parameters, not replacing engineering judgment but supporting it with more complete and structured information.
The results demonstrate that multi-agent architectures can serve as a practical foundation for automating complex engineering processes that require a combination of unstructured data interpretation, deterministic validation, domain-specific logic, and strict traceability. The proposed system does not replace engineers but augments their capabilities by reducing manual workload, improving analytical consistency, and providing a transparent basis for regulatory compliance verification.
V. K. Payrazyan, Oxana Gubaidullina, Rustam Galliamov et al.· SPE/IADC Asia Pacific Drilli...· 0 citations
This dataset contains over 7 million high-quality annotations of both railway-specific and general perception objects, captured under varying operational scenarios, to serve as a valuable resource for advancing AI-driven environment monitoring in the railway domain.
Claudio Diotallevi, Rodrigo Gudiño, Zaharia Pachalieva et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
