arXiv subjects

Daniel San Martín

Publications and source records attributed to Daniel San Martín.

3 recordsLinked to original sources

arXiv2026

AI4EOSC: a Federated Cloud Platform for Artificial Intelligence in Scientific Research

The rapid growth of Artificial Intelligence and Machine Learning in scientific research has highlighted a gap between industry-standard MLOps tools and platforms, and the unique requirements of modern and Open Science, particularly regarding the FAIR (Findable, Accessible, Interoperable, and Reusable) principles. This paper presents AI4EOSC, a federated, open-source platform designed to operationalize the full AI/ML lifecycle within the European Open Science Cloud (EOSC) ecosystem. Our methodology tackles the fragmentation of distributed research infrastructures by integrating a modular and distributed architecture comprising an AI development platform, a serverless AI-as-a-Service layer, and a federated orchestration model that is able to integrate heterogeneous compute and storage resources from distributed e-Infrastructures. AI4EOSC also introduces a ``FAIR-by-design'' approach that enforces metadata standardization (via MLDCAT-AP) and W3C PROV-compliant provenance tracking through a platform-integrated CI/CD pipeline. AI4EOSC added value is demonstrated through the delivery of a diverse set of community installations, showing consistent and seamless deployment across heterogeneous cloud providers. These installations are validated by a set of scientific cases, showing how our work reduces the manual burden on researchers while ensuring high levels of reproducibility and interoperability and providing an unified environment for development, training, and production of AI/ML models in the EOSC.

cs.DC↗

arXiv2025

A MAPE-K-Based Method for Architectural Conformance Checking in Self-Adaptive Systems

Self-adaptive systems (SASs) adjust their behavior at runtime in response to internal or external change. The MAPE-K model, which includes Monitors, Analyzers, Planners, Executors, and shared Knowledge, is a reference for structuring feedback loops. As SASs evolve, implementations can drift from the intended MAPE-K architecture, compromising planned quality attributes. Architectural Conformance Checking (ACC) addresses this risk by comparing the current implementation to a specification of the architecture. General purpose ACC techniques are flexible, but lack SAS specific semantics, leading to ambiguous specifications and missed violations. We present REMEDY, an ACC approach designed for MAPE-K based SASs. REMEDY provides three elements: a domain specific language for expressing planned architectures in MAPE-K terms, a tool that extracts the implemented architecture, and a conformance engine that reports violations. By encoding SAS domain rules and reusing MAPE-K abstractions, REMEDY reduces specification effort and lowers error rates relative to general ACC. We evaluate REMEDY through a robotic SAS case study and a controlled experiment with software engineering students. Results show higher modeling productivity and effective detection of architectural drift, supporting more reliable verification of conformance to the MAPE-K reference model.

cs.SE↗

arXiv2024

Transformer based super-resolution downscaling for regional reanalysis: Full domain vs tiling approaches

Super-resolution (SR) is a promising cost-effective downscaling methodology for producing high-resolution climate information from coarser counterparts. A particular application is downscaling regional reanalysis outputs (predictand) from the driving global counterparts (predictor). This study conducts an intercomparison of various SR downscaling methods focusing on temperature and using the CERRA reanalysis (5.5 km resolution, produced with a regional atmospheric model driven by ERA5) as example. The method proposed in this work is the Swin transformer and two alternative methods are used as benchmark (fully convolutional U-Net and convolutional and dense DeepESD) as well as the simple bicubic interpolation. We compare two approaches, the standard one using the full domain as input and a more scalable tiling approach, dividing the full domain into tiles that are used as input. The methods are trained to downscale CERRA surface temperature, based on temperature information from the driving ERA5; in addition, the tiling approach includes static orographic information. We show that the tiling approach, which requires spatial transferability, comes at the cost of a lower performance (although it outperforms some full-domain benchmarks), but provides an efficient scalable solution that allows SR reduction on a pan-European scale and is valuable for real-time applications.

cs.LG↗