Artificial-Intelligence

Our new paper has just been published in SoftwareX: “mcp-fdsnws-event: An MCP gateway for FDSNWS-Event web services”, by Valentino Lauciani and Daniele Bailo. The paper presents mcp-fdsnws-event, an open-source software component that creates a bridge between standard services used by the seismological community and the emerging ecosystem of applications based on Large Language Models and AI agents. The starting point is simple. For many years, the seismological community has used the FDSN Web Services standard to query earthquake catalogues and retrieve information about seismic events. These services are robust, interoperable and widely adopted, but using them normally requires knowledge of APIs, query parameters and formats such as QuakeML. ...

What generative artificial intelligence can teach us about machines, intelligence and, perhaps, ourselves. Artificial intelligence writes texts, generates images, produces software, solves problems and sustains increasingly convincing conversations. But does all this mean that machines are truly intelligent? This is the question at the heart of my article “Dentro la mente dell’intelligenza artificiale” (Inside the Mind of Artificial Intelligence), published in the July-August 2026 issue of Sapere. It is an apparently simple question, but one that contains many others. ...

Whoever governs knowledge also governs Artificial Intelligence. Artificial Intelligence is rapidly becoming one of the strategic technologies that will shape science, industry, and public institutions over the coming decades. Discussions often focus on which language model performs best or which company will release the next breakthrough. Yet a more fundamental question is emerging: Who governs the knowledge on which AI systems rely? Our new paper, published in Earth Science Informatics, argues that trustworthy scientific AI cannot depend solely on increasingly capable language models. It also requires a new way of governing scientific knowledge. ...

I am pleased to share an introduction to the world of Artificial Intelligence (AI), exploring its applications in everyday life as well as in scientific and technological contexts. The seminar examines the fundamental principles that guide AI development, with a focus on advanced technologies such as Machine Learning and Deep Learning, and discusses the differences between generative and traditional AI. It also offers space for reflection on the ethical and environmental aspects of AI use, in line with the European regulatory framework and the challenges ahead. ...

In November 2023, Nature Scientific Data published a scientific article presenting the data integration and computer science work that I carried out over the last 10 years together with a team of truly excellent colleagues. The article presents an initiative that is changing the way we approach Earth-science research in Europe: the EPOS Data Portal. In this post, I will explain in accessible terms what makes this multidisciplinary platform so special. The European Plate Observing System (EPOS) is not just an international initiative; it is a vision that is redefining Earth science in Europe. This pioneering research infrastructure has built a unique collaborative environment where the sharing and use of scientific data are encouraged, supported, and carefully managed. Open Data, in its purest spirit, allows everyone, scientists, policy makers, experts, and citizens, to access information freely. By adhering to the FAIR principles (Findable, Accessible, Interoperable, Reusable), EPOS is becoming a European reference point and a symbol of open and interoperable access to data. This approach not only opens new doors to knowledge, but is also a fundamental step toward more inclusive, collaborative, and innovative scientific research. ...