ICFDT8 8th International Conference on Frontier in Diagnostic Technologies

Session

AI in support of diagnostics

20 Oct 2026, 14:00

Sala Bruno Brunelli (Frascati)

3. Deep Learning for data driven understanding and control of complex systems

Dr Andrea Murari (Consorzio RFX)

20/10/2026, 14:00

AI in support of diagnostics

Tutorial

Given the continuous progress in instrumentation and storage technologies, the analysts are increasingly faced with the challenge of analysing time series generated by complex systems, whose physics is poorly known at best. The understanding and control of such systems requires at least the determination of the system dimensionality and the assessment of the cause-effect relationships between...

84. The rise of the agents in Earth Observation

Salvatore Pinto (European Space Agency)

20/10/2026, 14:20

AI in support of diagnostics

Oral

The rapid rise of Agentic AI is reshaping the way we interact with and extract knowledge from Earth Observation data. Beyond traditional AI pipelines, autonomous agents powered by foundation models and emerging world models are enabling more adaptive, context-aware, and interactive approaches to data analysis, scientific discovery, and operational decision-making. This keynote will explore the...

12. Optimising the layout of tomographic diagnostics with Genetic Programming

Ivan Wyss (Università degli studi di Roma Tor Vergata)

20/10/2026, 14:40

AI in support of diagnostics

Oral

Radiation measurements are essential for the operation of next-generation tokamaks, as they provide key information on plasma conditions and support control strategies. Diagnostics such as bolometers, soft X-ray detectors, and scintillators are widely employed for this purpose. However, the design of an effective detection layout is strongly constrained by the limited access provided by...

6. Integrating magnetic and kinetic measurements in the equilibrium reconstruction of tokamaks with Physics Based Neural Networks

Novella Rutigliano (Università degli Studi di Roma Tor Vergata)

20/10/2026, 15:00

AI in support of diagnostics

Oral

Integrated data analysis is essential for the full exploitation of diagnostic measurements. Physics-Informed Neural Networks (PINNs) present a compelling alternative to standard methods (e.g. the Bayesian statistics). As a novel branch of artificial intelligence, PINNs seamlessly integrate data-driven methodologies with physical equations, offering a highly efficient approach.
PINNs provide...

11. TokaLab: an open-access and open-source FAIR framework for tokamak synthetic diagnostics and inverse problems benchmarking

Riccardo Rossi (Università di Roma 2 Tor Vergata)

20/10/2026, 15:20

AI in support of diagnostics

Oral

The development and validation of computational methods for tokamak diagnostics, particularly in the context of inverse problems and data-driven approaches, are often limited by the lack of standardized and reproducible benchmarking practices. In this work, we present an open access and open-source FAIR (Findable, Accessible, Interoperable, Reusable) framework, implemented within TokaLab, for...

78. AI-ENHANCED I&C FOR HYBRID FISSION-FUSION REACTOR CONTROL

Mauro Cappelli (ENEA)

20/10/2026, 15:40

AI in support of diagnostics

Oral

Hybrid fission-fusion reactors (HFR) impose I&C requirements spanning nine frequency decades (DC to THz), generating interference between neutron instrumentation, plasma diagnostics, and RF heating systems. This paper identifies the primary coupling mechanisms, proposes a three-tier galvanic isolation architecture with 8th-order Butterworth filtering targeting −60 dBc inter-band crosstalk (IEC...