ENBIS-25 Conference

Session

Explainability (by FR) Invited Session

17 Sept 2025, 11:30

Amphitheater 001 (Ground floor)

Conveners

Explainability (by FR) Invited Session

• Bertrand Iooss (EDF R&D)

10. Interpretable neural network for airborne alpha radioactivity monitoring in decommissioning sites conditions.

Arthur Roblin (ASNR)

17/09/2025, 11:30

Explainability (by FR)

On nuclear sites, such as nuclear power plants, instruments for measuring atmospheric radioactivity are deployed to ensure the radiation protection of workers. This type of instrument continuously samples ambient air aerosols on a filter, measures as an energy spectrum the radioactivity accumulated on the filter in real time, and shall notify the operator if transuranic alpha emitters are...

15. Explaining numerical models with the Generalized Hoeffding decomposition

Joseph Muré (EDF)

17/09/2025, 12:00

Explainability (by FR)

Additive functional decomposition of arbitrary functions of random elements, under the form of high-dimensional model representations is crucial for global sensitivity analysis and more generally understanding black-box models. Formally, for random inputs $X = (X_1, \dots, X_d)^\top$, and an output $G(X)$, it amounts to finding the unique decomposition
\begin{equation}
G(X) = \sum_{A...

25. "Explainable" neural networks to model electricity consumption in a decentralised grid

Yvenn Amara-Ouali (Université Paris Saclay)

17/09/2025, 12:30

Explainability (by FR)

This presentation explores the application of innovative deep learning architectures to enhance electricity demand forecasting in decentralised grid systems, with a focus on the French energy market. Generalised Additive Models (GAMs), which are state of the art methods for electricity load forecasting, struggle with spatial dependencies and high-dimensional interactions inherent in modern...