DECIMA: Open-source AI-assisted analysis of MCNP PTRAC files for neutronics in fusion and fission

Read full text Summarise with VIRAT
Authors: Q. Ducasse, Feda Almuhisen
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

DECIMA (Data Extraction and Contextual Inference for MCNP Analysis) is an open-source framework designed to facilitate the analysis of MCNP PTRAC files, which contain detailed particle tracking data from neutron transport simulations. Due to their complexity and size, PTRAC files are difficult to exploit with traditional tools.DECIMA addresses this challenge by combining large language models (LLMs), knowledge graphs, and a modular agent-based architecture to enable intuitive and automated data analysis. The system allows users to query PTRAC data in natural language and automatically generates both explanations and executable analysis code.This approach aims to improve usability, reproducibility, and efficiency in nuclear simulation workflows, with applications in fusion, radiation protection, and nuclear safety.

Fields of Study & Subjects

Nuclear reactor physics and engineering Nuclear Physics and Applications Fusion materials and technologies

Publication details

Journal / source
HAL
Publication date
10 March 2026
Language
EN