Causal-informed multi-task learning for probabilistic trend prediction of nuclear power plant abnormal conditions
Authors:
- Ben QiBQBen Qi
- Xingyu XiaoXXXingyu Xiao
- Haijing ZhouHZHaijing Zhou
- Jingang LiangJingang Liang
- 4 May 2026
- journal article
- Published by Elsevier in Annals of Nuclear Energy
- Vol. 236
Abstract
No abstract availableFunding Information
- China Postdoctoral Science Foundation (2025M784448)
- National Natural Science Foundation of China (T2192933)
This publication has 30 references indexed in Scilit:
- Analysis of space nuclear reactor under accident conditions with CFD simulation and interpretable machine learning algorithmAnnals of Nuclear Energy, 2025
- Parameter prediction of lead-bismuth fast reactor under various accidents with recurrent neural networkApplied Energy, 2024
- Enhancement in the safety and reliability of Pressurized Water reactors using Machine Learning approachAnnals of Nuclear Energy, 2024
- Comparative study of data-driven and model-driven approaches in prediction of nuclear power plants operating parametersApplied Energy, 2023
- Online autonomous calibration of digital twins using machine learning with application to nuclear power plantsApplied Energy, 2022
- Prediction of crucial nuclear power plant parameters using long short‐term memory neural networksInternational Journal of Energy Research, 2022
- Assessment of RELAP5/MOD3.2 for startup transients in a natural circulation test facilityAnnals of Nuclear Energy, 2018
- Decision treesWIREs Computational Statistics, 2013
- Calculation of the power peaking factor in a nuclear reactor using support vector regression modelsAnnals of Nuclear Energy, 2008
- Multitask Learning: A Knowledge-Based Source of Inductive Bias1993