RECORD
Uncertainty Quantification for Data-Driven Machine Learning Models in Nuclear Engineering Applications: Where We Are and What Do We Need?
Systems and Control · Submitted 16 Mar 2025
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Finally, we will discuss the need for building a verification, validation and UQ framework to establish ML credibility.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
Machine learning (ML) has been leveraged to tackle a diverse range of tasks in almost all branches of nuclear engineering. Many of the successes in ML applications can be attributed to the recent performance breakthroughs in deep learning, the growing availability of computational power, data, and easy-to-use ML libraries. However, these empirical successes have often outpaced our formal understanding of the ML algorithms. An important but under-rated area is uncertainty quantification (UQ) of ML. ML-based models are subject to approximation uncertainty when they are used to make predictions, due to sources including but not limited to, data noise, data coverage, extrapolation, imperfect model architecture and the stochastic training process. The goal of this paper is to clearly explain and illustrate the importance of UQ of ML. We will elucidate the differences in the basic concepts of UQ of physics-based models and data-driven ML models. Various sources of uncertainties in physical modeling and data-driven modeling will be discussed, demonstrated, and compared. We will also present and demonstrate a few techniques to quantify the ML prediction uncertainties. Finally, we will discuss the need for building a verification, validation and UQ framework to establish ML credibility.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | Machine learning (ML) has been leveraged to tackle a diverse range of tasks in almost all branches of nuclear engineering. | background 1.00 | 0.06 | 0.02 | asserted 1.00 |
| s1 | Many of the successes in ML applications can be attributed to the recent performance breakthroughs in deep learning, the growing availability of computational power, data, and easy-to-use ML libraries. | background 1.00 | 0.06 | 0.02 | asserted 0.92 |
| s2 | However, these empirical successes have often outpaced our formal understanding of the ML algorithms. | gap 0.66 | 0.09 | 0.03 | asserted 0.93 |
| s3 | An important but under-rated area is uncertainty quantification (UQ) of ML. | gap 0.83 | 0.10 | 0.06 | asserted 0.99 |
| s4 | ML-based models are subject to approximation uncertainty when they are used to make predictions, due to sources including but not limited to, data noise, data coverage, extrapolation, imperfect model architecture and the stochastic training process. | background 0.99 | 0.08 | 0.04 | asserted 0.99 |
| s5 | The goal of this paper is to clearly explain and illustrate the importance of UQ of ML. | contribution 0.99 | 0.26 | 0.07 | asserted 0.91 |
| s6 | We will elucidate the differences in the basic concepts of UQ of physics-based models and data-driven ML models. | contribution 0.98 | 0.36 | 0.04 | asserted 0.87 |
| s7 | Various sources of uncertainties in physical modeling and data-driven modeling will be discussed, demonstrated, and compared. | contribution 0.94 | 0.38 | 0.04 | asserted 0.94 |
| s8 | We will also present and demonstrate a few techniques to quantify the ML prediction uncertainties. | contribution 0.88 | 0.69 | 0.06 | asserted 0.97 |
| s9 | Finally, we will discuss the need for building a verification, validation and UQ framework to establish ML credibility. | future work 0.95 | 0.15 | 0.40 | asserted 0.86 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
Machine learning (ML) has been leveraged to tackle a diverse range of tasks in almost all branches of nuclear engineering. Many of the successes in ML applications can be attributed to the recent performance breakthroughs in deep learning, the growing availability of computational power, data, and easy-to-use ML libraries. However, these empirical successes have often outpaced our formal understanding of the ML algorithms. An important but under-rated area is uncertainty quantification (UQ) of ML. ML-based models are subject to approximation uncertainty when they are used to make predictions, due to sources including but not limited to, data noise, data coverage, extrapolation, imperfect model architecture and the stochastic training process. The goal of this paper is to clearly explain and illustrate the importance of UQ of ML. We will elucidate the differences in the basic concepts of UQ of physics-based models and data-driven ML models. Various sources of uncertainties in physical modeling and data-driven modeling will be discussed, demonstrated, and compared. We will also present and demonstrate a few techniques to quantify the ML prediction uncertainties. Finally, we will discuss the need for building a verification, validation and UQ framework to establish ML credibility.
Human review
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.