Rapid Parameter Inference with Uncertainty Quantification for a Radiological Plume Source Identification Problem

2025-02-20

AI Summary

Rapid identification of the release source—location and key parameters—is critical for emergency response following instantaneous aerosol releases from nuclear accidents or radiological dispersal devices (RDDs). Method: This paper proposes an emergency-oriented source term inversion method that, given downwind radiation sensor array measurements and wind field data, infers the source location and parameters within minutes while quantifying associated uncertainties. It innovatively integrates a classification neural network—used to partition spatial probability—and a Bayesian neural network—whose weight distribution sampling enables efficient posterior density construction—for the first time in radioactive plume source identification. Contribution/Results: Compared to conventional MCMC-based approaches, the method accelerates inference by over two orders of magnitude. It achieves a median localization error below 150 m and ensures posterior credible intervals contain the true values with >92% coverage, thereby robustly satisfying emergency decision-making requirements for accuracy, speed, and uncertainty awareness.

Technology Category

• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Relational Probabilistic Models
• Planning, Routing, and Scheduling: Activity and Plan Recognition

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation

Abstract

In the event of a nuclear accident, or the detonation of a radiological dispersal device, quickly locating the source of the accident or blast is important for emergency response and environmental decontamination. At a specified time after a simulated instantaneous release of an aerosolized radioactive contaminant, measurements are recorded downwind from an array of radiation sensors. Neural networks are employed to infer the source release parameters in an accurate and rapid manner using sensor and mean wind speed data. We consider two neural network constructions that quantify the uncertainty of the predicted values; a categorical classification neural network and a Bayesian neural network. With the categorical classification neural network, we partition the spatial domain and treat each partition as a separate class for which we estimate the probability that it contains the true source location. In a Bayesian neural network, the weights and biases have a distribution rather than a single optimal value. With each evaluation, these distributions are sampled, yielding a different prediction with each evaluation. The trained Bayesian neural network is thus evaluated to construct posterior densities for the release parameters. Results are compared to Markov chain Monte Carlo (MCMC) results found using the Delayed Rejection Adaptive Metropolis Algorithm. The Bayesian neural network approach is generally much cheaper computationally than the MCMC approach as it relies on the computational cost of the neural network evaluation to generate posterior densities as opposed to the MCMC approach which depends on the computational expense of the transport and radiation detection models.

Problem

• Locate radiological plume source quickly
• Infer source parameters using neural networks
• Quantify uncertainty in predicted source location

Innovation

• Neural networks infer source parameters
• Bayesian neural network quantifies uncertainty
• Computationally cheaper than MCMC approach