GPU-accelerated Bayesian inference for block-cave mine monitoring via muon tomography

TL;DR

This paper introduces a GPU-accelerated Bayesian inference method for monitoring block cave geometries via muon tomography, enabling fast, realistic, and accurate 3D cave shape estimation.

Contribution

It presents a low-dimensional surface-based Bayesian framework combined with GPU-accelerated MCMC sampling for efficient and realistic block cave geometry reconstruction.

Findings

Method accurately recovers known cave geometries in simulations.

GPU acceleration significantly reduces sampling time.

Generated geometries are consistent with muon tomography data.

Abstract

We describe a Bayesian framework for an inverse problem arising from monitoring block caving operations via muon tomography. We work with a low dimensional surface-based representation of the geometry of the block cave, which dramatically reduces the computational requirements of the model while allowing realistic geometries. Adopting a Bayesian approach, we define a prior distribution on the space of geometries that favors realistic cave shapes. Pairing this prior with a likelihood based on the muon tomography forward model, we obtain a posterior distribution over cave geometries using Bayes rule. We obtain approximate samples from this posterior distribution using Markov chain Monte Carlo algorithms running on GPUs, resulting in fast and accurate sampling. We test the fidelity of our methodology by applying it to a simulated block caving scenario for which the ground truth is known. Results show that our method produces a diverse array of sensible geometries that are simultaneously compatible with the data.