Search papers, labs, and topics across Lattice.
This paper introduces a continually learning neural-operator surrogate for three-dimensional airborne electromagnetic (AEM) Bayesian inversion, addressing the computational challenges posed by the need for approximately \(10^{10}\) forward evaluations in large surveys. By leveraging the invariance of Maxwell's laws and employing continual learning across multiple geological priors, the surrogate enhances its capability over time, allowing for rapid inversion of over two million soundings in seconds. The method achieves credible intervals that closely align with the true posterior, demonstrating its effectiveness in providing uncertainty-quantified conductivity imaging essential for real-time mineral exploration.
A neural-operator surrogate enables rapid inversion of millions of airborne electromagnetic soundings, achieving near real-time results previously deemed infeasible.
Three-dimensional probabilistic inversion of time-domain airborne electromagnetic (AEM) data is limited by the cost of the forward solve. Even though one simulation takes only tens of seconds, a Bayesian inversion of a survey of millions of soundings requires of order $10^{10}$ forward evaluations. To address this, we develop a continually learning neural-operator surrogate of the three-dimensional AEM forward operator that replaces the solver inside the Bayesian inversion. We start from the point of view that regardless of what geological prior is specified, Maxwell's laws remain invariant. Secondly, we avoid the limitation of learning on a single prior by continual learning on consecutive priors, which means our surrogate becomes richer as it is applied in future case studies, either by the authors, or by the scientific community. We use a validity check built on ensemble disagreement to divert cases with measurements outside the training range to the solver. Driven by the surrogate, the identical Markov chain Monte Carlo sampler reproduces the full-solver posterior, and its credible intervals cover the truth within 2.6 percentage points. Applied to the 2013 Capricorn TEMPEST survey in Western Australia, the surrogate inverts over two million soundings in seconds, a computation infeasible for the solver. Testing the geological prior against the entire survey costs minutes. The framework delivers uncertainty-quantified conductivity imaging at survey scale, which we believe is essential to perform near real-time mineral-systems targeting with geophysics.
