---
title: "持续学习神经算子代理实现三维航空电磁贝叶斯反演"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.25932v1"
permalink: "https://feed.astralor.com/items/itm_a8cd29aed4a00538ed9583df"
published: "2026-08-26T15:43:10.000Z"
score: 70
channel: "ai"
tags: ["持续学习","矿产勘探","神经算子","航空电磁法","贝叶斯反演"]
---

# 持续学习神经算子代理实现三维航空电磁贝叶斯反演

## AI 点评

> 这项工作的真正亮点是把持续学习落到电磁反演这个具体物理场景，让代理模型能跨项目越用越强。对计算地球物理和矿产勘探团队来说，这是值得追踪的加速路径；对AI+科学计算的研究者，它示范了如何用集合分歧校验与求解器兜底来保证可靠性。

## 速览

论文针对三维航空电磁数据贝叶斯反演因正演求解成本过高而难以应用的问题，提出一种持续学习神经算子代理，利用麦克斯韦方程组不变性，在多个连续先验上训练代理模型，并通过集合分歧有效性检查将异常样本路由到精确求解器。该框架在2013年Capricorn TEMPEST数据上，仅用数秒即可反演超过两百万个测深点，后验与完整求解器一致，置信区间覆盖真值差距在2.6个百分点内。这套方法为近实时矿产系统靶区圈定提供了不确定度量化电导率成像能力。

## 关键点

- 提出持续学习神经算子替代三维AEM正演求解器，跨先验累积知识。
- 基于集合分歧的有效性检查，超出训练范围的测量自动转交求解器处理。
- 在2013年Capricorn TEMPEST数据上反演超过两百万测深点仅需数秒。
- 代理驱动的MCMC后验与完整求解器一致，置信区间覆盖真值差距仅2.6个百分点。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_a8cd29aed4a00538ed9583df