神经-物理反演器：一种将集成条件化与残差学习耦合的模块化大地电磁反演框架
The Neuro-Physical Inverter: A Modular Framework for Magnetotelluric Inversion Coupling Ensemble Conditioning with Residual Learning
浏览论文内容
中文总结 AI 辅助
提出神经-物理反演器（NPI），一种耦合集成条件化与残差学习的模块化大地电磁反演框架，通过合成实验和野外数据验证，能降低误差并保持不确定性估计。
中文摘要 AI 辅助
我们提出了神经-物理反演器（NPI），这是一种用于地球物理反演的模块化、不确定性感知框架，它将基于集成的条件化与约束残差学习相结合，并在1D大地电磁（MT）设置中作为受控测试平台进行了演示。该框架分两个阶段运行。集成条件高斯过程（EnsCGP）根据观测响应条件化先验电阻率模型集成，生成物理上可接受的参考集成。随后，一个残差学习神经网络预测对该参考的针对性修正，该网络在合成数据上训练，并通过物理耦合目标针对野外应用逐台站微调。由于集成在两个阶段中均被条件化、细化和传播，每个估计都带有相关的集成离散度。合成实验表明，NPI系统性地降低了集成平均误差，而未破坏集成的稳定性。应用于美国内华达州加布斯谷地热区的宽带MT数据时，NPI在中周期频段降低了跨台站平均失配，同时保持了相当的集成离散度。传播的集成产生了一个不确定性因子，作为假定模型类别内约束的操作性度量。两个阶段在公式上均与维度无关，此处确立的设计原则旨在扩展到更高维的参数化。
英文摘要
We present the Neuro-Physical Inverter (NPI), a modular, uncertainty-aware framework for geophysical inversion that couples ensemble-based conditioning with constrained residual learning, demonstrated in the 1D magnetotelluric (MT) setting as a controlled testbed. The framework operates in two stages. An Ensemble-Conditional Gaussian Process (EnsCGP) conditions a prior ensemble of resistivity models on the observed response, producing a physically admissible reference ensemble. A residual-learning neural network then predicts targeted corrections to this reference, trained on synthetic data and fine-tuned per station for field application through a physics-coupled objective. Because an ensemble is conditioned, refined, and propagated through both stages, every estimate carries an associated ensemble spread. Synthetic experiments show that NPI systematically reduces ensemble-mean error without destabilizing the ensemble. Applied to broadband MT data from the Gabbs Valley geothermal region (Nevada, USA), NPI reduces the across-station mean misfit over the mid-period band while retaining comparable ensemble spread. The propagated ensemble yields a factor of uncertainty that serves as an operational measure of constraint within the assumed model class. Both stages are dimension-agnostic in formulation, and the design principles established here are intended to scale to higher-dimensional parameterizations.
发表机构
- Massachusetts Institute of Technology（麻省理工学院）
- Woods Hole Oceanographic Institution（伍兹霍尔海洋研究所）
机构由 AI 辅助整理，请以论文原文为准。
