Computationally efficient emulation of spheroidal elastic deformation sources using machine learning models: a Gaussian-process-based approach

Kyle R. Anderson; Mengyang Gu

doi:10.1029/2024jh000161

Home/Archive/USGS

USGS · 70256116

Computationally efficient emulation of spheroidal elastic deformation sources using machine learning models: a Gaussian-process-based approach

Kyle R. Anderson·Mengyang Gu

View original source ↗Export metadata ↓

Abstract

Elastic continuum mechanical models are widely used to compute deformations due to pressure changes in buried cavities, such as magma reservoirs. In general, analytical models are fast but can be inaccurate as they do not correctly satisfy boundary conditions for many geometries, while numerical models are slow and may require specialized expertise and software. To overcome these limitations, we trained supervised machine learning emulators (model surrogates) based on parallel partial Gaussian processes which predict the output of a finite element numerical model with high fidelity but >1,000× greater computational efficiency. The emulators are based on generalized nondimensional forms of governing equations for finite non‐dipping spheroidal cavities in elastic halfspaces. Either cavity volume change or uniform pressure change boundary conditions can be specified, and the models predict both surface displacements and cavity (pore) compressibility. Because of their computational efficiency, using the emulators as numerical model surrogates can greatly accelerate data inversion algorithms such as those employing Bayesian Markov chain Monte Carlo sampling. The emulators also permit a comprehensive evaluation of how displacements and cavity compressibility vary with geometry and material properties, revealing the limitations of analytical models. Our open‐source emulator code can be utilized without finite element software, is suitable for a wide range of cavity geometries and depths, includes an estimate of uncertainties associated with emulation, and can be used to train new emulators for different source geometries.

Explore related subjects

JGR Machine Learning and Computation Article

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Kyle R. Anderson, Mengyang Gu. 2024-07-20. Computationally efficient emulation of spheroidal elastic deformation sources using machine learning models: a Gaussian-process-based approach. https://doi.org/10.1029/2024jh000161

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related USGS reports

USGS2026

SlideDetect: Spatio-temporal landslide detection using a three-dimensional convolutional neural network

Landslides pose a serious and ongoing threat to both human lives and infrastructure worldwide; therefore, it is of interest to predict where and when landslides are likely to occur. Advances in machine learning techniques have spurred numerous studies aimed at estimating relative landslide propensity, but are limited to spatial (as opposed to temporal) prediction due to the sparsity of landslide timing data. We address this data gap by training SlideDetect, a 3-dimensional convolutional neural network (3D CNN), to identify landslides based on their spatial and temporal occurrence within multitemporal image stacks. We use an inventory of landsides triggered by the 2018 Hokkaido earthquake and two years of monthly composite optical imagery spanning this event. The model can identify not only landslide location but also landslide date with an area under the precision-recall curve (PR-AUC) of 0.84. We further present a new standard for presenting PR curve results that explicitly compares model performance at different confidence thresholds, allowing for clearer model evaluation and comparison. Our new approach to constraining landslide timing paired with this more consistent and objective method for evaluating model performance shows considerable promise, and with further application and testing, SlideDetect could enhance the data availability and tools needed to advance landslide hazard and risk assessments.

JGR Machine Learning and Computation↗

USGS2026

Localization of spatiotemporally heterogeneous subsurface flows using autoencoder-based deep learning framework for time-lapse self-potential tomography

Self-potential (SP) monitoring has emerged as a valuable method for characterizing subsurface hydrogeological features and processes due to its sensitivity to fluid-induced electrokinetic effects. Despite advancements in SP inversion, challenges remain in imaging groundwater dynamics from SP activities due to complex hydrological settings and transient noise. In this study, a deep learning autoencoder (AE)-based framework is proposed for the spatiotemporal localization of subsurface fluid movement from time-lapse SP tomography. Temporal segments of time-lapse numerical inversions were first derived from long-term SP monitoring conducted from a floodplain site in Oak Ridge, Tennessee, known for active hyporheic exchange. Subsequently, AE models based on vision transformer (ViT), convolutional long short-term memory (ConvLSTM), convolutional neural network, and temporal convolutional network were individually trained and compared on the SP tomography segments for reconstruction performance. Finally, the reconstruction error over time serves as an anomaly score to identify moments of active SP variation, whereas spatial distributions of errors within these moments are analyzed to image and localize regions associated with anomalous subsurface fluid movement. The results demonstrate that ConvLSTM- and ViT-AE are most capable for the localization task with contrasting error distributions and consistent delineation of anomalies. Applying the method to both SP arrays parallel and perpendicular to the stream produced consistent anomaly zones near a fault or karst feature, validating the robustness and generalization of the approach. These results demonstrate the potential of the proposed framework as a scalable and interpretable tool for spatiotemporal analysis of subsurface flow dynamics in complex hydrogeological systems.

Tennessee↗

USGS2025

Uncertainty quantification of geophysical and hydrologic parameters estimated from borehole nuclear magnetic resonance data

Borehole nuclear magnetic resonance (bNMR) data are typically used to infer in situ hydrologic properties. Partial water content as a function of pore size is estimated by fitting the measured NMR response to a multi-exponential T 2 distribution, and the sum of estimated T 2 amplitudes equals the total volumetric water content. From these estimated parameters, several empirical relationships are commonly used to infer hydraulic conductivity from the NMR-estimated water content and T 2 distribution. Often, parameters are estimated through deterministic inversion methods that produce a single best-fit estimate, but do not reflect uncertainties in model parameters. Here, a Bayesian Markov chain Monte Carlo (McMC) approach for analyzing bNMR data is developed that allows for comprehensive uncertainty quantification of NMR parameters and derived hydrologic properties. The underlying model that describes the T 2 distribution is defined by a set of spline interpolation points. The number of interpolation points is allowed to vary in a trans-dimensional algorithm that naturally favors simple models with fewer interpolation points, allowing the data to inform the necessary level of model complexity. Additionally, data error is estimated as an unknown parameter. Analysis of the ensemble of models output from the McMC algorithm provides useful details on the range of plausible T 2 distributions that can fit a measured bNMR decay curve, as well as uncertainty estimates of total water content. The ensemble of NMR parameters can also be propagated through commonly used relationships to produce uncertainty estimates on derived parameters such as bound/capillary/mobile water content or hydraulic conductivity.

JGR Machine Learning and Computation↗