AI Insight
Researchers developed a complex-valued conditional variational autoencoder (CVAE) to analyze spectral induced polarization (SIP) data, which measures electrical properties of subsurface materials. The machine learning approach improved upon conventional methods by learning relaxation time distributions across 140 laboratory and field measurements, achieving reconstruction errors of 0.53% and 0.27% for imaginary and phase components respectively. The method also created a structured latent representation that improved data clustering by nearly a factor of two compared to traditional parameters.
Why it matters
This advancement could improve characterization of subsurface materials in geophysical applications such as groundwater exploration, mineral prospecting, and environmental site assessment. The improved uncertainty quantification and ability to handle heterogeneous datasets may enable more reliable interpretation of subsurface conditions across diverse geological settings.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Abstract: Spectral induced polarization (SIP) is a geophysical method used to characterize subsurface materials. It measures the frequency-dependent complex electrical resistivity of rocks and soils through the application of an alternating current. Debye and Warburg decompositions are standard methods for analyzing and interpreting SIP data, as they allow estimation of the relaxation time distribution (RTD) of geomaterials. However, conventional decomposition approaches treat measurements independently, work in real-valued spaces despite the complex-valued nature of SIP data, and provide limited uncertainty quantification. These limitations reduce the effectiveness of conventional decomposition on heterogeneous datasets. We reformulate the decomposition approach as an unsupervised machine learning problem and introduce a conditional variational autoencoder (CVAE) that learns a shared mapping from SIP datasets to continuous RTDs. The model is validated on a dataset comprising 140 laboratory and field SIP measurements of granular mixtures, sedimentary and igneous rock, and cementitious materials. The CVAE operates in complex-valued data space and achieves reconstruction errors of 0.53 % and 0.27 % for the imaginary and phase components of resistivity, respectively, with evidence of improvement over conventional methods at corresponding p-values of 0.007 and 0.06. The inferred RTDs are stable and physically consistent, and their total chargeability and mean relaxation time correlate with polarizable grain content and grain size, respectively, with coefficients of determination up to 0.98. An additional contribution of the proposed method is the learned latent representation, which organizes SIP spectra into a structured space. Unsupervised clustering in a two-dimensional projection of this space improves the silhouette score by nearly a factor of two relative to conventional RTD parameters.