Physics-Informed Neural Networks (PINNs) enable unsupervised inversion by integrating seismic forward modeling equations directly into neural network loss functions, operating on angle-domain seismic data. The inverse PINN (iPINN) extends this framework by treating the central frequency of the Ricker wavelet as a trainable parameter, thereby enhancing adaptability to spectral mismatch and improving lateral continuity in inversion results. However, iPINN do not provide uncertainty quantification for their predictions. To address this limitation, a Bayesian Physics-Informed Neural Network (iBPINN) is proposed, incorporating Flipout-based Bayesian convolutional and fully connected layers into the iPINN architecture. Through variational inference, iBPINN enables probabilistic modeling of both network weights and wavelet frequency, yielding not only predicted physical parameters but also posterior standard deviation (std) maps for direct visualization and quantitative assessment of predictive uncertainty. Numerical experiments on the Marmousi2 synthetic model show that PINN achieves rapid convergence for large-scale stratigraphic structures, while iPINN provides more consistent inversion results for deeper layers and weakly sensitive parameters via dynamic frequency correction. iBPINN maintains comparable inversion consistency and, crucially, enables intuitive mapping of predictive uncertainty through std analysis, particularly in fault zones, high-impedance contrasts, and low-SNR regions. Field application to seismic data from a CO₂ injection site further demonstrates that the uncertainty maps provided by iBPINN offer additional insights into fluid substitution and reservoir connectivity. This methodological progression—from PINN (“statistics + logic”), to iPINN (“logic + adaptability”), and ultimately to iBPINN (“logic + reasoning”)—mirrors the broader evolution of AI in geophysical inversion: from statistical models, to logic-embedded frameworks, and finally to reasoning-enhanced architectures. The proposed iBPINN framework thus offers a unified, interpretable, and trustworthy approach for next-generation seismic inversion in complex geological environments.

Salt bodies are significant reservoir structures, and there are still difficulties in interpreting them end-to-end from 3-D seismic data. Conventional semi-supervised learning struggles with obtaining high-quality pseudo labels early on, affecting subsequent model performance. Moreover, complex background noise hinders the accuracy of salt body predictions, while a strategy of gradually feeding training blocks leads to fragmented and confusing results. To address these challenges and restore realistic subsurface salt profiles, we have proposed an innovative, fully automated, and refined 3-D salt interpretation method called 3D Salt-HSM. In this method, we have designed a hybrid semi-supervised training paradigm based on stable pseudo labels and multilevel consistency constraints. This approach allows us to obtain high-quality pseudo labels for salt bodies and fully explore their features in unlabeled segmented blocks. We have also introduced a multitask learning strategy for fine interpretation of salt bodies, ranging from image level to pixel level. This strategy helps alleviate the adverse impact of interfering textures on salt body prediction. In addition, we have incorporated a contextual feature fusion module (CFFM) based on the multiscale context of salt bodies. This module enables the network to capture the global information of seismic images and achieve fine-grained salt body interpretation. In our experiments on the SEAM and F3 seismic datasets, we utilized only 3% of the labels for supervised learning, while the remaining data were used for unsupervised learning and validation. The experimental results demonstrate that 3D Salt-HSM outperforms previous state-of-the-art (SOTA) methods in terms of salt body segmentation performance, producing highly satisfactory results.

Cross-domain lithology identification (CDLI) is a common case in lithology identification, which aims to train a machine learning model using the logging data of an interpreted well to predict the lithology of another uninterpreted well. Compared with the general lithology identification problem, the CDLI problem is more challenging for two reasons: the data distribution shift between the wells, and the expensive label acquisition on the uninterpreted well. To tackle these issues, we propose a novel framework that embeds active learning (AL) and domain adaptation into lithology identification. The proposed framework is composed of two components: an AL algorithm that selects the most uncertain and diverse target samples to query their real labels, and a source reweighting method that leverages the target labels to reduce data distribution discrepancy. Experimental results on two real-world data sets demonstrate that the proposed method can more effectively suppress the performance degradation caused by the data distribution shift than the baselines, with fewer target label queries.

Subsurface lithofacies classification refers to the way of establishing a classifier on the interpreted well logging data to predict the lithofacies types corresponding to the uninterpreted ones. Such a task has become a research focus by applying machine learning technologies under the assumption of independent and identical distribution. However, due to the differences in, such as sedimentary environments, reservoir heterogeneity, and logging equipments, the same lithofacies might exhibit different logging characteristics between two different wells or even two different strata in one well. Therefore, motivated by the data drift issue and inspired by the domain adaptation methods, we propose the robust unilateral alignment (RUA) for lithofacies classification. The characteristics of the proposed RUA are as follows: 1) the projected maximum mean discrepancy (PMMD) is designed to reduce the marginal and conditional distribution discrepancy; 2) the random data mapping and target domain information preserving constraint is adopted to embody the data transformation model; and 3) the weighting mechanism and risk-aware constraint are introduced to solve the class imbalance and iterative risk problems. The experiments conducted on the data sets from Jiyang Depression, Bohai Bay Basin, verify the superior performances in accuracy and stability over the existing work.

Identifying borehole lithofacies through geop- hysical loggings is a fundamental task in petroleum exploration industry. Recent interdisciplinary studies have demonstrated the feasibility of applying machine learning to lithofacies identification. Most of these studies establish a mapping from the logging values at one depth point to the lithofacies type. However, due to the intrinsic properties of geophysical loggings, the logging shape should be taken into consideration, apart from the absolute values. In this article, we present the attempt to predict the lithofacies by feeding logging segments, and for the first time model the logging lithofacies identification problem as 1-D semantic segmentation. Such a logging segmentation task is challenging due to two reasons, strong spatial heterogeneity of lithofacies subsurface distribution and the explicit physical significance of geophysical loggings. To solve these challenges, we propose a novel geophysical logging segmentation network entitled SegLog. Specifically, we develop a global statistics pooling subnetwork and a statistics fusion subnetwork to generate statistical embeddings of geophysical loggings. Based on these statistical embeddings, we design a pixel-enhanced convolutional subnetwork to learn the microdetailed features, indicated by pixel-level logging values. These features are fused with the macrosemantic features extracted by a backbone U-Net to constitute the representations that can simultaneously describe the logging spatial correlation and pixel specificity. Experimental results on two logging datasets from the Jiyang Depression verify the effectiveness of our modeling strategy and its state-of-the-art performance on the lithofacies identification problem.