The refinement of acquired well logs has traditionally relied on predefined rock physics models, albeit with their inherent limitations and assumptions. As an alternative, effective yet less explicit machine learning (ML) techniques have emerged. The integration of these two methodologies presents a promising new avenue. In our study, we used four ML algorithms: Random Forests (RF), Gradient Boosting Decision Trees (GBDT), Multilayer Perceptrons (MLP), and Linear Regression (LR), to predict porosity and clay volume fraction from well logs. Throughout the entire workflow, from feature engineering to outcome interpretation, our predictions are guided by rock physics principles, particularly the Gardner relations and the Larionov relations. Remarkably, while the predictions themselves are satisfactory, SHapley Additive exPlanations (SHAP) analysis uncovers consistent patterns across the four algorithms, irrespective of their distinct underlying structures. By juxtaposing the SHAP explanations with rock physics concepts, we discover that all four algorithms align closely with rock physics principles, adhering to its cause–effect relationships. Nonetheless, even after intentionally excluding crucial controlling input features that would inherently compromise prediction accuracy, all four ML algorithms and the SHAP analysis continue to operate, albeit in a manner that seems irrational and starkly contradicts the fundamental principles of rock physics. This integration strategy facilitates a transition from solely mathematical explanations to a more philosophical interpretation of ML-based predictions, effectively dismantling the traditional black box nature of these ML models.

In petroleum exploration and production, extracting petrophysical parameters of oil reservoirs from 3D seismic elastic data poses significant challenges. Applying machine-learning (ML) algorithms to this issue promises much, but rigorous feasibility evaluation in advance is crucial. More significantly, a comprehensive mathematical and logical justification is imperative to illuminate the “black box” nature of ML, thereby bridging existing gaps in explanation for enhanced trust and insights. In this study, the input elastic data for random forests (including P- and S-wave velocities as well as density) is derived from the Raymer-Dvorkin-Voigt rock-physics model with known petrophysical parameters. Subsequently, noise or filtering is applied to the input data to emulate field application conditions. The modeled data, devoid of confounders, facilitate unambiguous causal interpretation. The algorithm demonstrates efficient and stable predictions for porosity, followed by clay volume, whereas water saturation predictions are less accurate. Subsequently, Shapley additive explanations are used to mathematically assess the relative importance of each input feature in determining the outcomes, thereby elucidating the algorithm’s functionality. Furthermore, the causality is understood by referencing rock physics as the foundational assumption of truth. The results indicate illogical behavior in association-oriented ML, contradicting rock physics and logical principles. Overall, ML for petrophysical prediction is effective but constrained by several factors, such as the problematic assumption of independent and identical distributed data, the unsatisfactory quality of data, and the complicated nature of the underlying physics. Our framework establishes a solid foundation for subsequent inquiries aimed at elucidating the explanation and causality behind ML-based petrophysical predictions.

Traditional geological mapping is often time-consuming, labor-intensive, and restricted by rugged terrain. This study addresses these challenges by proposing a novel methodology for automated lithological identification in the Ququleke area of the eastern Kunlun Mountains, which pioneers the integration of portable UAV oblique photogrammetry with a Coordinate Attention-enhanced DeepLabV3+ (CA-DeepLabV3+) semantic segmentation framework for geological mapping. Using a DJI Mavic 3M quadcopter, high-resolution oblique photogrammetric orthophotos were captured to build a pixel-level lithology dataset containing four classes: sandstone, diorite, marble, and Quaternary sediments. The CA-DeepLabV3+ model, adapted from the DeepLabV3+ encoder–decoder framework, integrates a lightweight MobileNetV2 backbone and a Coordinate Attention mechanism to strengthen spatial position encoding and fine-scale feature extraction, crucial for detailed lithological discrimination. Experimental evaluation demonstrates that the proposed model achieves an overall accuracy of 97.95%, mean accuracy of 97.80%, and mean intersection over union of 95.71%, representing a 5.48% improvement in mean intersection over union (mIoU) over the standard DeepLabV3+. These results indicate that combining UAV oblique photogrammetry with the CA-DeepLabV3+ network enables accurate lithological mapping in complex terrains. The proposed method provides an efficient and scalable solution for geological mapping and mineral resource exploration, highlighting the potential of low-altitude UAV remote sensing for field-based geological investigations.

Tectonic mélanges are crucial for deciphering collision processes in orogenic belts. This study investigates the nature of the metamorphosed mélange in the Milin area of the eastern Himalayan syntaxis to shed light on the India–Asia collision in the region. The mélange exhibits a ‘block-in-matrix’ fabric in the lower and upper parts and a ‘lenticular-thrust-slices’ fabric in the middle. Quartzite blocks in the lower part are proposed to be Silurian or younger quartz arenites with a Tethyan affinity. Metacherts and amphibolites in the middle and upper parts may have originated from hydrothermal or terrestrial cherts and Nb-enriched basalts in the Asian forearc or syncollisional basin at ∼48–45 Ma. The diverse blocks/slices of the mélange, sourced from both the subducting and overriding plates, are suggested as having formed during Indian plate subduction. The protoliths of the amphibolite–metachert slice (∼45 Ma) in the mélange are distinctly different from the contemporary shallow sea (post-collisional) deposits but similar to the deep-water (initial collisional or pre-collisional) sediments in other parts of the suture zone. This implies that the amphibolite–metachert slice may represent the product of the initial India–Asia collision or even pre-collision and that (hard) collision likely lagged by ∼10 Myr in the eastern Himalaya syntaxis. Supplementary material: Analytical methods, Figures S1–S5 showcasing field occurrences, cathodoluminescence images of zircons, and geochemical characteristics, Table S1 – geochronology data, Table S2 – zircon Lu–Hf isotopic data, and Table S3 – whole-rock major and trace element results are available at https://doi.org/10.6084/m9.figshare.c.6896942 Thematic collection: This article is part of the Ophiolites, melanges and blueschists collection available at: https://www.lyellcollection.org/topic/collections/ophiolites-melanges-and-blueschists

The Cryogenian–Ediacaran strata in the Kuruktag block, northeastern Tarim Craton, are pivotal for deciphering the breakup of Neoproterozoic Rodinia and related peripheral subduction processes. This study reveals previously unidentified Ediacaran strata in the western Kuruktag block, characterized by deltaic plain clastic rocks and channel deposits. Zircon geochronological analyses of basalts and sandstones indicate a maximum depositional age of ~596 Ma, thereby attributing these strata to the Ediacaran Yukengou Formation in conjunction with prior paleontological findings. The prevalence of lithic fragments and two primary detrital zircon age populations within the Yukengou Formation sandstones suggest a rift basin environment, in contrast to a passive continental margin, receiving detrital material from the neighboring Paleoproterozoic basement and Neoproterozoic magmatic activity. As a result, the Cryogenian–Ediacaran strata are posited to have been deposited in an aulacogen basin. The presence of numerous Neoproterozoic zircon grains further implies significant volcanic events preceding and concurrent with Cryogenian rifting, suggesting that continental rifting along the northeastern Tarim margin may have been instigated by subduction-induced extension.