Natural Resources Research最新文献

In petroleum and natural gas exploration, lithology identification—analyzing rock types beneath the Earth’s surface—is crucial for assessing hydrocarbon reservoirs and optimizing drilling strategies. Traditionally, this process relies on logging data such as gamma rays and resistivity, which often require manual interpretation, making it labor-intensive and prone to errors. To address these challenges, we propose a novel machine learning framework—contrastive learning-transformer—leveraging self-attention mechanisms to enhance the accuracy of lithology identification. Our method first extracts unlabeled samples from logging data while obtaining labeled core sample data. Through self-supervised contrastive learning and a transformer backbone network, we optimize performance using techniques like batch normalization. After pretraining, the model is fine-tuned with a limited number of labeled samples to improve accuracy and significantly reduce reliance on large labeled datasets, thereby lowering the costs associated with drilling core annotations. Additionally, our research incorporates shapley additive explanations (SHAP) technology to enhance the transparency of the model’s decision-making process, facilitating the analysis of the contribution of each feature to lithology predictions. The model also learns time-reversal invariance by reversing sequential data, ensuring reliable identification even with variations in data sequences. Experimental results demonstrate that our transformer model, combined with semi-supervised contrastive learning, significantly outperforms traditional methods, achieving more precise lithology identification, especially in complex geological environments.

In the realm of mineral prospectivity mapping, a novel hybrid approach for optimizing hyperparameters of the support vector machine (SVM) algorithm is proposed here. The concept of ant colony optimization (ACO) algorithm, inspired by collective intelligence of ant colonies, and grid search (GS) that systematically evaluate all hyperparameter combinations to find the optimal model configuration are leveraged to fine-tune SVM parameters, enhancing its predictive capabilities. A dataset comprising geophysical, geochemical, geological, tectonic, and remote sensing evidence layers from the Sardouyeh region in Kerman province, Iran, is utilized for model development aimed the prediction of areas favorable for porphyry-Cu mineralization. After generating the regular and tuned predictive models, a comparison was carried out using quantitative performance metrics such as confusion matrix and success rate curves. The results demonstrated that the optimized versions of SVM using ACO (ACO–SVM) and GS (GS–SVM) models exhibit superior performance, achieving better accuracy and predictive capability in identifying locations favorable for porphyry-Cu mineralization. The study highlights the potential of incorporating optimization algorithms, especially ACO, into SVM, leading to the development of more effective predictive models for mineral prospectivity mapping.

In surface deformation monitoring for mining areas, interferometric synthetic aperture radar (InSAR) technology has become a popular research topic due to its efficiency and high accuracy. However, transforming temporal monitoring data into surface deformation predictions remains challenging. In practical applications, InSAR data often face limitations like low acquisition frequency and insufficient data volume, leading to prediction models being prone to overfitting and having poor accuracy. Therefore, this paper proposes an improved temporal convolutional network (TCN) time-series generative adversarial network (GAN) with an attention mechanism, called the Attention–TCN–TimeGAN, to enhance InSAR surface deformation data for better prediction results. By combining the embedding, recovery, generator, and discriminator networks, we used the TCN to expand the receptive field and capture long-term temporal features. Additionally, we integrated the self-attention mechanism into the generator and discriminator to adapt to random vectors, achieving better data generation results. The loss function uses the Wasserstein distance to measure the original data distribution and adds a gradient penalty term with adaptive weights to achieve effective feature extraction from time-series data. Experimental results show that the data generated by our model more comprehensively cover the original data distribution. The prediction results at four test points showed the lowest mean absolute error and mean-squared error and the highest coefficient of determination (R²). These results demonstrate the effectiveness of our generative model in predicting small-sample InSAR time-series data, providing a new method for surface deformation monitoring.

Acid fracturing technology is one of the most effective methods for resolving mineral plugging and for improving the pore structure of coal reservoirs. To investigate the characteristics of shallow and deep coal nanopore structures under the influence of acidic fracturing fluids, experiments using synchrotron radiation small-angle X-ray scattering were conducted on shallow and deep coal samples soaked in acidic fracturing fluids of different concentrations for varying durations. This quantitatively characterized the different nanoscale pore scattering intensity ratios (A_I), fractal dimensions, and nanopore parameters. The research indicates that, under the influence of acidic fracturing fluids, the shallow coal nanopore structure tends to become more complex while that of deep coal becomes simpler. The impact of 20% acidic fracturing fluid is greatest on shallow coal nanopore structure, while deep coal nanopore structure is more susceptible to 12% acidic fracturing fluid, with these effects primarily concentrated in the 2–10 nm pores. Acidic fracturing fluids primarily affect the shallow and deep coal nanopore structures by dissolving, among others, carbonate minerals, pyrite, and clay minerals, resulting in the dynamic evolution of the shallow and deep coal nanopore structures during the soaking process.

The simultaneous interpretation of multiple geophysical data through their inverted models of various physical properties of subsurface geological structures and formations related to mineral deposits is a challenging task in mineral exploration. In this paper, a three-dimensional fusion algorithm based on the use of a two-dimensional contourlet transform for concurrent interpretation of multiple geophysical models is proposed. To achieve this, initially, a synthetic model based on a general structure simulating the spatial distribution of physical and geological properties of typical porphyry-Cu deposits using a mineral exploration database is generated, and the results of applying the proposed algorithm to this model are presented. Subsequently, the proposed algorithm is implemented on the Zaftak porphyry-Cu deposit in the southern part of Kerman Province in southern Iran. For this purpose, two fusion models with different contourlet decomposition levels are compared through their consistency with the geological settings of the study area to select the best fusion model using two well-known consistency analyses known as Jensen–Shannon divergence index and BLOB Analysis score. Moreover, the fusion models with 2 and 3 contourlet decomposition levels are compared based on available exploratory data. Finally, based on the validation and conformity of the fused model with the available exploratory borehole data and the geology of the study area, a suitable match for the three-dimensional fused model using two-dimensional contourlet transform with the Jensen–Shannon divergence index of 95.13% and a BLOB Analysis score of 4.68 was found.

Accurately analysis of the multifractal characteristics of geochemical element distribution is crucial for identifying geochemical anomalies and meaningful element associations. However, the most commonly used multifractal method, i.e., the method of moments, may generate different multifractal spectra for a single element distribution due to variations in the range of moment orders. This is because multifractals and their control mechanisms are not well defined. Fractal topography provides a basis for defining multifractals and clarifies the physical meaning of the singularity index. Therefore, a multifractal analysis method based on fractal topography is proposed to generate a unified multifractal spectrum and give new insight into the singularity analysis of element distribution. The similarities and distinctions between the two methods were evaluated using the de Wijs model. The distributions of two multifractal spectra are shown to be fundamentally consistent. The novel method, nevertheless, utilizes fewer statistics and presents a simplified criterion for element enrichment or depletion. To demonstrate its application, Cu geochemical distribution in the Zhongdian area, China, was used as a case study. Based on the comparison results of the two approaches, the proposed novel approach proves beneficial for accurately characterizing the heterogeneity of geochemical element distribution while maintaining a consistent range of the singularity index. The singularity index distribution map at a fine scale provides a comprehensively detailed zonation of geochemical anomalies and, at different scales, it can effectively reveal and interpret the variation of element distribution.

The production of coalbed methane (CBM) wells is positively correlated with their production performance, and key features of typical production performance can be applied to determine the high production exploration targets. However, accurately classifying the production types of CBM wells and rationally identifying the key controlling factors among them are challenging due to the strong heterogeneity of CBM reservoirs. The data-driven “black-box” algorithms utilized in previous studies often suffer from limited interpretability due to a lack of sufficient domain theoretical foundation. This paper proposes an interpretable residual graph convolutional neural network model (I–RGCN) for classifying the production types and for identifying key features of typical production of CBM wells from spatial relationships and attribute data. This model constructs a topological graph structure based on the spatial correlations among wells and utilizes the dynamic time warping algorithm to assess the similarity of geological feature parameters among CBM wells, incorporating these as edge weights in the model for accurate classification of CBM production types. Subsequently, the GNNExplainer was used to rank the importance of features during the model's decision-making process. Final experiments conducted on datasets from the Fanzhuang–Zhengzhuang block within the Qinshui coalfield demonstrated that the I–RGCN achieves accuracy of > 84% and F1 score of ~ 65%, and outperformed other baseline models and enhanced the interpretability of the results obtained. Thus, this paper offers a novel and interpretable research methodology for the classification of CBM production types and the identification of key features of the production performance of CBM.

Liquid nitrogen fracturing is an efficient stimulation technique for exploiting hot dry rock geothermal energy. Understanding the physical and mechanical damage characteristics of high-temperature reservoir rocks under liquid nitrogen cooling is crucial for the application of liquid nitrogen fracturing technology. Therefore, nuclear magnetic resonance technology, acoustic wave velocity measurement technique, acoustic emission (AE) technology, and 3D scanning technology were used to explore changes in the physical and mechanical properties of high-temperature granite under liquid nitrogen cooling from macroscopic and microscopic perspectives. Our research findings show that, as treatment temperature increased, the internal pore structure of the sample changed gradually, with decrease in proportion of micropores and increase in proportion of macropores. The number of pores of various sizes increased gradually. In particular, after treating the granite to a treatment of 600℃, there was a significant increase in the quantity of pores within the granite, primarily manifested by an increase in macropores. From 25 to 600℃, the compressive strength decreased from 160.79 to 68.44 MPa, a reduction of 57.44%; the tensile strength decreased from 11.13 to 6.02 MPa, a reduction of 45.91%. The fractal dimension of the fracture surface of Brazilian disk samples was calculated using the box-counting method, and the results indicated that an increase in treatment temperature would lead to an increase in roughness of the sample’s fracture surface. During the uniaxial compression tests, the AE parameter rise angle (RA) suddenly increased near the peak load. The straight line relationship (average frequency = 11RA + 60) was used to classify the AE signals generated during uniaxial compression of samples. With increase in treatment temperature, the shear signal increased gradually, which is highly consistent with the macroscopic failure characteristics of the samples.

As natural gas exploration and research progress, the Yinggehai Basin has achieved notable advancements and discoveries regarding middle-deep strata in recent years. Due to insufficient exploration in the Northern Yinggehai Basin, the previous studies primarily concentrated on the Miocene reservoirs with lack of research attention on the Oligocene Yacheng Formation (E₃y) source rocks. A comprehensive evaluation of the E₃y source rocks, encompassing hydrocarbon generation, expulsion characteristics, and resource potential, is lacking, thereby hindering further exploration in the study area. Utilizing the geological and geochemical data of E₃y, the hydrocarbon generation and expulsion model was developed. For the first time, a division of hydrocarbon generation and expulsion amount into gas and oil amount is proposed, comprising generated and expelled gas amount, as well as generated and expelled oil amount. The findings suggest that the sedimentary facies of E₃y primarily consisted of delta plain swamp facies and neritic facies, influencing the development of coal-bearing source rocks and marine mudstones. The coal-bearing source rocks exhibited limited thicknesses and areas. During the early to late Oligocene, there was a gradual increase in thickness and area of the marine mudstone. The source rocks exhibit a notable presence of organic matter, with total organic carbon contents ranging from 19% to 95% for coal and 0.12% to 12.6% for mudstone, predominantly composed of type III, and display high maturity indicated by vitrinite reflectance values ranging from 2.0% to 5.0%. At 0.8%, R_o reached the hydrocarbon expulsion threshold, resulting in generated and expelled amounts of 677.73 × 10⁸ t and 441.14 × 10⁸ t, respectively. The generated gas amount, generated oil amount, expelled gas amount and expelled oil amount are 651.2 × 10⁸ t, 30.15 × 10⁸ t, 442.63 × 10⁸ t, and 5.95 × 10⁸ t, respectively. Employing the genetic method, the gas and oil resources of E₃y were estimated at 3.28 × 10⁸ t and 0.46 × 10⁸ t, respectively. This indicates that the Northern Yinggehai Basin presents favorable conditions for exploration.

The complex geological architecture, complicated dynamics processes and nonlinear association in mineral systems are the major intrinsic hindrances to predictive mineral exploration. For effectively overcoming such difficulties to achieve credible prediction, 3D geological modeling, numerical dynamics simulation (NDS) and machine learning (ML) were applied to characterize the complex geological architecture, to replay the complicated dynamics processes and to predict mineralization-favor spaces by extracting nonlinear association of multi-features with mineralization in the Dongguashan orefield. The method of SHapley Additive exPlanations (SHAP) was used to explain the correlations between different features and mineralization in the predictive model. The results of the 3D geological modeling revealed that the orebodies are unevenly distributed around the intrusion and closely related to the features of the intrusion’s contact zone and wall rocks. The 3D distribution of resistivity can provide some evidence to infer underground geological architecture rather than a threshold to separate orebodies from wall rocks. The NDS results showed that dilation zones developed around the intrusion and within some beds, being closely associated with the known orebodies. By applying the most popular ML algorithm, random forest, and combining different geological, geophysical and dynamics features as evidence variables, eight ML models were run to predict potential orebodies. The predictive model performance on the test samples indicates that the integration of dynamics evidence with geological evidence significantly improves the predictive capacity of the ML model. The SHAP values demonstrate that volumetric strain is the most important feature, while the inclination of the contact zone has the greatest positive contribution to the predictions. The SHAP values of variable interactions indicate that complex intrusion contact zones and low-pressure, high-dilation areas are closely related to mineralization. The 3D ML prediction evidenced synthetically by geological, geophysical and geodynamical features demonstrates that there are substantial potential ores at depth of the northern east and southern east parts of the orefield.