Spatio-temporal characterization analysis plays a key role in spatio-temporal data mining tasks such as social relationship inference, traffic flow prediction, and spatio-temporal graph node classification. Although traditional numerical simulation methods are effective, they often struggle to accurately portray the complex characteristics of spatio-temporal data due to the intricacy of the modeling processes and the limitations of underlying assumptions. Models based on statistical learning and machine learning, such as ARIMA (AutoRegressive Integrated Moving Average Model) and SVM (Support Vector Machine), are capable of handling spatio-temporal data to a certain extent, but they are limited in their ability to characterize highly nonlinear data and can fail to effectively capture spatio-temporal correlations. To address these challenges, this paper introduces a new deep learning model, the Attention-Guided Spatio-Temporal Convolutional Network (AG-STCN). In the spatial dimension, the model captures spatial dependencies through an attention-guided soft pruning strategy and graph convolution operations. In the temporal dimension, it employs causal convolutions, gated linear units, and a self-attention mechanism to capture temporal dependencies. Experimental results demonstrate that the AG-STCN significantly outperforms existing baseline methods on real-world datasets for multiple spatio-temporal characterization analysis tasks.

The diagenetic facies of tight oil reservoirs reflect the diagenetic characteristics and micro-pore structure of reservoirs, determining the formation and distribution of sweet spot zones. By establishing the correlation between diagenetic facies and logging curves, we can effectively identify the vertical variation of diagenetic facies types and predict the spatial variation of reservoir quality. However, it is still challenging work to establish the correlation between logging and diagenetic facies, and there are some problems such as low accuracy, high time consumption and high cost. To this end, we propose a lithofacies identification method for tight oil reservoirs based on hybrid intelligence using the Fuyu oil layer of the Sanzhao depression in Songliao Basin as the target area. Firstly, the geological characteristics of the selected area were analyzed, the definition and classification scheme of diagenetic facies and the dominant diagenetic facies were discussed, and the logging response characteristics of various diagenetic facies were summarized. Secondly, based on the standardization of logging curves, the logging image data set of various diagenetic facies was built, and the imbalanced data set processing was performed. Thirdly, by integrating CNN (Convolutional Neural Networks) and ViT (Visual Transformer), the C-ViTM hybrid intelligent model was constructed to identify the diagenetic facies of tight oil reservoirs. Finally, the effectiveness of the method is demonstrated through experiments with different thicknesses, accuracy and single-well identification. The experimental results show that the C-ViTM method has the best identification effect at the sample thickness of 0.5 m, with Precision of above 86%, Recall of above 90% and F1 score of above 89%. The calculation result of the Jaccard index in the identification of a single well was 0.79, and the diagenetic facies of tight reservoirs can be identified efficiently and accurately. At the same time, it also provides a new idea for the identification of the diagenetic facies of old oilfields with only logging image data sets.

Spatio-temporal heterogeneous data is the database for decision-making in many fields, and checking its accuracy can provide data support for making decisions. Due to the randomness, complexity, global and local correlation of spatiotemporal heterogeneous data in the temporal and spatial dimensions, traditional detection methods can not guarantee both detection speed and accuracy. Therefore, this article proposes a method for detecting the accuracy of spatiotemporal heterogeneous data by fusing graph convolution and temporal convolution networks. Firstly, the geographic weighting function is introduced and improved to quantify the degree of association between nodes and calculate the weighted adjacency value to simplify the complex topology. Secondly, design spatiotemporal convolutional units based on graph convolutional neural networks and temporal convolutional networks to improve detection speed and accuracy. Finally, the proposed method is compared with three methods, ARIMA, T-GCN, and STGCN, in real scenarios to verify its effectiveness in terms of detection speed, detection accuracy and stability. The experimental results show that the RMSE, MAE, and MAPE of this method are the smallest in the cases of simple connectivity and complex connectivity degree, which are 13.82/12.08, 2.77/2.41, and 16.70/14.73, respectively. Also, it detects the shortest time of 672.31/887.36, respectively. In addition, the evaluation results are the same under different time periods of processing and complex topology environment, which indicates that the detection accuracy of this method is the highest and has good research value and application prospects.

Reservoir evaluation is essential in oil and gas exploration, influencing development decisions. Traditional classification methods are often limited by small sample sizes and low accuracy, restricting their effectiveness. To address this, we propose an intelligent classification method, GA-XGBoost, which integrates Genetic Algorithm (GA) optimization with Extreme Gradient Boosting (XGBoost) to enhance the classification accuracy in small-sample scenarios. The lithological, physical, and lithofacies characteristics of tight sandstone reservoirs are analyzed, and key evaluation parameters—including the mineral composition, porosity, permeability, oil saturation, and logging data (GR, SP, CAL, DEN, AC, LLS)—are selected. After data normalization, the GA-XGBoost model is developed and compared with SVM, XGBoost, and AdaBoost models. The experimental results demonstrate that GA-XGBoost achieves an 88.8% classification precision, outperforming traditional algorithms in both efficiency and accuracy. This study advances experiments on and the standardization of intelligent reservoir evaluations, providing a more reliable classification approach for tight sandstone reservoirs. Additionally, it contributes to the integration of geological exploration and computational intelligence, offering new insights into the application of machine learning in geosciences.

Intelligent identification of sandstone slice images using deep learning technology is the development trend of mineral identification, and accurate mineral particle segmentation is the most critical step for intelligent identification. A typical identification model requires many training samples to learn as many distinguishable features as possible. However, limited by the difficulty of data acquisition, the high cost of labeling, and privacy protection, this has led to a sparse sample number and cannot meet the training requirements of deep learning image identification models. In order to increase the number of samples and improve the training effect of deep learning models, this paper proposes a tight sandstone image data augmentation method by combining the advantages of the data deformation method and the data oversampling method in the Putaohua reservoir in the Sanzhao Sag of the Songliao Basin as the target area. First, the Style Generative Adversarial Network (StyleGAN) is improved to generate high-resolution tight sandstone images to improve data diversity. Second, we improve the Automatic Data Augmentation (AutoAugment) algorithm to search for the optimal augmentation strategy to expand the data scale. Finally, we design comparison experiments to demonstrate that this method has obvious advantages in generating image quality and improving the identification effect of deep learning models in real application scenarios.