Artificial Intelligence in Geosciences最新文献

Accurately and efficiently predicting the permeability of porous media is essential for addressing a wide range of hydrogeological issues. However, the complexity of porous media often limits the effectiveness of individual prediction methods. This study introduces a novel Particle Swarm Optimization-based Permeability Integrated Prediction model (PSO-PIP), which incorporates a particle swarm optimization algorithm enhanced with dynamic clustering and adaptive parameter tuning (KGPSO). The model integrates multi-source data from the Lattice Boltzmann Method (LBM), Pore Network Modeling (PNM), and Finite Difference Method (FDM). By assigning optimal weight coefficients to the outputs of these methods, the model minimizes deviations from actual values and enhances permeability prediction performance. Initially, the computational performances of the LBM, PNM, and FDM are comparatively analyzed on datasets consisting of sphere packings and real rock samples. It is observed that these methods exhibit computational biases in certain permeability ranges. The PSO-PIP model is proposed to combine the strengths of each computational approach and mitigate their limitations. The PSO-PIP model consistently produces predictions that are highly congruent with actual permeability values across all prediction intervals, significantly enhancing prediction accuracy. The outcomes of this study provide a new tool and perspective for the comprehensive, rapid, and accurate prediction of permeability in porous media.

The large spatial/temporal/frequency scale of geoscience and remote-sensing datasets causes memory issues when using convolutional neural networks for (sub-) surface data segmentation. Recently developed fully reversible or fully invertible networks can mostly avoid memory limitations by recomputing the states during the backward pass through the network. This results in a low and fixed memory requirement for storing network states, as opposed to the typical linear memory growth with network depth. This work focuses on a fully invertible network based on the telegraph equation. While reversibility saves the major amount of memory used in deep networks by the data, the convolutional kernels can take up most memory if fully invertible networks contain multiple invertible pooling/coarsening layers. We address the explosion of the number of convolutional kernels by combining fully invertible networks with layers that contain the convolutional kernels in a compressed form directly. A second challenge is that invertible networks output a tensor the same size as its input. This property prevents the straightforward application of invertible networks to applications that map between different input–output dimensions, need to map to outputs with more channels than present in the input data, or desire outputs that decrease/increase the resolution compared to the input data. However, we show that by employing invertible networks in a non-standard fashion, we can still use them for these tasks. Examples in hyperspectral land-use classification, airborne geophysical surveying, and seismic imaging illustrate that we can input large data volumes in one chunk and do not need to work on small patches, use dimensionality reduction, or employ methods that classify a patch to a single central pixel.

Magnitude estimation is a critical task in seismology, and conventional methods usually require dense seismic station arrays to provide data with sufficient spatiotemporal distribution. In this context, we propose the Earthquake Graph Network (EQGraphNet) to enhance the performance of single-station magnitude estimation. The backbone of the proposed model consists of eleven convolutional neural network layers and ten RCGL modules, where a RCGL combines a Residual Connection and a Graph convolutional Layer capable of mitigating the over-smoothing problem and simultaneously extracting temporal features of seismic signals. Our work uses the STanford EArthquake Dataset for model training and performance testing. Compared with three existing deep learning models, EQGraphNet demonstrates improved accuracy for both local magnitude and duration magnitude scales. To evaluate the robustness, we add natural background noise to the model input and find that EQGraphNet achieves the best results, particularly for signals with lower signal-to-noise ratios. Additionally, by replacing various network components and comparing their estimation performances, we illustrate the contribution of each part of EQGraphNet, validating the rationality of our approach. We also demonstrate the generalization capability of our model across different earthquakes occurring environments, achieving mean errors of $\pm$0.1 units. Furthermore, by demonstrating the effectiveness of deeper architectures, this work encourages further exploration of deeper GNN models for both multi-station and single-station magnitude estimation.

This study develops a method to use deep learning models to predict the mineral assemblages and their relative abundances in paleolake cores using high-resolution XRF core scan elemental data and X-ray diffraction (XRD) mineralogical results from the same core taken at coarser resolution. It uses the XRF core scan data along with published mineralogical information from the Olduvai Gorge Coring Project (OGCP) 2014 sediment cores 1A, 2A, and 3A from Paleolake Olduvai, Tanzania. Both regression and classification models were developed using a Keras deep learning framework to assess the predictability of mineral assemblages with their relative abundances (in regression models) or at least the mineral assemblages (in classification models) using XRF core scan data. Models were created using the Sequential class and Functional API with different model architectures. The correlation matrix of element ratios calculated from XRF element intensity records from the cores and XRD-derived mineralogical information was used to select the most useful features to train the models. 1057 training data records were used for the models. Lithological classes were also used for some models using Wide & Deep neural networks since those combine the benefits of memorization and generalization for mineral prediction. The results were validated using 265 validation data records unseen by the model and discuss the accuracy of models using six test records. The optimized Deep Neural Network (DNN) classification model achieved over 86% binary accuracy while the regression models were also able to predict the relative mineral abundances of samples with high accuracies. Overall, the study shows the efficacy of a carefully crafted Deep Learning (DL) model for predicting mineral assemblages and abundances using high-resolution XRF core scan data.

In this study, we present an artificial neural network (ANN)-based approach for travel-time tomography of a volcanic edifice under sparse-ray coverage. We employ ray tracing to simulate the propagation of seismic waves through the heterogeneous medium of a volcanic edifice, and an inverse modeling algorithm that uses an ANN to estimate the velocity structure from the “observed” travel-time data. The performance of the approach is evaluated through a 2-dimensional numerical study that simulates i) an active source seismic experiment with a few (explosive) sources placed on one side of the edifice and a dense line of receivers placed on the other side, and ii) earthquakes located inside the edifice with receivers placed on both sides of the edifice. The results are compared with those obtained from conventional damped linear inversion. The average Root Mean Square Error (RMSE) between the input and output models is approximately 0.03 km/s for the ANN inversions, whereas it is about 0.4 km/s for the linear inversions, demonstrating that the ANN-based approach outperforms the classical approach, particularly in situations with sparse ray coverage. Our study emphasizes the advantages of employing a relatively simple ANN architecture in conjunction with second-order optimizers to minimize the loss function. Compared to using first-order optimizers, our ANN architecture shows a ∼25% reduction in RMSE. The ANN-based approach is computationally efficient. We observed that even though the ANN is trained based on completely random velocity models, it is still capable of resolving previously unseen anomalous structures within the edifice with about 5% anomalous discrepancies, making it a potentially valuable tool for the detection of low velocity anomalies related to magmatic intrusions or mush.

Water prediction plays a crucial role in modern-day water resource management, encompassing both hydrological patterns and demand forecasts. To gain insights into its current focus, status, and emerging themes, this study analyzed 876 articles published between 2015 and 2022, retrieved from the Web of Science database. Leveraging CiteSpace visualization software, bibliometric techniques, and literature review methodologies, the investigation identified essential literature related to water prediction using machine learning and deep learning approaches. Through a comprehensive analysis, the study identified significant countries, institutions, authors, journals, and keywords in this field. By exploring this data, the research mapped out prevailing trends and cutting-edge areas, providing valuable insights for researchers and practitioners involved in water prediction through machine learning and deep learning. The study aims to guide future inquiries by highlighting key research domains and emerging areas of interest.

Emeralds – the green colored variety of beryl – occur as gem-quality specimens in over fifty deposits globally. While digital traceability methods for emerald have limitations, sample-based approaches offer robust alternatives, particularly for determining the geographic origin of emerald. Three factors make emerald suitable for provenance studies and hence for developing models for origin determination. First, the diverse elemental chemistry of emerald at minor (<1 wt%) and trace levels (<1 to 100’s ppmw) exhibits unique inter-element fractionations between global deposits. Second, minimally destructive techniques, including laser ablation inductively coupled plasma mass spectrometry (LA-ICP-MS), enable measurement of these diagnostic elemental signatures. Third, when applied to extensive datasets, machine learning (ML) techniques enable the creation of predictive models and statistical discrimination with adequate characterization of the deposits. This study employs a carefully selected dataset comprising more than 1000 LA-ICP-MS analyses of gem-quality emeralds, enriched with new analyses. This dataset represents the largest available for global emerald deposits. We conducted unsupervised exploratory analysis using Principal Component Analysis (PCA). For machine learning-based classification, we employed Support Vector Machine Classification (SVM-C), achieving an initial accuracy rate of 79%. This was enhanced to 96.8% through the use of hierarchical SVM-C with PCA filters as our modeling approach. The ML models were trained using the concentrations of eight statistically significant elements (Li, V, Cr, Fe, Sc, Ga, Rb, Cs). By leveraging high-quality LA-ICP-MS data and ML techniques, accurate identification of the geographical origin of emerald becomes possible. These models are important for accurate provenance of emerald, and from a geochemical perspective, for understanding the formation environments of beryl-bearing pegmatites and shales.

Seismic inversion can be divided into time-domain inversion and frequency-domain inversion based on different transform domains. Time-domain inversion has stronger stability and noise resistance compared to frequency-domain inversion. Frequency domain inversion has stronger ability to identify small-scale bodies and higher inversion resolution. Therefore, the research on the joint inversion method in the time-frequency domain is of great significance for improving the inversion resolution, stability, and noise resistance. The introduction of prior information constraints can effectively reduce ambiguity in the inversion process. However, the existing model-driven time-frequency joint inversion assumes a specific prior distribution of the reservoir. These methods do not consider the original features of the data and are difficult to describe the relationship between time-domain features and frequency-domain features. Therefore, this paper proposes a high-resolution seismic inversion method based on joint data-driven in the time-frequency domain. The method is based on the impedance and reflectivity samples from logging, using joint dictionary learning to obtain adaptive feature information of the reservoir, and using sparse coefficients to capture the intrinsic relationship between impedance and reflectivity. The optimization result of the inversion is achieved through the regularization term of the joint dictionary sparse representation. We have finally achieved an inversion method that combines constraints on time-domain features and frequency features. By testing the model data and field data, the method has higher resolution in the inversion results and good noise resistance.