Computers & Geosciences最新文献

Geophysical logging is a geo-scientific instrument that detects information such as electric, acoustic, and radioactive properties of a well. Its data plays a vital role in interpreting subsurface geology. However, since logging data is an indirect reflection of rocks, it requires the construction of a logging interpretation model in combination with core samples. Obtaining and analysing all core samples in a well is not practical due to their enormous cost, leading to the problem of scarce core sample labels. This problem can be addressed using semi-supervised learning. Existing studies on lithology identification using logging data mostly utilize graph-based semi-supervised learning, which requires known features to establish a graph Laplacian matrix. Therefore, these methods often use logging values at certain depths to construct feature vectors and cannot learn the shape information of logging curves. In this paper, we propose a semi-supervised learning method with feature learning capability based on semi-supervised generative adversarial network (SSGAN) to learn the shape information of logging curves while utilizing unlabelled logging curves. Additionally, considering the problem of insufficient use of labels when dividing a validation set in extremely scarce-label situations, we propose a strategy of weighted averaging of three sub-models, which effectively improves model performance. We verify the effectiveness of our proposed method on five wells and demonstrate the mechanism of semi-supervised learning using adversarial learning through extensive visualization methods.

In this study, we proposed a general workflow that aims to enhance the ML-based geothermobarometer modelling. Our workflow focuses on three key areas. Firstly, we developed a robust pre-processing pipeline that addresses data imbalance, feature engineering, and data augmentation. Secondly, we assessed modelling errors using a Monte Carlo approach to quantify the impact of analytical uncertainties on the final pressure and temperature estimates. Thirdly, we implemented a robust strategy to validate and test the ML models to avoid over- and under-fitting issues while correcting biases associated with the application of specific ML models (i.e., tree-based ensembles).

To facilitate the use of our workflow, we have developed a web app (https://bit.ly/ml-pt-web) and a Python module (https://bit.ly/ml-pt-py). The robustness of this strategy has been tested on two calibrations: clinopyroxene (cpx) and clinopyroxene-liquid (cpx-liq). Our results show a significant reduction in errors compared to the baseline model, as well as good generalization ability on an independent external dataset. The Root Mean Squared Errors are 57 °C and 2.5 kbar for the cpx calibration, and 36 °C and 2.1 kbar for the cpx-liq calibration. Finally, our models show improved outcomes on the external dataset compared to existing ML and classical cpx and cpx-liq thermobarometers.

The present study proposes a double-branch classification network, DPNet (Double Path Net), for the classification and identification of microseismic and blasting signals based on multimodal feature extraction. The vibration signals’ one-dimensional spectrogram and two-dimensional wavelet time–frequency graph are inputted into the double branch network. Subsequently, convolutional neural networks and ResNet are employed to extract the one-dimensional frequency features and two-dimensional time–frequency features of the vibration signals, respectively. Experimental results demonstrate that our proposed method achieves outstanding classification performance with an accuracy of 97.34% for microseismic signals and blasting signals. This research not only provides innovative solutions to practical problems but also introduces a novel idea of multimodal feature extraction at a theoretical level. By successfully applying it to efficiently classify complex signals in mining engineering, we offer a feasible solution that holds promising prospects for practical applications in this field.

Numerical modeling of electromagnetic (EM) fields in a conductive marine environment is crucial for marine EM data interpretation. During marine controlled-source electromagnetic (MCSEM) surveys, a variety of transmitter locations are used to introduce electric currents. The resulting electric and magnetic fields are then concurrently logged by a network of receivers. The forward simulation of MCSEM data for a subsea structure whose electrical properties vary in all three dimensions is computationally intensive. We demonstrate how such computations may be substantially accelerated by adapting algorithms to operate efficiently on modern GPUs with many core architectures. The algorithm we present features a hybrid MPI-CUDA programming model suitable for multi-GPU computers and consists of three levels of parallelism. We design the optimal kernels for different components to minimize redundant memory accesses. We have tested the algorithm on NVIDIA Kepler architecture and achieved up to 105 × speedup compared with the serial code version. We further showcased the algorithm's performance advantages through its application to a realistic marine model featuring complex geological structures. Our algorithm's significant efficiency increase opens the possibility of 3D MCSEM data interpretation based on probabilistic or machine learning approaches, which require tens of thousands of forward simulations for every survey.

Mine induced seismic events are a major safety concern in mining and require careful monitoring and management to reduce their effects. Therefore, an essential step in assessing seismic and rock burst hazards is the analysis of mine seismicity. Recently, deep neural networks have been used to automatically determine seismic wave arrival times, surpassing human performance and allowing their use in seismic data analysis such as seismic event location and seismic energy calculation. In order to properly automate the rockburst and seismic hazard assessment deep neural network phase picker and a spatio-temporal clustering method were utilized. Seismic and rockburst hazards were statistically quantified using two-way contingency tables for two categorical variables: seismic energy level of mine tremors and number of clusters. Correlations between several spatio-temporal clusters and a statistical association between two categorical variables: seismic energy level and cluster number indicate an increase of seismic hazard in the Marcel hard coal mine in Poland. A new automated tool has been elaborated to automatically identify high-stress areas in mines in the form of spatio-temporal clusters.

Some target seismic signals in the earthquake data can be very weak compared with interfering phases, and are thus difficult to detect, which further hinders the effective usage of these weak phases for subsequent high-resolution imaging of earth interiors. The strong ambient noise makes this situation even more troublesome since the weak signals can be mostly buried in the noise. Here, we present an open-source package for uncovering the weak phases from global seismograms. We adopt a two-step scheme to reconstruct and denoise array data. The first step is weighted average interpolation which puts the data into irregular grids. The second step adopts the weighted projection-onto-convex sets based on damped rank-reduction to further interpolate and denoise for the binned data. Taking the complexity of the weak signal into consideration, we adopt the automatic strategy to select an appropriate rank in different localized windows. We conduct several synthetic tests to carefully investigate the performance regarding effectiveness, robustness, and efficiency, and compare the algorithm with the frequency–wavenumber-domain projection onto convex sets method that is already used in the global seismology literature. Finally, the proposed framework is validated via a recorded array data set of the 1995 May 5 Philippines earthquake.

Single-sided magnetic resonance (SSMR) offers advantages of portability and noninvasive measurement for water detection, with significant potential applications in groundwater exploration, petroleum well logging, and soil moisture monitoring. However, the inherent highly inhomogeneous static magnetic field and radiofrequency (RF) field in SSMR necessitate the utilization of the Carr–Purcell–Meiboom–Gill (CPMG) sequence measurement scheme. To accelerate forward modeling during pulse excitation, we introduce a Geometric Analysis Method (GAM) and assess $T_2$ error using its primary parameters. The GAM involves applying spatial geometric rotations on the magnetization vector, leading to an analytical solution to the Bloch equation that disregards relaxation effects. Compared with the rotation matrix (RM) method, the GAM demonstrates high accuracy and reduces computational time by approximately 20.9%. By analyzing the primary parameters governing the magnetization vector in the analytical formula, we evaluated their impact on the transverse relaxation time ($T_2$) obtained through fitting the SE signal. Ultimately, the forward modeling results of the CPMG sequence within the region of interest (ROI) of a single-sided Halbach magnet array are validated. The $T_2$ fitting error increases as the primary parameters deviate from the ideal values, highlighting their significant role in the $T_2$ fitting results. This study provides a theoretical foundation for optimizing the design of SSMR magnets and RF coils.

The accurate taxonomic identification of fusulinid fossils holds significant scientific value in palaeontology, paleoecology, and palaeogeography. However, imbalanced image samples lead to the model preferring to learn features from categories with many samples while ignoring fewer sample categories, greatly reducing the prediction accuracy of fusulinid fossil identification. Moreover, the textual description of fusulinid fossils contains rich feature information. We collected and created an order fusulinid multimodal (OFM) dataset for research. We proposed a transformer-based multimodal integration framework (TMIF) using deep learning for fusulinid fossil identification. Compared to traditional neural networks, the transformer can create global dependencies between features at different locations. TMIF incorporates image and text branches dedicated to extracting features for both modalities, and a pivotal cross-modal integration module that allows visual features to learn textual semantic features sufficiently to obtain a more comprehensive feature representation. Experimental evaluation using the OFM dataset shows that TMIF achieves a prediction accuracy of 81.7%, which is a 2.8% improvement over the only image-based method. Further comparative analyses across multiple networks affirm that the TMIF performs optimally in addressing the taxonomic identification of fusulinid fossils with imbalanced samples.

A new CNN based approach supported by semantic segmentation, was proposed. This approach is frequently used to carry out regional-scale studies. The core of our method revolves around a CNN model, based on the famous U-Net architecture. Its purpose is to identify different classes of pixels on satellite images and later to automatically detect the coastline. The recently launched Coast Train dataset was used to train the CNN model. Traditional coastline detection was improved (“water/land” segmentation) by means of two new aspects the use of the Sobel-edge loss function and the segmentation of the satellite images into several categories like built-up areas, vegetation and land besides beach/sand and water classes. The approach used ensures a more precise coastline extraction, distinguishing water pixels from all other categories. Our model adeptly identifies features, such as cliff vegetation or coastal roads, that some models might overlook. In this way, coastline localization and its drawing for regional scale study, have minor uncertainties. The performance of the CNN-based method, achieving 85% accuracy and 80% IoU (Intersection over Union) in the segmentation process. The ability of the model to extract the coastline was validated on a Sicilian case study, notably the San Leone beach (Agrigento). The model's results align closely with the ground truth, moreover, its reliability was further confirmed when it was tested on other Sicilian coastal regions.

Beyond robustness, the model offers a promising avenue for enhanced coastal analysis potentially applicable to coastal planning and management.

Seismology has witnessed significant advancements in recent years with the application of deep learning methods to address a broad range of problems. These techniques have demonstrated their remarkable ability to effectively extract statistical properties from extensive datasets, surpassing the capabilities of traditional approaches to an extent. In this study, we present SAIPy, an open-source Python package specifically developed for fast seismic data processing by implementing deep learning. SAIPy offers solutions for multiple seismological tasks, including earthquake signal detection, seismic phase picking, first motion polarity identification and magnitude estimation. We introduce upgraded versions of previously published models such as CREIME_RT capable of identifying earthquakes with an accuracy above 99.8% and a root mean squared error of 0.38 unit in magnitude estimation. These upgraded models outperform state-of-the-art approaches like the Vision Transformer network. SAIPy provides an API that simplifies the integration of these advanced models, including CREIME_RT, DynaPicker_v2, and PolarCAP, along with benchmark datasets. It also, to the best of our knowledge, introduces the first fully automated deep learning based pipeline to process continuous waveforms. The package has the potential to be used for real-time earthquake monitoring to enable timely actions to mitigate the impact of seismic events. Ongoing development efforts aim to further enhance SAIPy’s performance and incorporate additional features that enhance exploration efforts, and it also would be interesting to approach the retraining of the whole package as a multi-task learning problem. A detailed description of all functions is available in a supplementary document.