Applied Computing and Geosciences最新文献

The aim of this work is to present a methodology for the reconstruction of missing fracture density within highly fractured intervals, which can represent preferential fluid flow pathways. The lack of record can be very common due to the intense presence of fractures, dissolution processes, or data acquisition issues. The superposition of numerous fractures makes the definition of fracture surfaces impossible, as a consequence, modeling such zones is challenging. In order to address this issue, the usage of direct sampling multiple-point statistics to perform gap filling in well logs is demonstrated as an alternative to other techniques. It reproduces data patterns and provides several models representing uncertainty. The method was tested in intervals from a highly fractured well, by removing previously known fracture density data, and simulating different scenarios with direct sampling. Simulation results are compared to the observed data using cross-validation and continuous rank probability score. The reference scenario training data set consists in one well and two variables: fracture density and fracture occurrence. A sensitivity analysis is carried out considering additional variables, additional wells, different intervals, resampling with extremes, and other gap filling techniques. The auxiliary variable plays an important role in pattern matching, but adding wells and logs increases the complexity of the method without improving pattern retrieval. Best results are obtained applying extreme values theory for stochastic process with the enrichment of the fracture density data at the tail region, followed by resampling of the new values. The enriched data is used for the gap filling resulting in lower continuous rank probability score, and the achievement of extreme fracture density values.

Advancements in high-resolution in-situ analyses have led to the extensive use of mineral diffusion zonings in determining petrologic and orogenic rates. The diffusion simulation, especially in multi-element systems, is numerically complex in practice. To streamline the application, we developed DIFFUSUP, a software featuring a graphic user interface (GUI) that facilitates the numerical simulation of diffusion with intricate initial conditions and thermal histories. DIFFUSUP alleviates the need for the knowledge of diffusion formulae, numerical solutions, and programming while still necessitating a fundamental understanding of problem setting, including the initial profiles and P-T-t evolution. DIFFUSUP's intuitive interface significantly simplifies the simulation setup process, making it particularly beneficial for reconnaissance research. It provides users with a balance between simplicity and flexibility, catering to a wide range of applications. These include support for multi-component systems, linear or isotropic spherical settings, variations in P-T-f_O2 conditions, initial profiles, and boundary conditions. The software is stand-alone, compatible with Windows and macOS, and can be adapted to diverse problem settings. The software, user's guide, and a few examples can be downloaded from www.diffusup.org.

We introduce GeaVR, an open-source package containing tools for geological-structural exploration and mapping in Immersive Virtual Reality (VR). GeaVR also makes it possible to carry out quantitative data collection on 3D realistic, referenced and scaled Virtual Reality scenarios. Making use of Immersive Virtual Reality technology through the Unity game engine, GeaVR works with commercially available VR equipment. This allows VR to be accessible to a broad audience, resulting in a revolutionary tool package for Earth Sciences. Users can explore various 3D datasets, spanning from freely available Digital Surface Models and Bathymetric data to ad-hoc 3D high-resolution models from photogrammetry processing. The user can navigate the 3D model in first person, walking or flying above the surrounding environment, mapping the main geological features such as points, lines and polygons, and collecting quantitative data using the provided field survey tools. Such data, including geographic coordinates, can be exported for further spatial analyses. Here we describe three different case studies aimed at showing the potential of our tools. GeaVR is revolutionary as it can be used worldwide, with no spatial limitations, both for geo-education and Earth Science popularization, as well as for research purposes. Secondly, it makes it possible to safely access dangerous areas, such as vertical cliffs or volcanic terrains, virtually from a computer screen or Virtual Reality headset. Furthermore, it can help to reduce carbon emissions by avoiding the use of flights and vehicles to conduct field trips.

In the field of geosciences, the integration of artificial intelligence is transitioning from perceptual intelligence to cognitive intelligence. The simultaneous utilization of knowledge and data in the geoscience domain is a universally addressed concern. In this paper, based on the interpretability of deep learning models for rock images, rock features such as structure, texture, mineral and macroscopic identification characteristics were selected to extract a rock identification subgraph from the petrographic knowledge graph and carry out rock type similarity reasoning. Comparative experiments were conducted on few-shot learning of rock images under the supervision of rock type similarity knowledge. The results of the few-shot learning comparisons demonstrate that the supervision of rock type similarity knowledge significantly enhances performance. Additionally, rock type similarity knowledge exhibits a marginal effect on improving few-shot learning performance. Given the absence of Chinese word embedding and large-scale Chinese pre-trained language models in the geological domain, graph embedding based on domain-specific knowledge graphs in geosciences can offer computable geoscience knowledge for research dually propelled by data and knowledge.

The field of geology has been the subject of a range of research efforts aiming to formalize geological domain knowledge, notably through geological domain ontologies. The main focus of existing geological ontologies primarily lies in describing static geological objects and their properties, paying less attention to the knowledge concerning geological processes and events. Meanwhile, the geological process modeling and simulation predominantly rely on quantitative numerical approaches that necessitate comprehensive and abundant data as input. However, many geological processes took place on a million-year time scale with insufficient data and non-direct observations. Given the inherent incompleteness of geological data, geologists still rely on qualitative reasoning to validate their interpretations. There is currently a dearth of applicable methods to facilitate qualitative reasoning and simulate geological processes based on domain knowledge.

We propose to model the effects of a geological process through an object-oriented program, while keeping an ontological representation of the situation at each instant. To combine the two models, we propose using semantically defined ‘process triggers.’ These process triggers are defined as part of the ontology, in accordance with the Basic Formal Ontology. They enable geologists to describe the precise moment when a geological process is triggered and initiated. On the computational program side, we employ the ‘Semantic Micro Object Language’ to embody the knowledge and rules provided by geologists, facilitating the simulation of geological processes. Through an evaluation experiment, our proposed approach demonstrates promising results within a reasonable timeframe. As proof of concept, we have applied our method to a real-world scenario of petroleum thermal maturation in Ekofisk Field and got a promising result. Our approach provides a formalism that allows a powerful code to interact with domain ontologies, which paves the path for future knowledge reasoning.

The increasing scale and diversity of seismic data, and the growing role of big data in seismology, has raised interest in methods to make data exploration more accessible. This paper presents the use of knowledge graphs (KGs) for representing seismic data and metadata to improve data exploration and analysis, focusing on usability, flexibility, and extensibility. Using constraints derived from domain knowledge in seismology, we define a semantic model of seismic station and event information used to construct the KGs. Our approach utilizes the capability of KGs to integrate data across many sources and diverse schema formats. We use schema-diverse, real-world seismic data to construct KGs with millions of nodes, and illustrate potential applications with three big-data examples. Our findings demonstrate the potential of KGs to enhance the efficiency and efficacy of seismological workflows in research and beyond, indicating a promising interdisciplinary future for this technology.

This paper presents an enhanced 3D heat map for exploratory data analysis (EDA) of open mineral data, addressing the challenges caused by rapidly evolving datasets and ensuring scientifically meaningful data exploration. The Mindat website, a crowd-sourced database of mineral species, provides a constantly updated open data source via its newly established application programming interface (API). To illustrate the potential usage of the API, we constructed an automatic workflow to retrieve and cleanse mineral data from it, thus feeding the 3D heat map with up-to-date records of mineral species. In the 3D heat map, we developed scientifically sound operations for data selection and visualization by incorporating knowledge from existing mineral classification systems and recent studies in mineralogy. The resulting 3D heat map has been shared as an online demo system, with the source code made open on GitHub. We hope this updated 3D heat map system will serve as a valuable resource for researchers, educators, and students in geosciences, demonstrating the potential for data-intensive research in mineralogy and broader geoscience disciplines.

We explore an attenuation and shape-based identification of euhedral pyrites in high-resolution X-ray Computed Tomography (XCT) data using deep neural networks. To deal with the scarcity of annotated data we generate a complementary training set of synthetic images. To investigate and address the domain gap between the synthetic and XCT data, several deep learning models, with and without domain adaption, are trained and compared. We find that a model trained on a small set of human annotations, while displaying over-fitting, can rival the human annotators. The unsupervised domain adaptation approaches are successful in bridging the domain gap, which significantly improves their performance. A domain-adapted model, trained on a dataset that fuses synthetic and real data, is the overall best-performing model. This highlights the possibility of using synthetic datasets for the application of deep learning in mineralogy.

Geochemical data are compositional in nature and are subject to the problems typically associated with data that are restricted to the real non-negative number space with constant-sum constraint, that is, the simplex. Geochemistry can be considered a proxy for mineralogy, comprised of atomically ordered structures that define the placement and abundance of elements in the mineral lattice structure. Based on the innovative contributions of John Aitchison, who introduced the logratio transformation into compositional data analysis, this contribution provides a systematic workflow for assessing geochemical data in a simple and efficient way, such that significant geochemical (mineralogical) processes can be recognized and validated. This workflow, called GeoCoDA and presented here in the form of a tutorial, enables the recognition of processes from which models can be constructed based on the associations of elements that reflect mineralogy. Both the original compositional values and their transformation to logratios are considered. These models can reflect rock-forming processes, metamorphism, alteration and ore mineralization. Moreover, machine learning methods, both unsupervised and supervised, applied to an optimized set of subcompositions of the data, provide a systematic, accurate, efficient and defensible approach to geochemical data analysis. The workflow is illustrated on lithogeochemical data from exploration of the Star kimberlite, consisting of a series of eruptions with five recognized phases.

Inland water bodies play a vital role at all scales in the terrestrial water balance and Earth’s climate variability. Thus, an inventory of inland waters is crucially important for hydrologic and ecological studies and management. Therefore, the main aim of this study was to develop a deep learning-based method for inventorying and mapping inland water bodies using the RGB band of high-resolution satellite imagery automatically and accurately.

The Sentinel-2 Harmonized dataset, together with ZABAGED-validated ground truth, was used as the main dataset for the model training step. Three different deep learning algorithms based on U-Net architecture were employed to segment inland waters, including a simple U-Net, Residual Attention U-Net, and VGG16-U-Net. All three algorithms were trained using a combination of Sentinel-2 visible bands (Red [B04; 665nm], Green [B03; 560nm], and Blue [B02; 490 nm]) at a 10-meter spatial resolution.

The Residual Attention U-Net achieved the highest computational cost due to the increased number of trainable parameters. The VGG16-U-Net had the shortest run time and the lowest number of trainable parameters, attributed to its architecture compared to the simple and Residual Attention U-Net architectures, respectively. As a result, the VGG16-U-Net provided the best segmentation results with a mean-IoU score of 0.9850, a slight improvement compared to other proposed U-Net-based architectures.

Although the accuracy of the model based on VGG16-U-Net does not make a difference from Residual Attention U-Net, the computation costs for training VGG16-U-Net were dramatically lower than Residual Attention U-Net.