Search

This paper presents a novel machine learning framework that applies evolutionary ensembles of artificial agents to mineralogical analysis and classification. The approach is based on hybridization techniques that combine diverse machine learning algorithms, creating large and effective communities of agents. These progressively mute and improve through crossover, hybridization, and selection, addressing the challenges of mineral recognition and classification from thin section images. By combining multiple machine learning techniques, the ensemble of agents autonomously improves by evolving to adapt, enhancing its ability to identify mineral species and classify different types of alterations. We detail the method, provide examples using synthetic and real data, and explore the potential to improve mineralogical analysis workflows through this dynamic, self-improving system. [ABSTRACT FROM AUTHOR]

In this paper, we discuss the implementation of artificial self-awareness mechanisms and self-reflection abilities in deep neural networks. While the current limitations of research prevent achieving cognitive capabilities on par with natural biological entities, the incorporation of basic self-awareness and self-reflection mechanisms in deep learning architectures offers substantial advantages in tackling specific problems across various scientific fields, including geosciences. In the first section, we outline the foundational architecture of our deep learning approach termed Self-Aware Learning (SAL). The subsequent part of the paper highlights the practical benefits of this machine learning methodology through synthetic tests and applications addressed to automatic classification and image analysis of real petrological data sets. We show how Self-Aware Learning allows enhanced accuracy, reduced overfitting problems, and improved performances compared to other existing methods. [ABSTRACT FROM AUTHOR]

Recent studies have demonstrated the potential of machine learning methods for fast and accurate mineral classification based on microscope thin sections. Such methods can be extremely useful to support geoscientists during the phases of operational geology, especially when mineralogical and petrological data are fully integrated with other geological and geophysical information. In order to be effective, these methods require robust machine learning models trained on pre-labeled data. Furthermore, it is mandatory to optimize the hyper-parameters of the machine learning techniques in order to guarantee optimal classification accuracy and reliability. Nowadays, deep learning algorithms are widely applied for image analysis and automatic classification in a large range of Earth disciplines, including mineralogy, petrography, paleontology, well-log analysis, geophysical imaging, and so forth. The main reason for the recognized effectiveness of deep learning algorithms for image analysis is that they are able to quickly learn complex representations of images and patterns within them. Differently from traditional image-processing techniques based on handcrafted features, deep learning models automatically learn and extract features from the data, capturing, in almost real-time, complex relationships and patterns that are difficult to manually define. Many different types of deep learning models can be used for image analysis and classification, including fully connected deep neural networks (FCNNs), convolutional neural networks (CNNs or ConvNet), and residual networks (ResNets). In this paper, we compare some of these techniques and verify their effectiveness on the same dataset of mineralogical thin sections. We show that the different deep learning methods are all effective techniques in recognizing and classifying mineral images directly in the field, with ResNets outperforming the other techniques in terms of accuracy and precision. In addition, we compare the performance of deep learning techniques with different machine learning algorithms, including random forest, naive Bayes, adaptive boosting, support vector machine, and decision tree. Using quantitative performance indexes as well as confusion matrixes, we demonstrate that deep neural networks show generally better classification performances than the other approaches. Furthermore, we briefly discuss how to expand the same workflow to other types of images and geo-data, showing how this deep learning approach can be generalized to a multiscale/multipurpose methodology addressed to the analysis and automatic classification of multidisciplinary information. This article has tutorial purposes, too. For that reason, we will explain, with a didactical level of detail, all the key steps of the workflow. [ABSTRACT FROM AUTHOR]

Featured Application: In this work, Vector Autoregressive and Recurrent Neural Network algorithms are used to predict time-space evolution of a saline water plume in homogeneous and real aquifers. In this paper, an integrated workflow aimed at optimizing aquifer monitoring and management through time-lapse Electric Resistivity Tomography (TL-ERT) combined with a suite of predictive algorithms is discussed. First, the theoretical background of this approach is described. Then, the proposed approach is applied to real geoelectric datasets recorded through experiments at different spatial and temporal scales. These include a sequence of cross-hole resistivity surveys aimed at monitoring a tracer diffusion in a real aquifer as well as in a laboratory experimental set. Multiple predictive methods were applied to both datasets, including Vector Autoregressive (VAR) and Recurrent Neural Network (RNN) algorithms, over the entire sequence of ERT monitor surveys. In both field and lab experiments, the goal was to retrieve a determined number of "predicted" pseudo sections of apparent resistivity values. By inverting both real and predicted datasets, it is possible to define a dynamic model of time-space evolution of the water plume contaminated by a tracer injected into the aquifer system(s). This approach allowed for describing the complex fluid displacement over time conditioned by the hydraulic properties of the aquifer itself. [ABSTRACT FROM AUTHOR]

In this paper, we introduce a novel inversion methodology that combines the benefits offered by Reinforcement-Learning techniques with the advantages of the Epsilon-Greedy method for an expanded exploration of the model space. Among the various Reinforcement Learning approaches, we applied the set of algorithms included in the category of the Q-Learning methods. We show that the Temporal Difference algorithm offers an effective iterative approach that allows finding an optimal solution in geophysical inverse problems. Furthermore, the Epsilon-Greedy method properly coupled with the Reinforcement Learning workflow, allows expanding the exploration of the model-space, minimizing the misfit between observed and predicted responses and limiting the problem of local minima of the cost function. In order to prove the feasibility of our methodology, we tested it using synthetic geo-electric data and a seismic refraction data set available in the public domain. [ABSTRACT FROM AUTHOR]

ABSTRACT In this paper, we introduce a new method of geophysical data interpretation based on simultaneous analysis of images and sounds. The final objective is to expand the interpretation workflow through multimodal (visual-audio) perception of the same information. We show how seismic data can be effectively converted into standard formats commonly used in digital music. This conversion of geophysical data into the musical domain can be done by applying appropriate time-frequency transforms. Using real data, we demonstrate that the Stockwell transform provides a very accurate and reliable conversion. Once converted into musical files, geophysical datasets can be played and interpreted by using modern computer music tools, such as sequencers. This approach is complementary and not substitutive of interpretation methods based on imaging. It can be applied not only to seismic data but also to well logs and any type of geophysical time/depth series. To show the practical implications of our integrated visual-audio method of interpretation, we discuss an application to a real seismic dataset in correspondence of an important hydrocarbon discovery. [ABSTRACT FROM AUTHOR]

ABSTRACT Well-log data are processed in order to derive subsurface physical parameters, namely rock porosity, fluid saturations and permeability. This step involves the selection and inversion of experimental constitutive equations, which are the link between the rock parameters and geophysical measurements. In this paper we investigate the rock parameter observability and the reliability of well-log data processing. We present a visual analysis of the constitutive equations and of the inverse problem conditioning, when using independently, or jointly, log data from different domains. The existence of a common set of rock properties (cross-properties) that influence different measurements, makes it possible to reduce the ambiguities of the interpretation. We select a test case in a reservoir scenario and we explore how to determine rock porosity and fluid saturation from sonic, conductivity and density logs. We propose a Bayesian joint inversion procedure, which is able to control the conditioning problems, to efficiently take into account input data and model uncertainty and to provide a confidence interval for the solution. The inversion procedure is validated on a real well-log data set. [ABSTRACT FROM AUTHOR]

In this paper we show how marine controlled source electromagnetic data interpretation can be improved if the data are acquired with an expanded frequency spectrum. Especially in the case of targets located at a wide range of depths, both high- and low-frequency data can provide useful information for improving the risk analysis associated with different prospects with variable size and depth. We discuss an application to a real data set acquired in deep water offshore Nigeria using two values of fundamental frequency: 0.05 Hz and 0.25 Hz. Both frequencies, together with higher frequency harmonics, have been used for multi-frequency and multi-dimensional modelling and inversion with excellent results. At the end of the interpretation work, areas with different electric and magnetic anomalies were mapped and quantitatively interpreted in terms of resistivity distribution in the 3D space. Relatively high-frequency data (0.25 Hz and the first two harmonics) were useful for constraining the shallowest part of the resistivity models, including the presence of thin resistive layers, such as the gas sand recognized in correspondence of the well previously drilled in the NW portion of the block. Low-frequency data (0.05 Hz) were useful for constraining the deepest portion of the models (from 2 km to 4 km below sea floor) and for characterizing the resistivity of the background. From an exploration point of view, the whole workflow based on multi-frequency data analysis of this electromagnetic data set was very useful for further de-risking the different prospects previously individuated in the area using seismic information. [ABSTRACT FROM AUTHOR]