The Tikhonov regularization parameter is a key parameter controlling the smoothness degree and oscillations of a regularized unknown solution. Usual methods to determine a proper parameter (L-curve or the discrepancy principle, for example) are not readily applicable to the evaluation of regularized derivatives, since this formulation does not make explicit a set of model parameters that are ne…
Recently, workflow management platforms are gaining more attention in the artificial intelligence (AI) community. Traditionally, researchers self-managed their workflows in a manual and tedious way that heavily relies on their memory. Due to the complexity and unpredictability of AI models, they often struggled to track and manage all the data, steps, and history of the workflow. AI workflows a…
Accurately modeling highly heterogenous aquifers is one of the big challenges in hydrogeology. There is a pressing need to develop new methods that transform high-resolution data into hydrogeological parameters representative of such aquifers. We use random forest-based machine learning to predict the distribution of hydrostratigraphic units and hydraulic conductivity (K) at a regional scale. W…
We propose a workflow for updating 3D geological meshed models to test different layering scenarios and to assess their impact on the simulation of injection. This workflow operates on a tetrahedral mesh that encodes rock unit information as well as rock physical properties. The alternative layering meshes are built by modifying the input mesh and inserting a new horizon defined by a scalar …
Geological modeling commonly results in a single prescribed geometric representation of the subsurface with no consideration of uncertainties. Accounting for uncertainties is of particular importance in the triangle zone at the leading edge of deformation of the foreland fold-thrust belt of the European Alps, the Subalpine Molasse. Here, interpretations of the complex structures are limited to …
Machine learning (ML) has been a technique employed to build data-driven models that can map the relationship between the input and output data provided. ML-based data-driven models offer an alternative path to solving optimization problems, which are conventionally resolved by applying simulation models. Higher computational cost is induced if the simulation model is computationally intensive.…
Domains define the boundaries of mineralisation zones, within which the grade distribution of the target minerals can be quantified via an established mineral resource estimation procedure. Available domain modelling techniques include manual interpretation, implicit modelling and advanced geostatistical approaches. In mining applications, the most commonly used method is manual domaining, whic…
Spatial domains defining either geological models or mineral estimation envelopes are among the few components of the mining life cycle that are not quantitatively assessed to communicate uncertainty or error in mineral resource projects. Recent work has investigated the use of Bayesian approximation methods to assess interpretation uncertainty of the classification of drill hole intercepts to …
During drilling, to maximize future expected production of hydrocarbon resources, the experts commonly adjust the trajectory (geosteer) in response to new insights obtained through real-time measurements. Geosteering workflows are increasingly based on the quantification of subsurface uncertainties during real-time operations. As a consequence, operational decision-making is becoming both bette…
The construction of conceptual geological models is an essential task in petroleum exploration, especially during the early stages of investment, when evidence about the subsurface is limited. In this task, geoscientists recreate the most likely geological scenarios that led to potential accumulation of reserves in a target block, based on past experience, historical analogues, and interpreted …