## About

116

Publications

23,468

Reads

**How we measure 'reads'**

A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more

727

Citations

Introduction

Mauro Roisenberg currently works at the Departamento de Informática e Estatística, Federal University of Santa Catarina. Mauro does research in Artificial Neural Network, Artificial Intelligence and Computing in Mathematics, Natural Science, Engineering and Medicine. Their current project is 'Research and Development of Efficient and Scalable Methods for Uncertainty Estimation in Petrophysical Modeling of Reservoir Properties'.

## Publications

Publications (116)

Seismic facies inversion is an important process in the oil and gas industry to estimate subsurface geological facies or rock types based on seismic data. Recently, the Ensemble Smoother with Multi Data Assimilation (ES-MDA) has shown great success in solving complex inverse problems by generating an ensemble of solutions of the model variables for...

History matching is applied to update reservoir parameters, such as the porosity and permeability of the subsurface rocks, according to new indirect observations. Local fluid production and pressure measurements in the drilled wells are the commonly dynamic observations used in the process. Another dynamic reservoir observation is the time-lapse se...

The determination of the shape and extent of strata is one of the most important steps in the classification of architectural elements in an outcrop. However, mapping and accessing outcrops with broad lateral and vertical continuity can be difficult due to their geographic position. In this work, UAV-captured outcrop images are used to apply seedin...

Neural networks have been applied to seismic inversion problems since the 1990s. More recently, many publications have reported the use of Deep Learning (DL) neural networks capable of performing seismic inversion with promising results. However, when solving a seismic inversion problem with DL, each author uses, in addition to different DL models,...

I am honored to be invited, along with Professor Wagner Lupinacci, to be Guest Editor of Energies MDPI Special Issue on "Advances in Computational Intelligence and Machine Learning Techniques for Exploration and Production in the Oil and Gas Industry". The deadline for paper submission is November 30, 2022.

Generally, in inverse modeling in geoscience, we aim to predict the values of a group of model variables from a set of observed data, based on physical relations between model parameters and data. Specifically, in seismic inversion, the goal is to predict rock and fluid properties in the subsurface from seismic and well-log data. The relation betwe...

Determination of lithofacies is one of the most important steps for reservoir characterization. Well log curves are not always sufficient to determine lithology as some times the signals are similar for different lithologies. We believe that the sequence of sedimentary patterns that follows the general geologic rules can be essential to help this d...

The aim of this study is to investigate the regional hydrogeochemical spatialization and controls of the Serra Geral Aquifer System (SGAS), a transboundary fractured aquifer, across the southern region of Brazil. An extensive dataset of 1564 groundwater wells represented by 16 attributes was analyzed to identify spatial patterns and groups with sim...

Several applications in geoscience require the generation of multiple realizations of random fields of physical properties to mimic their spatial distribution and quantify the model uncertainty. Some modeling problems present complex multivariate distributions with heteroscedasticity and non-linear relations among the variables. We propose a new al...

Several methodologies can be found in the literature for inversion of partial angle stack seismic data, including deterministic and stochastic frameworks. However, most methods require a low frequency model (LFM) of each property as an input. These models are usually obtained by the interpolation of the wells along a stratigraphic grid based on the...

One of the main objectives in the reservoir characterization is estimating the rock properties based on seismic measurements. We propose a stochastic sampling method for the joint prediction of facies and petrophysical properties, assuming a non-parametric mixture prior distribution and a non-linear forward model.The proposed methodology is based o...

Convolutional Neural Networks are extensively used in computer vision applications. Many convolutional models became famous after being widely adopted in a variety of computer vision tasks because o their high accuracy and great generality. Trough Transfer Learning, pre-trained versions of these models can be applied to a large number of different...

(CODE AVAIBILITY: https://github.com/leandrofgr/GaussianMixtureMCMC)
We have developed a Markov chain Monte Carlo (MCMC) method for joint inversion of seismic data for the prediction of facies and elastic properties. The solution of the inverse problem is defined by the Bayesian posterior distribution of the properties of interest. The prior distr...

In this paper, we propose a deep convolutional gen-erative adversarial network model to reconstruct the petroleum reservoir connectivity patterns. In the petroleum exploration industry, the critical issue is determining the internal reservoir structure and connectivity, aiming to find a flow channel for placing the injection and the production well...

Domain-specific methods for deblurring particular sorts of objects have gained increasing attention due to the ineffectiveness of generic methods. We present a simple and effective convolutional neural network that deblurs postinversion acoustic impedance images. The architecture of our model consists of a convolutional layer that highlights edges...

The joint inversion of seismic data for elastic and petrophysical properties is an inverse problem with a non-unique solution. There are several factors that impact the accuracy of the results, such as the statistical rock-physics relations and observation errors. We present a general methodology to incorporate a linearized rock-physics model
in a...

Accuracy and interpretability are contradictory objectives that conflict in all machine learning techniques and achieving a satisfactory balance between these two criteria is a major challenge. The objective is not only to maximize interpretability, but also to guarantee a high degree of accuracy. This challenge is even greater when it is considere...

We propose a Bayesian approach for seismic inversion to estimate acoustic impedance, porosity and lithofacies within the reservoir conditioned to post-stack seismic and well data. The link between elastic and petrophysical properties is given by a joint prior distribution for the logarithm of impedance and porosity, based on a rock-physics model. T...

Seismic inversion is an important technique for reservoir modeling and characterization due to its potential in inferring the spatial distribution of the subsurface elastic properties of interest. Two of the most common seismic inversion methodologies within the oil and gas industry are iterative geostatistical seismic inversion and Bayesian linear...

Geostatistical simulations are widely used to generate random field realizations that mimic the subsurface heterogeneities, in order to reproduce the expected spatial variability related to geological stratigraphy and deposition. There are several techniques that can be used to generate multiple realizations of the stochastic models, the most popul...

In this paper, we present a prediction model developed to identify particles size of ice crystals in clouds. The proposed model combines a Feed Forward Multi-Layer Perceptron neural network with Bayesian regularization backpropagation and other machine learning techniques for feature reduction with Principal Component Analysis and rotation invarian...

When an artificial neural network is used to determine the value of a physical quantity its result is usually presented without an uncertainty. This is due to the difficulty in determining the uncertainties related to the neural model. However, the result of a measurement can be considered valid only with its respective measurement uncertainty. The...

Modeling uncertainty in seismic inversion problems is a topic of interest for both the oil and gas industry and the academia. Although recent advances in methodologies for sampling the posterior space of the petro-elastic properties of interest, integrating the a priori knowledge, they still have high computational cost. Global Stochastic Inversion...

Biological inspiration of animal behavior, nervous systems and natural evolution mechanisms, allow the construction of artificial Autonomous Agents (AAs) that, as animals, could work very well in the real world. This paper uses this inspiration to analyze and simulate evolutionary mechanisms capable of creating and developing different neural netwo...

This paper proposes a hybrid neuro-evolutive algorithm (NEA) that uses a compact indirect encoding scheme (IES) for representing its genotypes (a set of ten production rules of a Lindenmayer System with memory), moreover has the ability to reuse the genotypes and automatically build modular, hierarchical and recurrent neural networks. A genetic alg...

Bayesian networks are probabilistic graphical models capable of modeling statistical uncertainty and are widely applied in many classification problems. Specifically, Naive Bayesian networks are largely used due to their simple, naive structure, while still producing precise results. Fuzzy systems, on the other hand, are a well known technique capa...

The speed of information publishing in WWW is unprecedented. The individuals and organizations struggle to be up to date and find relevant knowledge from a tsunami of news, videos, posts, and comments. In the other hand, these contents (mostly bound to HTML pages) are unstructured and not explicitly classified. In this context, machine-learning tec...

The aim of this paper is to present a biologically inspired Neuro Evolutive Algorithm (NEA) able to generate modular, hierarchical and recurrent neural structures as those often found in the nervous system of live beings, and that enable them to solve intricate survival problems. In our approach we consider that a nervous system design and organiza...

In this letter, we show how a seismic inversion method based on a Bayesian framework can be applied on poststack seismic data to estimate the wavelet, the seismic noise level, and the subsurface acoustic impedance. We propose a different linearized forward model and discuss in detail how some stochastic quantities are defined in a geophysical inter...

This paper presents a novel neuro-fuzzy inference system, called RBFuzzy, capable of knowledge extraction and generation of highly interpretable Mamdani-type fuzzy rules. RBFuzzy is a four layer neuro-fuzzy inference system that takes advantage of the functional behavior of Radial Basis Function (RBF) neurons and their relationship with fuzzy infer...

Multimodal optimization attempts to find multiple global and local optima of a function. Finding a set of optimal solutions is particularly important for practical problems. However, this kind of problem requires optimization techniques that demand a high computational cost and a large amount of parameters to be adjusted. These difficulties increas...

This letter presents ACOR-V , a new computationally efficient Ant Colony Optimization (ACO) based algorithm, tailored for continuous domain problems. The ACOR-V algorithm is well suited for application in seismic inversion problems owing to its intrinsic features, such as heuristics in generating the initial solution population and its facility to...

This article presents an on-going research that addresses the optimization of the cost of drilling wells in environments of high complexity and risk such as those related to the pre-salt region offshore Brazil. The minimization of these costs is directly related to the maximization of ROP (Rate of Penetration). The metric cost, i.e., the cost per m...

This chapter proposes an authentication methodology that is both inexpensive and non-intrusive and authenticates users continuously while using a computer keyboard. This proposed methodology uses neural network committee machines. The committee consists of several independent neural networks trained to recognize a behavioral biometric characteristi...

The aim of this study is to simulate a network traffic ana-lyzer that is part of an Intrusion Detection System -IDS, the main focus of research is data mining and for this type of application the steps that precede the data mining : data preparation (possibly involving clean-ing data, data transformations, selecting subsets of records, data nor-mal...

The use of confidence estimation techniques on neural networks outputs plays an important role when these mathematical models are applied in many practical applications. In general, the method to provide confidence estimation is dependent on the neural network architecture, but traditionally, most popular prediction interval (PI) estimation methods...

Ant Colony Optimization (ACO) is an optimization metaheuristic based on the foraging behavior of ants. This metaheuristic was originally proposed to find good solutions to discrete combinatorial problems. Many extensions of the ACO heuristic for continuous domain have been proposed, but even those that claim close similarity with classical (discret...

The main contribution of this paper is to propose a hybrid architecture which efficiently integrates an adaptive topological map learning with reactive navigation for an autonomous robot. The reactive control is implemented by an artificial neural networks arrangement which allows the learning of perception-action mappings. In the deliberative leve...

In this paper we introduce a biologically plausi-ble methodology capable to automatically generate Artificial Neural Networks (ANNs) with optimum number of neurons and adequate connection topology. In order to do this, three biological metaphors were used: Genetic Algorithms (GA), Lindenmayer Systems (L-Systems) and ANNs. The methodology tries to m...

This chapter proposes an authentication methodology that is both inexpensive and non-intrusive and authenticates users continuously while using a computer keyboard. This proposed methodology uses neural network committee machines. The committee consists of several independent neural networks trained to recognize a behavioral biometric characteristi...

Artificial Neural Networks have been used for function approximation and pattern recognition in a variety of domains. However,
due to its empirical nature, it is difficult to derive an estimate of neural network’s accuracy. There are in the literature
a number of proposed methods to calculate a measure of confidence to the output of neural networks...

Dentre as principais dificuldades encontradas para a construção de sistemas multiagentes em que existe a disponibilidade de um sistema de visão local, como é o caso de algumas categorias de futebol de robôs, destacam-se: necessidade de resposta em tempo real para identificação dos objetos em cena, conhecimento do ambiente, distribuição das competên...

The use of confidence estimation techniques on neural networks outputs plays an important role when these mathematical models are applied in many practical applications. However, few of these techniques have the capability to deal with variable noise rate in the predictions over the domain, making the assumptions about the reliability of these outp...

Petroleum exploration is an economical activity where many billions of dollars are invested every year. Despite these enormous investments, it is still considered a classical example of decision-making under uncertainty. In this paper, a new hybrid fuzzy-probabilistic methodology is proposed and the implementation of a software tool for assessing t...

Dentre as principais dificuldades encontradas para a construção de sistemas multiagentes em que existe a disponibilidade de um sistema de visão local, como é o caso de algumas categorias de futebol de robôs, destacam-se: necessidade de resposta em tempo realpara identificação dos objetos em cena, conhecimento do ambiente, distribuição das competênc...

This paper considers the use of notions about autonomous agents in the conception of models of Artificial Life to simulate various population dynamics in natural and artificial environments. It materializes the characteristic behaviors of the agents in populations by means of the Subsumption architecture. A first model was programmed aiming to simu...

Several issues still need to be unraveled in the development of multiagent systems equipped with global vision, as in robot soccer leagues. Here, we underscore three of them (1) real-time constraints on recognition of scene objects; (2) acquisition of environment knowledge; and (3) distribution and allocation of control competencies shared between...

This paper describes a new Evolutionary Control System (ECS) able to control a population of mobile robots. The system has two main modules: the first one, called EMSS (Execution, Management and Supervision System), is the system responsible for managing all the evolutionary process that takes place in an embedded fashion in each robot. The second...