Cookies
O website necessita de alguns cookies e outros recursos semelhantes para funcionar. Caso o permita, o INESC TEC irá utilizar cookies para recolher dados sobre as suas visitas, contribuindo, assim, para estatísticas agregadas que permitem melhorar o nosso serviço. Ver mais
Aceitar Rejeitar
  • Menu
Publicações

Publicações por Rui Lourenço Lopes

2016

An Overview of Evolutionary Computing for Interpretation in the Oil and Gas Industry

Autores
Lopes, RL; Jahromi, HN; Jorge, AM;

Publicação
Proceedings of the Ninth International C* Conference on Computer Science & Software Engineering, C3S2E '16, Porto, Portugal, July 20-22, 2016

Abstract
The Oil and Gas Exploration & Production (E&P) field deals with high-dimensional heterogeneous data, collected at different stages of the E&P activities from various sources. Over the years different soft-computing algorithms have been proposed for data-driven oil and gas applications. The most popular by far are Artificial Neural Networks, but there are applications of Fuzzy Logic systems, Support Vector Machines, and Evolutionary Algorithms (EAs) as well. This article provides an overview of the applications of EAs in the oil and gas E&P industry. The relevant literature is reviewed and categorised, showing an increasing interest amongst the geoscience community. © 2016 ACM.

2018

Assessment of predictive learning methods for the completion of gaps in well log data

Autores
Lopes, RL; Jorge, AM;

Publicação
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING

Abstract
Well logs are records of petro-physical data acquired along a borehole, providing direct information about what is in the subsurface. The data collected by logging wells can have significant economic consequences in oil and gas exploration, not only because it has a direct impact on the following decisions, but also due to the subsequent costs inherent to drilling wells, and the potential return of oil deposits. These logs frequently present gaps of varied sizes in the sensor recordings, that happen for diverse reasons. These gaps result in less information used by the interpreter to build the stratigraphic models, and consequently larger uncertainty regarding what will be encountered when the next well is drilled. The main goal of this work is to compare Gradient Tree Boosting, Random Forests, Artificial Neural Networks, and three algorithms of Linear Regression on the prediction of the gaps in well log data. Given the logs from a specific well, we use the intervals with complete information as the training data to learn a regression model of one of the sensors for that well. The algorithms are compared with each other using a few individual example wells with complete information, on which we build artificial gaps to cross validate the results. We show that the ensemble algorithms tend to perform significantly better, and that the results hold when addressing the different examples individually. Moreover, we performed a grid search over the ensembles parameters space, but did not find a statistically significant difference in any situation.

2013

Genetic Programming with Genetic Regulatory Networks

Autores
Lopes, RL; Costa, E;

Publicação
GECCO'13: PROCEEDINGS OF THE 2013 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE

Abstract
Evolutionary Algorithms (EA) approach differently from nature the genotype - phenotype relationship, and this view is a recurrent issue among researchers. Recently, some researchers have started exploring computationally the new comprehension of the multitude of regulatory mechanisms that are fundamental in both processes of inheritance and of development in natural systems, by trying to include those mechanisms in the EAs. One of the first successful proposals was the Artificial Regulatory Network (ARN) model. Soon after some variants of the ARN, including different improvements over the base model, were tested. In this paper, we combine two of those alternatives, demonstrating experimentally how the resulting model can deal with complex problems, including those that have multiple outputs. The efficacy and efficiency of this variant are tested experimentally using two benchmark problems that show how we can evolve a controller or an artificial artist.

2014

Developments on the Regulatory Network Computational Device

Autores
Lopes, R; Costa, E;

Publicação
International Journal of Natural Computing Research

Abstract

2013

GEARNet: Grammatical Evolution with Artificial Regulatory Networks

Autores
Lopes, RL; Costa, E;

Publicação
GECCO'13: PROCEEDINGS OF THE 2013 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE

Abstract
The Central Dogma of Biology states that genes made proteins that made us. This principle has been revised in order to incorporate the role played by a multitude of regulatory mechanisms that are fundamental in both the processes of inheritance and development. Evolutionary Computation algorithms are inspired by the theories of evolution and development, but most of the computational models proposed so far rely on a simple genotype to phenotype mapping. During the last years some researchers advocate the need to explore computationally the new biological understanding and have proposed different gene expression models to be incorporated in the algorithms. Two examples are the Artificial Regulatory Network (ARN) model, first proposed by Wolfgang Banzhaf, and the Grammatical Evolution (GE) model, introduced by Michael O'Neill and Conor Ryan. In this paper, we show how a modified version of the ARN can be combined with the GE approach, in the context of automatic program generation. More precisely, we rely on the ARN to control the gene expression process ending in an ordered set of proteins, and on the GE to build, guided by a grammar, a computational structure from that set. As a proof of concept we apply the hybrid model to two benchmark problems and show that it is effective in solving them.

2013

Evolving an Harmonic Number Generator with ReNCoDe

Autores
Lopes, RL; Costa, E;

Publicação
PROGRESS IN ARTIFICIAL INTELLIGENCE, EPIA 2013

Abstract
Evolutionary Algorithms (EA) are loosely inspired in the ideas of natural selection and genetics. Over the years some researchers have advocated the need of incorporating more ideas from biology into EAs, in particular with respect to the individuals' representation and the mapping from the genotype to the phenotype. One of the first successful proposals in that direction was the Artificial Regulatory Network (ARN) model. Soon after some variants of the ARN with increased capabilities were proposed, namely the Regulatory Network Computational Device (ReNCoDe). In this paper we further study ReNCoDe, testing the implications of some design choices of the underlying ARN model. A Genetic Programming community-approved symbolic regression benchmark (the harmonic number) is used to compare the performance of the different alternatives.

  • 1
  • 3