This work proposes a method to determine oil, gas and water presence in reservoirs directly from commonly measured well log parameters, such as resistivity, gamma-ray, density and neutron, by using Artificial Neural Networks (ANN). The wells from the oil field approached in this case study require frequent workover jobs to put their multiple zones in production one after another as soon as they become depleted. Once this oil field is segmented in hundreds of hydraulically isolated reservoirs containing small oil volumes, a procedure for identification of the fluids contained in the reservoirs crossed by a well can be of great value to make routine decisions (regarding evaluations and perforations) faster and more accurate. The work started based on the observation that zones with different fluids (or the absence of fluids) show characteristics sufficiently particular in the cited logs that make possible their classification by an artificial intelligence algorithm. The ANN approach is chosen considering its capability of working with a non-linear problem in which some uncertainties are also present, based on algorithms with relatively simple implementation. A characteristic of this method is that the ANN can be trained with data points of a specific zone, block or area, which means adjusting itself to this specific data set, learning its particularities, what leads to more accurate results when used to classify other zones with similar characteristics. The method's applicability increases in mature fields presenting a large number of logged wells with perforated and tested zones allowing validation of the information used in the supervised learning of the ANN. For the training and validation of a Multi Layer Perceptron (MLP) Neural Network, 160 data points were used with depth information and the corresponding Gamma Ray, Resistivity, Density and Neutron log values, along with fluid identifications based on the results of logs and perforations. These data points came from two wells of Alagoas Basin, Brazil. In the tests performed in this work, the ANN presented a generalization capability after extracting information from the training data, leading to a good confidence in the classification results for a testing data set.
The use of fingerprints for biometry presents some interesting technological challenges, especially when large populations are involved. This paper describes how a high-quality database of fingerprint minutiae can be created. First research was carried out to establish which algorithms are state of the art. Certain techniques are then selected, and improvements are proposed for some. The results were analyzed aiming to evaluate the quality of the biometric data base generated. The information in the database so obtained is quite good (approximately 92% of the detected minutiae are real), but further work can doubtless improve the quality of the results.
Real Estate Investment Trusts represent a growing market in the national scene, offering many opportunities for investors. However, they are risky assets, therefore it is important to identify and quantify this risk, and adjust the desired return. This work aims to develop a methodology that uses statistical analysis to compare risk and return of real estate trusts with other applications available in the market, like applications linked to CDI, IGP-M, IBOV, INCC and IMOB. Furthermore, combinations are performed simulating different possible portfolios, based on nineteen real estate trusts, offering different levels of return and risk, which can be adjusted according to the investor's profile. Using the Sharpe Ratio to create a rank, the top five portfolios are then exposed. The optimal portfolio has a expected return of 1.90 % per month with a deviation of 3.73 %, being an intermediate investment between fixed income and the stock market, although it has a higher expected return compared to the other indexes. Finally, it is verified by simple linear regression that neither future behavior of the optimal portfolio, nor assets that compose it, can be estimated based on IMOB's behavior, with 95 % of reliability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.