1
|
Application of Machine Learning and Artificial Intelligence in Proxy Modeling for Fluid Flow in Porous Media. FLUIDS 2019. [DOI: 10.3390/fluids4030126] [Citation(s) in RCA: 34] [Impact Index Per Article: 6.8] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
Reservoir simulation models are the major tools for studying fluid flow behavior in hydrocarbon reservoirs. These models are constructed based on geological models, which are developed by integrating data from geology, geophysics, and petro-physics. As the complexity of a reservoir simulation model increases, so does the computation time. Therefore, to perform any comprehensive study which involves thousands of simulation runs, a very long period of time is required. Several efforts have been made to develop proxy models that can be used as a substitute for complex reservoir simulation models. These proxy models aim at generating the outputs of the numerical fluid flow models in a very short period of time. This research is focused on developing a proxy fluid flow model using artificial intelligence and machine learning techniques. In this work, the proxy model is developed for a real case CO2 sequestration project in which the objective is to evaluate the dynamic reservoir parameters (pressure, saturation, and CO2 mole fraction) under various CO2 injection scenarios. The data-driven model that is developed is able to generate pressure, saturation, and CO2 mole fraction throughout the reservoir with significantly less computational effort and considerably shorter period of time compared to the numerical reservoir simulation model.
Collapse
|
2
|
Benchmarking the efficiencies of Indonesia’s municipal water utilities using Stackelberg data envelopment analysis. BENCHMARKING-AN INTERNATIONAL JOURNAL 2015. [DOI: 10.1108/bij-01-2014-0009] [Citation(s) in RCA: 13] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
Purpose
– The purpose of this paper is to present a yardstick efficiency comparison of 269 Indonesian municipal water utilities (MWUs) and measures the impact of exogenous environmental variables on efficiency scores.
Design/methodology/approach
– Two-stage Stackelberg leader-follower data envelopment analysis (DEA) and artificial neural networks (ANN) were employed.
Findings
– Given that serviceability was treated as the leader and profitability as the follower, the first and second stage DEA scores were 55 and 32 percent (0 percent = totally inefficient, 100 percent = perfectly efficient), respectively. This indicates sizeable opportunities for improvement, with 39 percent of the total sample facing serious problems in both first- and second-stage efficiencies. When profitability instead leads serviceability, this results in more decreased efficiency. The size of the population served was the most important exogenous environmental variable affecting DEA efficiency scores in both the first and second stages.
Research limitations/implications
– The present study was limited by the overly restrictive assumption that all MWUs operate at a constant-return-to-scale.
Practical implications
– These research findings will enable better management of the MWUs in question, allowing their current level of performance to be objectively compared with that of their peers, both in terms of scale and area of operation. These findings will also help the government prioritize assistance measures for MWUs that are suffering from acute performance gaps, and to devise a strategic national plan to revitalize Indonesia’s water sector.
Originality/value
– This paper enriches the body of knowledge by filling in knowledge gaps relating to benchmarking in Indonesia’s water industry, as well as in the application of ensemble two-stage DEA and ANN, which are still rare in the literature.
Collapse
|