A transparent Open-Box learning network provides insight to complex systems and a performance benchmark for more-opaque machine learning algorithms
Journal Title: Advances in Geo-Energy Research - Year 2018, Vol 2, Issue 2
Abstract
It is now commonplace to deploy neural networks and machine-learning algorithms to provide predictions derived from complex systems with multiple underlying variables. This is particularly useful where direct measurements for the key variables are limited in number and/or difficult to obtain. There are many petroleum systems that fit this description. Whereas artificial intelligence algorithms offer effective solutions to predicting these difficult-to-measure dependent variables they often fail to provide insight to the underlying systems and the relationships between the variables used to derive their predictions are obscure. To the user such systems often represent “black boxe”. The novel transparent open box (TOB) learning network algorithm described here overcomes these limitations by clearly revealing its intermediate calculations and the weightings applied to its independent variables in deriving its predictions. The steps involved in building and optimizing the TOB network are described in detail. For small to mid-sized datasets the TOB network can be deployed using spreadsheet formulas and standard optimizers; for larger systems coded algorithms and customised optimizers are easy to configure. Hybrid applications combining spreadsheet benefits (e.g. Microsoft Excel Solver) with algorithm code are also effective. The TOB learning network is applied to three petroleum datasets and demonstrates both its learning capabilities and the insight to the modelled systems that it is able to provide. TOB is not proposed as a replacement for neural networks and machine learning algorithms, but as a complementary tool; it can serve as a performance benchmark for some of the less transparent algorithms.
Authors and Affiliations
David A. Wood
Keywords
Related Articles
- EP ID EP427917
- DOI 10.26804/ager.2018.02.04
- Views 56
- Downloads 0
Mechanisms of reservoir pore/throat characteristics evolution during long-term waterflooding
Formation pore structure and reservoir parameters change continually during waterflooding due to sand production, clay erosion, and pressure/temperature variation, which causes great challenge in geological modeling and...
A new algorithm for computation of horizontal-well pressure in Laplace domain
The effect of wellbore pressure drop on horizontal well pressure response is relatively important when flow velocity is high or the surface of horizontal wellbore is rough. The objective of this study is to develop a sta...
Impact of four different CO2 injection schemes on extent of reservoir pressure and saturation
This study investigates how four different injection schemes, (i. constant rate, ii. stepwise increasing rate, iii. stepwise decreasing rate, and iv. cyclic rate), constrained by the cumulative amount of CO2 injected, af...
A new model for calculating permeability of natural fractures in dual-porosity reservoir
During the development of naturally fractured carbonate reservoirs, understanding the change in fracture permeability is the basis for production evaluation and scientific development. The conventional method of analyzin...
Non-Darcy displacement by a non-Newtonian fluid in porous media according to the Barree-Conway model
An analytical solution for describing the non-Darcy displacement of a Newtonian fluid by a non-Newtonian fluid in porous media has been developed. The two-phase non-Darcy flow is described using the Barree-Conway model u...