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 52
- Downloads 0
The new method on gas-water two phase steady-state productivity of fractured horizontal well in tight gas reservoir
Based on a large number of tight gas exploration and development literature researches, it is found that the horizontal drilling technology and fracturing operation are usually used in the tight gas reservoir for its low...
Characterization of marine-terrigenous transitional Taiyuan formation shale reservoirs in Hedong coal field, China
To better understand the basic characteristics of Marine-terrigenous Transitional Taiyuan formation shale (TYS) reservoirs in Hedong coal field, a series of reservoir evaluation experiments were conducted on 33 core samp...
Quantitative characterization of micropore structure for organic-rich Lower Silurian shale in the Upper Yangtze Platform, South China: Implications for shale gas adsorption capacity
The pores in shales are mainly of nanometer-scale, and their pore size distribution is very important for shale gas storage and adsorption capacity, especially micropores having widths less than 2 nm, which contribute to...
Redox condition and organic carbon accumulation mechanism in the Cryogenian Nanhua Basin, South China: Insights from iron chemistry and sulfur, carbon, oxygen isotopes of the Datangpo Formation
Global glaciation, oxidation event and eukaryotic expansion and diversification in the Neoproterozoic period are marked events that characterize the early evolution of the Earth, but how the interactions occurred among t...
The effect of flow resistance on water saturation profile for transient two-phase flow in fractal porous media
Due to the rapid development of Micro-Electro-Mechanical System (MEMS), more and more attention has been paid to the fluid properties of porous media, which is significant for petroleum engineering. However, most of surf...