Ukari Osah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ukari Osah has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- John Howell
Department of Geology and Geophysics, School of Geosciences University of Aberdeen, King's College Meston Building Aberdeen AB24 3UE UK
2 shared publications
Latest Publications
- Open Access
- 9 January 2023
- Published by Geological Society of London in Petroleum Geoscience
- Vol. 29 (1)
Predicting oil field performance using machine learning programming: a comparative case study from the UK continental shelf
Predicting the performance of a subsurface oil field is a large, multivariant problem. Production is controlled and influenced by a wide array of geological and engineering parameters which overlap and interact in ways that are difficult to unravel in a manner that can be predictive. Supervised machine learning is a statistical approach which uses empirical learnings from a training dataset to create models and make predictions about future outcomes. The goal of this study is to test a number of supervised machine learning methods on a dataset of oil fields from the United Kingdom continental shelf (UKCS), in order to assess whether, (a) it is possible to predict future oil field performance and (b), which methods are the most effective. The study is based on a dataset of 60 fields with 5 controlling parameters, (gross depositional environment, average permeability, net-to-gross, gas–oil ratio and total number of wells) and 2 outcome parameters (recovery factor and maximum field rate) for each. The choice of controlling parameters was based on a PCA of a larger dataset from a wider project database. Five different machine learning algorithms were tested. These include linear regression, robust linear regression, linear kernel support vector regression, cubic kernel support vector regression and boosted trees regression. Overall, 83% of the data was used as a training dataset while 17% was used to test the predictability of the algorithms. Results were compared using R-Squared, Mean Square Error, Root Mean Square Error and Mean Absolute Error. Graphs of predicted responses v. true (actual) responses are also shown to give a visual illustration of model performance. Results of this analysis show that certain methods perform better than others, depending on the outcome variable in question (recovery factor or maximum field rate). The best method for both outcome variables was the support vector regression, where, depending on the kernel function applied, a reliable level of predictability with low error rates were achieved. This demonstrates a strong potential for statistics-based prediction models of reservoir performance. Thematic collection: This article is part of the Digitally enabled geoscience workflows: unlocking the power of our data collection available at https://www.lyellcollection.org/topic/collections/digitally-enabled-geoscience-workflows
- 9 January 2023
- Published by Geological Society of London in Petroleum Geoscience
- Vol. 29 (1)
Open AccessPredicting oil field performance using machine learning programming: a comparative case study from the UK continental shelf
Predicting the performance of a subsurface oil field is a large, multivariant problem. Production is controlled and influenced by a wide array of geological and engineering parameters which overlap and interact in ways that are difficult to unravel in a manner that can be predictive. Supervised machine learning is a statistical approach which uses empirical learnings from a training dataset to create models and make predictions about future outcomes. The goal of this study is to test a number of supervised machine learning methods on a dataset of oil fields from the United Kingdom continental shelf (UKCS), in order to assess whether, (a) it is possible to predict future oil field performance and (b), which methods are the most effective. The study is based on a dataset of 60 fields with 5 controlling parameters, (gross depositional environment, average permeability, net-to-gross, gas–oil ratio and total number of wells) and 2 outcome parameters (recovery factor and maximum field rate) for each. The choice of controlling parameters was based on a PCA of a larger dataset from a wider project database. Five different machine learning algorithms were tested. These include linear regression, robust linear regression, linear kernel support vector regression, cubic kernel support vector regression and boosted trees regression. Overall, 83% of the data was used as a training dataset while 17% was used to test the predictability of the algorithms. Results were compared using R-Squared, Mean Square Error, Root Mean Square Error and Mean Absolute Error. Graphs of predicted responses v. true (actual) responses are also shown to give a visual illustration of model performance. Results of this analysis show that certain methods perform better than others, depending on the outcome variable in question (recovery factor or maximum field rate). The best method for both outcome variables was the support vector regression, where, depending on the kernel function applied, a reliable level of predictability with low error rates were achieved. This demonstrates a strong potential for statistics-based prediction models of reservoir performance. Thematic collection: This article is part of the Digitally enabled geoscience workflows: unlocking the power of our data collection available at https://www.lyellcollection.org/topic/collections/digitally-enabled-geoscience-workflows
- Open Access
- 1 January 2023
- Published by Wiley in Resource Geology
- Vol. 73 (1)
Spatial and temporal distribution of hydrocarbon production on the UK continental shelf
Hydrocarbon production from oil and gas fields is controlled by a variety of interconnected factors with a hierarchy of significance that is, for the most part, difficult to untangle. This article documents and investigates the spatial and temporal distribution of key hydrocarbon field parameters on the UK Continental Shelf. Data have been compiled from publicly available sources for 424 fields. Variables are considered as “descriptive parameters,” “control parameters” and “outcomes”. Descriptive parameters are metadata such as field name, location, etc. Control Parameters include depositional environment, present depth of burial, porosity, permeability, reservoir formation pressure, reservoir temperature, average net‐to‐gross, number of fault populations, hydrocarbon API, field area, bulk rock volume, well density, number of wells (production and injection), well spacing, gas oil ratio, reservoir thickness, fluid saturation, compartmentalization (quantitated by number of observable non‐communicating fault compartments), structural complexity (scaled from 0 to 5), field production strategy, trap type and stratigraphic heterogeneity. Outcomes are used to assess field performance and include final recovery factor (estimated), maximum production rate, and cumulative monthly production. Analysis of the database illustrates a number of empirical observations regarding hydrocarbon production on the UKCS. The Jurassic plays have been the most successful in the region in terms of total volumes produced while the Permian reservoirs of the SNS account for the majority of the gas. Most of the UKCS reservoirs record top depths between 2000 and 4500 m with good reservoir quality. The best reservoir quality is observed in reservoirs that were deposited within deep marine systems. The largest hydrocarbon reserves are found in the Northern North Sea basin in these deep marine (as well as paralic and shallow marine) reservoirs. Using the data from this article and affiliated data, potential exists for extracting insight beyond spatio‐temporal distributions.
- 1 January 2023
- Published by Wiley in Resource Geology
- Vol. 73 (1)
Open AccessSpatial and temporal distribution of hydrocarbon production on the UK continental shelf
Hydrocarbon production from oil and gas fields is controlled by a variety of interconnected factors with a hierarchy of significance that is, for the most part, difficult to untangle. This article documents and investigates the spatial and temporal distribution of key hydrocarbon field parameters on the UK Continental Shelf. Data have been compiled from publicly available sources for 424 fields. Variables are considered as “descriptive parameters,” “control parameters” and “outcomes”. Descriptive parameters are metadata such as field name, location, etc. Control Parameters include depositional environment, present depth of burial, porosity, permeability, reservoir formation pressure, reservoir temperature, average net‐to‐gross, number of fault populations, hydrocarbon API, field area, bulk rock volume, well density, number of wells (production and injection), well spacing, gas oil ratio, reservoir thickness, fluid saturation, compartmentalization (quantitated by number of observable non‐communicating fault compartments), structural complexity (scaled from 0 to 5), field production strategy, trap type and stratigraphic heterogeneity. Outcomes are used to assess field performance and include final recovery factor (estimated), maximum production rate, and cumulative monthly production. Analysis of the database illustrates a number of empirical observations regarding hydrocarbon production on the UKCS. The Jurassic plays have been the most successful in the region in terms of total volumes produced while the Permian reservoirs of the SNS account for the majority of the gas. Most of the UKCS reservoirs record top depths between 2000 and 4500 m with good reservoir quality. The best reservoir quality is observed in reservoirs that were deposited within deep marine systems. The largest hydrocarbon reserves are found in the Northern North Sea basin in these deep marine (as well as paralic and shallow marine) reservoirs. Using the data from this article and affiliated data, potential exists for extracting insight beyond spatio‐temporal distributions.