Developing Ensemble Machine Learning Models to Predict Petrophysical Properties of Sandstone Reservoirs

This research investigated the applicability of bagging and boosting ensemble machine learning algorithms in predicting petrophysical properties, namely porosity, permeability and water saturation which is a vital aspect in reservoir characterization. Further, an in-depth analysis was done on the ef...

Full description

Bibliographic Details
Main Author: Kohona Walawwe, Kushan Oshadi Sandunil
Format: Thesis
Published: Curtin University 2025
Online Access:http://hdl.handle.net/20.500.11937/97704
_version_ 1848766307985522688
author Kohona Walawwe, Kushan Oshadi Sandunil
author_facet Kohona Walawwe, Kushan Oshadi Sandunil
author_sort Kohona Walawwe, Kushan Oshadi Sandunil
building Curtin Institutional Repository
collection Online Access
description This research investigated the applicability of bagging and boosting ensemble machine learning algorithms in predicting petrophysical properties, namely porosity, permeability and water saturation which is a vital aspect in reservoir characterization. Further, an in-depth analysis was done on the effects of different hyperparameter optimization algorithms. The study successfully proposed stacking-based novel ensemble models to predict petrophysical properties of sandstone reservoirs where some models performed up to 97% in prediction accuracy.
first_indexed 2025-11-14T11:49:04Z
format Thesis
id curtin-20.500.11937-97704
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T11:49:04Z
publishDate 2025
publisher Curtin University
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-977042025-05-09T00:51:20Z Developing Ensemble Machine Learning Models to Predict Petrophysical Properties of Sandstone Reservoirs Kohona Walawwe, Kushan Oshadi Sandunil This research investigated the applicability of bagging and boosting ensemble machine learning algorithms in predicting petrophysical properties, namely porosity, permeability and water saturation which is a vital aspect in reservoir characterization. Further, an in-depth analysis was done on the effects of different hyperparameter optimization algorithms. The study successfully proposed stacking-based novel ensemble models to predict petrophysical properties of sandstone reservoirs where some models performed up to 97% in prediction accuracy. 2025 Thesis http://hdl.handle.net/20.500.11937/97704 Curtin University fulltext
spellingShingle Kohona Walawwe, Kushan Oshadi Sandunil
Developing Ensemble Machine Learning Models to Predict Petrophysical Properties of Sandstone Reservoirs
title Developing Ensemble Machine Learning Models to Predict Petrophysical Properties of Sandstone Reservoirs
title_full Developing Ensemble Machine Learning Models to Predict Petrophysical Properties of Sandstone Reservoirs
title_fullStr Developing Ensemble Machine Learning Models to Predict Petrophysical Properties of Sandstone Reservoirs
title_full_unstemmed Developing Ensemble Machine Learning Models to Predict Petrophysical Properties of Sandstone Reservoirs
title_short Developing Ensemble Machine Learning Models to Predict Petrophysical Properties of Sandstone Reservoirs
title_sort developing ensemble machine learning models to predict petrophysical properties of sandstone reservoirs
url http://hdl.handle.net/20.500.11937/97704