Claim Missing Document
Check
Articles

Found 2 Documents
Search

Trap Prevention in Machine Learning in Prediction of Petrophysical Parameters: A Case Study in The Field X Adam Putra Pratama Zainuri; Pahala Dominicus Sinurat; Dedy Irawan; Hari Sasongko
Scientific Contributions Oil and Gas Vol. 46 No. 3 (2023): SCOG
Publisher : Testing Center for Oil and Gas LEMIGAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29017/scog.46.3.328

Abstract

Petrophysical parameters such as porosity and water saturation are vital in the petroleum industry for reservoir characterization. These aspects are typically assessed through laboratorium measurements of core samples or intricate petrophysical calculations. Machine Learning (ML) offers a cost-effective and efficient approach as an alternative to conventional methods of predicting those parameters. However, developing ML models can be prone to the invisible traps such as overfitting, underfitting, feature selection, and feature importance. This study is intended to share how to identify the traps and its mitigation by establishing a synergistic workflow between ML and petrophysical theory. A model was developed based on data from several wells in X field, where they are randomized and split into test and train data. Well-log normalization preceded data splitting, and input features were normalized with outlier removal. A feature selection function was then employed to choose a specific amount of log data. Finally, the model selection function identified the highest-scoring model. Without a proper workflow, overfitting, irrelevant feature selection, and imprecise ranking issues emerged. However, with the proper workflow, these invisible traps were mitigated, even with a relatively small dataset. The final model could accurately predict porosity and water saturation
Integration of Empirical Methods for Accurate Water Saturation Calculation in Low Resistivity Reservoir Citrowati, Sekar Ayu; Dedy Irawan; Pahala Dominicus Sinurat
Journal of Earth Energy Science, Engineering, and Technology Vol. 7 No. 3 (2024): JEESET VOL. 7 NO. 3 2024
Publisher : Penerbitan Universitas Trisakti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25105/6qfar389

Abstract

The Indonesian oil and gas industry faces significant challenges in exploring low-resistivity reservoirs, such as the Talang Akar Formation in South Sumatra, the Tanjung Formation in East Kalimantan, and the Gumai Formation in South Sumatra and West Java. These reservoirs often contain clay, clayey sand, and conductive minerals, which complicate geophysical log interpretation, leading to missed hydrocarbon potential. Common methods such as Archie’s Law are often used to calculate water saturation but tend to be inaccurate in formations with high conductivity due to clay content. The Simandoux method attempts to address this limitation by considering the conductivity of clay, but the assumption of homogeneous clay distribution often does not match actual conditions. This study proposes a modification to the Simandoux method by accounting for the non-linear behavior of clay conductivity and formation-specific parameters derived from core analysis. This approach integrates multi-parameter log data and advanced petrophysical models to address mineralogical heterogeneity and clay distribution. The results show that the modified Simandoux method provides more accurate water saturation estimates in low-resistivity zones. Validation with core and production data demonstrates the improved reliability of this model, supporting optimal field development and hydrocarbon exploration in Indonesia.