Wibowo, Rahmat Catur and Dewanto, Ordas and Sarkowi, Muh (2021) Total Organic Carbon (TOC) Prediction Using Machine Learning Methods Based On Well Logs Data. In: 2nd ULICOSTE 2021, Bandar Lampung, Indonesia. (In Press)
|
Text
13_FP.pdf Download (965kB) | Preview |
Abstract
TOC (Total Organic Carbon) Determination is very important for the evaluation of each source rock unit. Methods that rely on extensive laboratory testing are limited by the availability and integrity of rock samples. Prediction of TOC from wells log data is available for most wells drilled, providing a rapid evaluation of organic content, providing a continuous record while eliminating sampling problems. Therefore, the ideal method for determining the TOC fraction in source rock units would be to use general well log data. The purpose of this study is to apply a machine learning method with the Multi-Layer Perceptron Artificial Neural Network (ANN) technique to predict the best correlation from a new empirical correlation that can be used to estimate TOC using well logs. Eighteen data points from the Talang Akar Formation were used for training and testing the MLP-ANN model. The results obtained show that the MLP-ANN model predicts TOC using only well logs: bulk density (RHOB), compressional time (DT), deep resistivity (ILD), gamma-ray (GR), and neutron porosity (NPHI) with accuracy. high (CC 0.98 and average absolute percentage error (AAPE) 5%). The TOC correlation that has been developed is simple and can be applied using any computer without the need for an ANN model or special software. The developed technique will help reservoir geophysicists and geologists to estimate TOC values using only well logs with high accuracy.
| Item Type: | Conference or Workshop Item (Paper) |
|---|---|
| Subjects: | Q Science > QD Chemistry Q Science > QE Geology |
| Divisions: | Fakultas Teknik (FT) > Prodi Teknik Geofisika |
| Depositing User: | Rahmat Catur Wibowo, S.T., M.Eng. |
| Date Deposited: | 08 Nov 2021 03:46 |
| Last Modified: | 08 Nov 2021 03:46 |
| URI: | http://repository.lppm.unila.ac.id/id/eprint/35460 |
Actions (login required)
 |
View Item |