Aditya Nur'ahya, . (2023) SISTEM PREDIKSI ZONA POTENSIAL HIDROKARBON BERDASARKAN DATA WELL-LOG MENGGUNAKAN METODE RANDOM FOREST. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (428kB) |
|
Text
AWAL.pdf Download (1MB) |
|
Text
BAB 1.pdf Download (574kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (759kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (817kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (2MB) |
|
Text
BAB 5.pdf Download (561kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (433kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (342kB) |
|
Text
LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (3MB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (7MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (1MB) |
Abstract
The activity of interpreting geophysical data is an analytical activity carried out by geophysicists in interpreting the acquired data with related data. Thus, obtaining initial estimates to explain the subsurface conditions. This research was conducted to make predictions that could help speed up the initial prediction of the hydrocarbon content made by a geophysicist as an interpretation activity. Interpretation activities require high speed and accuracy so as to produce the right analysis results. The application of the concept of data mining is used to classify the hydrocarbon content in the soil layer which is predicted using well-log data. One of the data mining classification algorithms used in this study is the Random Forest algorithm. This algorithm is used to classify the hydrocarbon content. In this study, datasets obtained from the official website of the National Offshore Petroleum Information Management System (NOPIMS) were used with an initial dataset of 28,378 data and after cleaning the data used amounted to 4,556 data, then the data was divided into training data and test data for model training. In this study, an evaluation of the model was carried out which included measurements of accuracy, precision, recall value, f1-measure value, and AUC score value which was carried out by measuring each ratio of data sharing ratios. With a ratio of 80-20, the accuracy value obtained is 0.9923 or 99.23%, the precision value is 0.97 or 97%, the recall value is 0.98 or 98%, the f1-measure value is 0.97 or 97%, and AUC Score value of 0.9919. It is hoped that the implementation of the model in the system can assist geophysicists in interpreting well-log data in determining potential hydrocarbon zones.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1910512025] [Pembimbing: Ati Zaidiah] [Penguji 1: Widya Cholil] [Penguji 2: Kraugusteeliana] |
| Uncontrolled Keywords: | Prediction, Hidrocarbon, Random Forests |
| Subjects: | Q Science > Q Science (General) Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Sistem Informasi (S1) |
| Depositing User: | Aditya Nur'ahya |
| Date Deposited: | 01 Feb 2023 06:25 |
| Last Modified: | 01 Feb 2023 06:25 |
| URI: | http://repository.upnvj.ac.id/id/eprint/22748 |
Actions (login required)
 |
View Item |