Prediksi Litologi Menggunakan Support Vector Machine Pada Lapangan "VISA" Formasi Balikpapan Kalimantan Timur

Nugraha, Muhammad Faiz (2025) Prediksi Litologi Menggunakan Support Vector Machine Pada Lapangan "VISA" Formasi Balikpapan Kalimantan Timur. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5017211054-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (6MB) | Request a copy

Abstract

Penelitian ini berada di lapangan “VISA” Formasi Balikpapan yang terletak di Cekungan Kutai, salah satu cekungan hidrokarbon terbesar di Indonesia. Formasi ini didominasi oleh litologi sandstone dan shale, yang penting untuk eksplorasi dan produksi hidrokarbon. Dalam pengolahan data sumur, penentuan litologi di awal adalah cara agarndapat memahami karakteristik data sumur sehingga pada penelitian ini digunakan algoritma Support Vector Machine (SVM) yang dapat membantu melakukan prediksi terhadap litologi pada data sumur. Pada penelitian ini digunakan empat data sumur sebagai dataset yaitu sumur VISA-9, VISA-13, VISA-36, dan VISA-39. Hasil prediksi kemudian divisualisasikan dalam bentuk log sumur dan distribusi litologi menggunakan histogram agar mempermudah pemahaman hasil prediksi berdasarkan empat kategori litologi yang di interpretasi yaitu sandstone, shale, dan coal. Dari hasil prediksi masih terlihat ada kesalahan dalam melakukan klasifikasi SVM terhadap parameter data sumur yang dilihat dari hasil performa SVM. Pada percobaan 1 percobaan 2, dan percobaan 3 terlihat range eror yang didapatkan sebesar 11-22% terhadap litologi aktual. Pada percobaan ke 4 terlihat peningkatan yang signifikan karena menggunakan 3 data training, peningkatan terjadi sebesar 7% dari percobaan sebelumnya dan eror yang didapatkan sebesar 5%. Secara keseluruhan, metode SVM dapat digunakan dalam mengklasifikasikan litologi batuan sesuai dengan litologi aktual pada dari sumur tetapi SVM masih perlu dioptimalkan karena masih mengalami beberapa kesalahan dalam proses prediksi litologi. Penelitian ini membuktikan bahwa Support Vector Machine (SVM) bisa digunakan dalam proses prediksi litologi menggunakan parameter log sumur.
===================================================================================================================================
This research is located in the “VISA” field of the Balikpapan Formation located in the Kutai Basin, one of the largest hydrocarbon basins in Indonesia. This formation is dominated by sandstone and shale lithology, which is important for hydrocarbon exploration and production. In well data processing, determining the lithology at the beginning is a way to understand the characteristics of well data so that in this study the Support Vector Machine (SVM) algorithm is used which can help predict lithology in well data. In this study, four well data were used as datasets, namely wells VISA-9, VISA-13, VISA-36, and VISA-39. The prediction results are then visualized in the form of well logs and lithology distribution using a histogram to facilitate understanding of the prediction results based on the four interpreted lithology categories, namely sandstone, shale, and coal. From the prediction results, there are still errors in performing SVM classification of well data parameters as seen from the results of SVM performance. In experiment 1, experiment 2, and experiment 3, the error range obtained was 11-22% of the actual lithology. In the 4th experiment, a significant increase was seen because it used 3 training data, an increase of 7% from the previous experiment and the error obtained was 5%. Overall, the SVM method can be used to classify rock lithology according to the actual lithology of the well but SVM still needs to be optimized because it still experiences some errors in the lithology prediction process. This study proves that Support Vector Machine (SVM) can be used in the lithology prediction process using well log parameters.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Lithology Prediction, Support Vector Machine, Radial Basis Function, Accuracy, Prediksi Litologi, Mesin Pendukung Vector, Fungsi Basis Radial, Akurasi
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QE Geology
Divisions:	Faculty of Civil, Planning, and Geo Engineering (CIVPLAN) > Geophysics Engineering > 33201-(S1) Undergraduate Thesis
Depositing User:	Muhammad Faiz Nugraha
Date Deposited:	11 Feb 2025 00:41
Last Modified:	11 Feb 2025 00:41
URI:	http://repository.its.ac.id/id/eprint/118603

Actions (login required)

View Item