Identifikasi Area Potensial Untuk Perencanaan Lokasi Sumur Migas Menggunakan Metode Machine Learning (Studi Kasus: Kabupaten Blora, Jawa Tengah)

Safira, Rizka Amelia Dwi (2023) Identifikasi Area Potensial Untuk Perencanaan Lokasi Sumur Migas Menggunakan Metode Machine Learning (Studi Kasus: Kabupaten Blora, Jawa Tengah). Other thesis, Institut Teknologi Sepuluh Nopember.

Text 03311940000044-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (16MB) | Request a copy

Abstract

Sebagai upaya meningkatkan produktivitas eksplorasi minyak dan gas serta memenuhi kebutuhan energi nasional dalam mendukung kajian Grand Strategi Energi Nasional (GSEN), diperlukan aplikasi teknologi yang mampu memberikan solusi alternatif, memangkas waktu pekerjaan, dan mengendalikan resiko ketidaksuksesan, salah satunya adalah machine learning. Penelitian tugas akhir ini bertujuan untuk menentukan area potensial perencanaan lokasi sumur migas baru menggunakan algoritma Support Vector Machine (SVM) dan Naive Bayes (NB) pada machine learning dengan perbandingan 80:20, 75:25, 60:40, dan 50:50 pada jumlah training dan testing data sehingga dihasilkan delapan pemodelan area potensial. Penelitian ini menggunakan empat belas parameter kondisional yang meliputi ketinggian, kemiringan, aspect, jarak dari jaringan sungai, tutupan lahan, jarak dari jaringan jalan, jenis tanah, NDVI (Normalized Difference Vegetation Index), clay mineral index, iron oxide index, suhu permukaan, anomali bouguer lengkap (ABL), jarak dari patahan, dan jenis batuan. Melalui pengujian performa menggunakan confusion matrix dan kurva ROC-AUC, diketahui algoritma dan pemodelan paling stabil untuk penelitian ini adalah SVM 75:25 dengan nilai accuracy (Acc), sensitivity (Sen), specificity (Spe), dan predictive value (PPV) sebesar 0,8333; Matthew`s correlation coefficient (MCC) dan Cohen`s Kappa sebesar 0,6667; serta AUC sebesar 0,9444. Parameter yang memberikan kontribusi paling tinggi terhadap pemodelan ini yaitu kemiringan dengan persentase index importance degree (IID) sebesar 100%. Berdasarkan model tersebut, wilayah yang memiliki potensi sebagai lokasi perencanaan sumur migas adalah Kecamatan Blora, Randublatung, Bogorejo, Jepon, Jati, Jiken, Sambong, dan Tunjungan.
=================================================================================================================================
As an effort to increase the productivity of oil and gas exploration and meet national energy needs in support of Grand National Energy Strategy (GSEN) study, it is necessary to apply technology that can provide alternative solutions, cut work time, and control the risk of failure, one of which is machine learning. This final project research aims to determine potential areas for new oil and gas well location planning using Support Vector Machine (SVM) dan Naive Bayes (NB) algorithms on machine learning with a ratio of 80:20, 75:25, 60:40, and 50:50 on the amount of training data and testing data so that eight potential area modeling will be produced. This study uses fourteen conditioning parameters which included height, slope, NDVI (Normalized Difference Vegetation Index), clay mineral index, iron oxide index, surface temperature, complete Bouguer anomaly (ABL), distance from the fault, and rock type. Through testing the performance of machine learning modeling, namely the confusion matrix and the ROC-AUC curve, it is known that the most stable algorithm and modeling for this research is SVM 75:25 with accuracy (Acc), sensitivity (Sen), specificity (Spe), and predictive value (PPV) of 0.8883; Matthew`s correlation coefficient (MCC) and Cohen`s Kappa (CK) of 0.6667; and AUC of 0.9444. While the conditioning parameter that contributes the highest to this modeling is the slope with an index importance degree (IID) the percentage of 100%. Based on this model, areas that have potential as locations for oil adn gas wells planning are the Blora, Randublatung, Bogorejo, Jepon, Jati, Jiken, Sambong, dan Tunjungan Districts.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Energy, Oil and Gas, Modeling, Energi, Machine Learning, Migas, Pemodelan.
Subjects:	G Geography. Anthropology. Recreation > G Geography (General) > G70.212 ArcGIS. Geographic information systems. G Geography. Anthropology. Recreation > G Geography (General) > G70.217 Geospatial data Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. T Technology > TP Chemical technology > TP692.5 Oil and gasoline handling and storage
Divisions:	Faculty of Civil, Planning, and Geo Engineering (CIVPLAN) > Geomatics Engineering > 29202-(S1) Undergraduate Thesis
Depositing User:	Rizka Amelia Dwi Safira
Date Deposited:	29 Jul 2023 17:25
Last Modified:	29 Jul 2023 17:25
URI:	http://repository.its.ac.id/id/eprint/100700

Actions (login required)

View Item