Sandy Kurniawan Suhardja
Department of Geophysical Engineering University of Pertamina, Jl. Teuku Nyak Arief, Simprug, Kebayoran Lama, Jakarta 12220, Indonesia

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal Geofisika

Early Results of Comparison between K-Nearest Neighbor and Artificial Neural Network Method for Facies Estimation Hadyan Pratama; Loris Alif Syahputra; Muhammad Fauzan Albany; Agus Abdullah; Sandy Kurniawan Suhardja; Epo Kusumah; Weny Astuti; Bambang Mujihardi
Jurnal Geofisika Vol 18 No 1 (2020): Jurnal Geofisika
Publisher : Himpunan Ahli Geofisika Indonesia (HAGI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36435/jgf.v18i1.418

Abstract

Artificial Intelligence method has been widely used recently in many aspects to understand big data. Fundamentally, the purpose of Artificial Intelligence is to solve nonlinear problem. Most methods are trying to optimize an output from one or many inputs parameter by identifying any potential patterns that fit or using a statistical data. In Oil & Gas industry, one of the main challenges that can be solved by Artificial Intelligence is estimating facies from well log or seismic data. The main scope of this study is estimating lithofacies by analyzing well logs input using two different methods, K-Nearest Neighbor (KNN) and Artificial Neural Network (ANN). We employed various well log data such as gamma-ray, resistivity, neutron density porosity, and photoelectric effect from well log data at Panoma Council Grove Field, South West Kansas, United States. This study shows that using optimized parameters, KNN method faster than ANN method but, ANN give result better than KNN. Nevertheless, despite the fact this research could estimate lithologies, many aspect should be considered in order to reach optimum result such as insights from geological regional models.
Comparison of 3-D Raytracing and Finite Frequency Tomography Sandy K Suhardja; Yosua Hotmaruli Lumban Gaol; Agus Abdullah; Andri Dian Nugraha; Z. Zulfakriza
Jurnal Geofisika Vol 17 No 1 (2019): Jurnal Geofisika
Publisher : Himpunan Ahli Geofisika Indonesia (HAGI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (5587.934 KB) | DOI: 10.36435/jgf.v17i1.393

Abstract

We performed 3-D seismic tomography using teleseismic arrival time at Southwest Mexico. The Mexican subduction zone results from successive fragmentation events that affected the ancient Farallon plate as various segments of the East Pacific rise approached the paleo-trench off western North America. The complexity in this region is related to two subducting oceanic plates, the Rivera and Cocos plates, that have different ages, compositions, convergence velocities and subduction dip angles. In this study, we compared the 3-D raytracing tomography model with finite frequency tomography model. Final models show the differences in amplitude and pattern between the raytracing and finite frequency. 3D raytracing models produced sharper images of fast velocity structures in the mantle. The deeper slabs are more coherent and show less broadening with depth than using 1D finite frequency kernels. However, although the finite frequency and 3-D ray tracing models show some differences in amplitude and pattern, the overall agreement of the models supports the interpretation of Yang et al. (2009) that slab rollback is occurring in South Western Mexico. One possible different interpretation between the raytracing and finite frequency theory results concerns the deep structure of the Rivera slab. The finite frequency models show that the Rivera slab is clearly observable at a depth of about 300km but fades away at greater depths. However, the 3-D ray tracing model shows a clear fast velocity band down to a depth of 400 km and thus our model does not support a slab tear of the Rivera plate above 400 km depth