Claim Missing Document
Check
Articles

Yeo-Johnson Transformation Usage in Data Preprocessing for Well Production Prediction Using Deep Neural Networks (DNN) Alringga Rizky; Anny Yuniarti
Journal of Business, Social and Technology Vol. 7 No. 2 (2026): Journal of Business, Social and Technology
Publisher : Politeknik Siber Cerdika Internasional

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59261/jbt.v7i2.607

Abstract

Background: The accurate prediction of infill well production is one of the major bottlenecks for hydrocarbon reservoir development. Traditional reservoir simulation tools are computationally expensive, taking weeks to months per scenario. Objective: This paper presents the development of a Deep Neural Network (DNN) model for prediction with hyperparameter optimization using the Tree-structured Parzen Estimator (TPE) to predict pay porosity (PORPAYX) in infill wells of the Pertamina Hulu Sanga Sanga field. Methods: A DNN model was developed to predict oil well production based on subsurface and production features from a comprehensive dataset of Pertamina Hulu Sanga Sanga reservoir characteristics and production data. Details of our method include: training the model on a robust dataset, hyperparameter tuning using the Tree-structured Parzen Estimator (TPE), and K-fold cross-validation for performance validation. Results: Scaling normalized the data in such a way that every feature had equal influence during model training, enabling better learning and accurate prediction. In contrast, fitting the model using unscaled data resulted in an R² of less than zero (a negative score), meaning that the model could not explain the variability in the data. The mean R² score of the unscaled data model was −0.08496, along with a higher MSE = 0.009057 and RMSE = 0.095148. This was due to the model's failure to process features with varying scales, which prevented proper learning and prediction. Conclusion: Residual plots confirmed that the model trained with scaled data met the assumptions of linearity and normality.
Co-Authors Abdullah Al-Haddad Achmad Chabiburrohman Achmad Fahriza Agus Arifin Agus Arifin, Agus Agus Z. Arifin, Agus Z. Agus Zainal Arifin Agus Zainal Arifin Ahmad Mustofa Hadi Ahmad Mustofa Hadi Ahmad Raihan Muzakki Akira Asano Akira Taguchi Alifiansyah Arrizqy Hidayat Alringga Rizky Amrullah, Muhammad Syiarul Andi Baso Kaswar Andi Baso Kaswar Anindhita Sigit Nugroho Anindita Sigit Nugroho Anita Hakim Nasution Arif Fathur Mahmuda Arifiani, Siska Arifzan Razak Aris Fanani Aris Tjahyanto Arya Yudhi Wijaya Aulya Sri Utami Ilham Berlian Rahmy Lidiawaty Betty Natalie Fitriatin Bilqis Amaliah Budi Nugroho Budi Nugroho Chastine Fatichah Chilyatun Nisa' Christy Atika Sari Darlis Heru Mukti Darlis Herumurti Devira Wiena Pramintya Dhian Satria Yudha Kartika Diana Suteja Dini Adni Navastara, Dini Adni Eva Yulia Puspaningrum Fawwaz Abdulloh Al-Jawi Feni Siti Fauziah2 Fetty Tri A. Fiandra Fatharany Gulpi Qorik Oktagalu Pratamasunu Hadziq Fabroyir Handayani Tjandrasa Hani Ramadhan Hidiyah Ayu Ratna Ma’rufah Hisyam Syarif Hudan Studiawan I Made Satria Bimantara I Made Widiartha I Putu Gede Hendra Suputra Imam Kuswardayan Imam Kuswardayan Ishardan Ishardan Isye Arieshanti Kelly Rossa Sungkono Khairun Nisa Kostidjan, Okky Darmawan Lutfiani Ratna Dewi M. Ali Fauzi M. Ali Fauzi Maulana, Hendra MIFTAHOL ARIFIN, MIFTAHOL Mohamad Dion Tiara Muhammad I. Rosadi, Muhammad I. Muhammad Meftah Mafazy Muhammad Rayyaan Fatikhahur Rakhim Muhammad Riduwan Nadya Anisa Syafa Nafiiyah, Nur Nanik Suciati Nanik Suciati Oviyanti Mulyani Pasnur Pasnur Purwanto, Yudhi Puspitasari, Leny Ratri Enggar Pawening Reginawanti Hindersah Ridho Rahman Hariadi Riduwan, Muhammad Rindah Febriana Suryawati Rizky Damara Ardy Sahmanbanta Sinulingga Saiful Bahri Musa Saprina Mamase Saputra, Wahyu Syaifullah Jauharis Siska Arifiani Soegeng Soetedjo Sofyan Sauri, Sofyan Takashi Nakamoto Thoha Haq Wahyu Syaifullah Jauharis Saputra Wibowo, Della Aulia Wijayanti Nurul K Wijayanti Nurul Khotimah Xinyou Zeng