Penerapan Algoritma Propagasi Balik Jaringan Saraf Tiruan untuk Prediksi Produksi Sumur Gas di Sumatera Bagian Selatan
Keywords:
artificial neural network, backpropagation, energy, forecasting, artificial intelligenceAbstract
Gas production forecasting plays a crucial role in supporting planning and management within a country's or region's oil and gas (O&G) sector. Artificial Neural Networks (ANN) are among the most effective methods for forecasting; however, the main challenge lies in determining the optimal number of neurons and hidden layers to achieve high prediction accuracy. This study aims to design an ANN architecture using the backpropagation algorithm to predict gas well production. The research stages include gas production data collection, data pre-processing, prediction processing, accuracy and error testing, and implementation. The dataset consists of daily natural gas well production records from January to December 2022, used for both training and testing the model. The results indicate that the ANN architecture 16-4-1 with a sigmoid activation function achieved the highest accuracy of 99.978% and the lowest MAPE of 2.192%. These findings demonstrate that the developed model can accurately represent the complexity of historical daily production data, making it a valuable tool for O&G field managers to plan production, optimize operations, and support strategic decision-making in the energy sector.
References
Abu, S. M., Hannan, M. A., Ker, P. J., Mansor, M., Tiong, S. K., & Mahlia, T. M. I. (2023). Recent progress in electrolyser control technologies for hydrogen energy production: A patent landscape analysis and technology updates. Journal of Energy Storage, 72, 108773. https://doi.org/10.1016/J.EST.2023.108773
Ali, A., Shaukat, H., Bibi, S., Altabey, W. A., Noori, M., & Kouritem, S. A. (2023). Recent progress in energy harvesting systems for wearable technology. Energy Strategy Reviews, 49, 101124. https://doi.org/10.1016/J.ESR.2023.101124
Ayu, D. K., Susilaningrum, D., & Suhartono, S. (2016). Pemodelan Produksi Minyak dan Gas Bumi di PT. “Z” Menggunakan Metode ARIMA, FFNN, dan Hybrid ARIMA-FFNN. Jurnal Sains Dan Seni ITS, 5(2), 2337–3520. https://doi.org/10.12962/J23373520.V5I2.17189
Dong, J., Song, B., He, F., Xu, Y., Wang, Q., Li, W., & Zhang, P. (2023). Research on a Hybrid Intelligent Method for Natural Gas Energy Metering. Sensors (Basel, Switzerland), 23(14). https://doi.org/10.3390/S23146528
Fan, D., Sun, H., Yao, J., Zhang, K., Yan, X., & Sun, Z. (2021). Well production forecasting based on ARIMA-LSTM model considering manual operations. Energy, 220, 119708. https://doi.org/10.1016/J.ENERGY.2020.119708
Fry, M., Brannstrom, C., & Sakinejad, M. (2017). Suburbanization and shale gas wells: Patterns, planning perspectives, and reverse setback policies. Landscape and Urban Planning, 168, 9–21. https://doi.org/10.1016/J.LANDURBPLAN.2017.08.005
Glushchenko, A., Petrov, V., & Lastochkin, K. (2021). Backpropagation method modification using Taylor series to improve accuracy of offline neural network training. Procedia Computer Science, 186, 202–209. https://doi.org/10.1016/J.PROCS.2021.04.139
Goh, A. T. C. (1995). Back-propagation neural networks for modeling complex systems. Artificial Intelligence in Engineering, 9(3), 143–151. https://doi.org/10.1016/0954-1810(94)00011-S
Gonzalez, D. J. X., Sherris, A. R., Yang, W., Stevenson, D. K., Padula, A. M., Baiocchi, M., Burke, M., Cullen, M. R., & Shaw, G. M. (2020). Oil and gas production and spontaneous preterm birth in the San Joaquin Valley, CA: A case–control study. Environmental Epidemiology, 4(4). https://doi.org/10.1097/EE9.0000000000000099
Hecht-Nielsen, R. (1992). Theory of the Backpropagation Neural Network. Neural Networks for Perception, 65–93. https://doi.org/10.1016/B978-0-12-741252-8.50010-8
Hennings, P., Allwardt, P., Paul, P., Zahm, C., Reid, R., Alley, H., Kirschner, R., Lee, B., & Hough, E. (2012). Relationship between fractures, fault zones, stress, and reservoir productivity in the Suban gas field, Sumatra, Indonesia. AAPG Bulletin, 96(4), 753–772. https://doi.org/10.1306/08161109084
Herdiansah, A., Borman, R. I., Nurnaningsih, D., Sinlae, A. A. J., & Al Hakim, R. R. (2022). Klasifikasi Citra Daun Herbal Dengan Menggunakan Backpropagation Neural Networks Berdasarkan Ekstraksi Ciri Bentuk. JURIKOM (Jurnal Riset Komputer), 9(2), 388–395. https://doi.org/10.30865/jurikom.v9i1.3846
Liu, H., Liu, Y., Wang, C., Song, Y., Jiang, W., Li, C., Zhang, S., & Hong, B. (2023a). Natural Gas Demand Forecasting Model Based on LASSO and Polynomial Models and Its Application: A Case Study of China. Energies, 16(11). https://doi.org/10.3390/EN16114268
Liu, H., Liu, Y., Wang, C., Song, Y., Jiang, W., Li, C., Zhang, S., & Hong, B. (2023b). Natural Gas Demand Forecasting Model Based on LASSO and Polynomial Models and Its Application: A Case Study of China. Energies, 16(11). https://doi.org/10.3390/EN16114268
Liu, X., Tang, H., Zhang, D., Geng, S., Wu, G., Li, C., & Liu, S. (2023). A prediction model for new well deliverability in an underground gas storage facility using production data. Journal of Energy Storage, 60, 106649. https://doi.org/10.1016/J.EST.2023.106649
Nagar, R., Srivastava, S., Hudson, S. L., Amaya, S. L., Tanna, A., Sharma, M., Achayalingam, R., Sonkaria, S., Khare, V., & Srinivasan, S. S. (2023). Recent developments in state-of-the-art hydrogen energy technologies – Review of hydrogen storage materials. Solar Compass, 5, 100033. https://doi.org/10.1016/J.SOLCOM.2023.100033
Nourislam, A., Jondri, J., & Saadah, S. (2014). Analisis dan Implementasi Jaringan Syaraf Tiruan – Propagasi Balik Dalam Memprediksi Produksi dan Konsumsi Minyak Bumi, Gas Bumi, dan Batu Bara di Indonesia. EProceedings of Engineering, 1(1), 558–564.
Purnawan, H., Putra, R. A. P., Fauzi, R., Setiawan, A. D., Jaenul, A., Al-Hakim, R. R., Nugroho, H. S., & Kuntjoro, Y. D. (2024). Using Backpropagation Neural Network for Polyvinylchloride Ceiling Price Modeling. Informatech: Jurnal Ilmiah Informatika Dan Komputer, 1(1), 26–30.
Puspitaningrum, D. (2006). Pengantar Jaringan Saraf Tiruan. Andi.
Sutama, C., & Inayah, F. (2013). Expanding Cement Application for High Rate Gas Wells in South Sumatra. Society of Petroleum Engineers - SPE Asia Pacific Oil and Gas Conference and Exhibition, APOGCE 2013: Maximising the Mature, Elevating the Young, 1, 368–376. https://doi.org/10.2118/165792-MS
Szoplik, J., & Muchel, P. (2023). Using an artificial neural network model for natural gas compositions forecasting. Energy, 263, 126001. https://doi.org/10.1016/J.ENERGY.2022.126001
Vlachas, P. R., Pathak, J., Hunt, B. R., Sapsis, T. P., Girvan, M., Ott, E., & Koumoutsakos, P. (2020). Backpropagation algorithms and Reservoir Computing in Recurrent Neural Networks for the forecasting of complex spatiotemporal dynamics. Neural Networks, 126, 191–217. https://doi.org/10.1016/J.NEUNET.2020.02.016
Wong, F. S. (1991). Time series forecasting using backpropagation neural networks. Neurocomputing, 2(4), 147–159. https://doi.org/10.1016/0925-2312(91)90045-D
Wythoff, B. J. (1993). Backpropagation neural networks: A tutorial. Chemometrics and Intelligent Laboratory Systems, 18(2), 115–155. https://doi.org/10.1016/0169-7439(93)80052-J
Zhang, M., Mu, L., Li, C., Zheng, K., Duan, L., Wang, G., Zuo, S., & Li, D. (2017). Mature Condensated Gas Field Development Strategy: An Integration of Geophysics, Geology and Log for the South Sumatra Basin, Indonesia. SPE Reservoir Characterisation and Simulation Conference and Exhibition, RCSC 2017, 513–523. https://doi.org/10.2118/186060-MS
