A Hybrid Transfer Learning Framework for Enhanced Oil Production Time Series Forecasting  

作　　者：Dalal A.L-Alimi Mohammed A.A.Al-qaness Robertas Damaševičius 

机构地区：[1]Department of Information Technology,Gulf Colleges,Hafr Al-Batin,2600,Saudi Arabia [2]College of Physics and Electronic Information Engineering,Zhejiang Normal University,Jinhua,321004,China [3]College of Engineering and Information Technology,Emirates International University,Sana’a,16881,Yemen [4]Department of Applied Informatics,Vytautas Magnus University,Akademija,44404,Lithuania

出　　处：《Computers, Materials & Continua》2025年第2期3539-3561,共23页计算机、材料和连续体(英文)

摘　　要：Accurate forecasting of oil production is essential for optimizing resource management and minimizing operational risks in the energy sector. Traditional time-series forecasting techniques, despite their widespread application, often encounter difficulties in handling the complexities of oil production data, which is characterized by non-linear patterns, skewed distributions, and the presence of outliers. To overcome these limitations, deep learning methods have emerged as more robust alternatives. However, while deep neural networks offer improved accuracy, they demand substantial amounts of data for effective training. Conversely, shallow networks with fewer layers lack the capacity to model complex data distributions adequately. To address these challenges, this study introduces a novel hybrid model called Transfer LSTM to GRU (TLTG), which combines the strengths of deep and shallow networks using transfer learning. The TLTG model integrates Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRU) to enhance predictive accuracy while maintaining computational efficiency. Gaussian transformation is applied to the input data to reduce outliers and skewness, creating a more normal-like distribution. The proposed approach is validated on datasets from various wells in the Tahe oil field, China. Experimental results highlight the superior performance of the TLTG model, achieving 100% accuracy and faster prediction times (200 s) compared to eight other approaches, demonstrating its effectiveness and efficiency.

关 键 词：Time series forecasting gaussian transformation quantile transformation long short-term memory gated recurrent units 

分 类 号：TE328[石油与天然气工程—油气田开发工程]