Using a Deep Neural Network with Small Datasets to Predict the Initial Production of Tight Oil Horizontal Wells

Abstract

Due to its abundant reserves, tight oil has emerged as a significant substitute for conventional petroleum resources. It has become one of the focal points of exploration and research, and a new hot spot in global unconventional oil and gas exploration and development. This has led to a significant increase in the demand for forecasting the production capacity of tight oil horizontal wells. The deep neural network (DNN), as a mature model, has demonstrated significant advantages in many fields. However, due to the confidentiality and uniqueness of oilfield data, acquiring large datasets has become a challenge. Traditional methods using small datasets for training DNN models result in low accuracy and overfitting issues, which hinders the development of neural networks in the petroleum industry. This study aims to predict the initial production capacity of tight oil horizontal wells by using a small dataset of 650 data points through a DNN model. The research results indicate that pre-trained and fine-tuned DNNs outperform shallow neural networks, supporting vector machines, and DNN trained with traditional methods in terms of better generalization performance. Their accuracy reached 91.3%, demonstrating that it is reasonable to use a small dataset with pre-trained and fine-tuned DNN models.

Insights into the Efficient Release of the Polyacrylamide Drag Reducer via a pH-Responsive Inverse Polymer Emulsion

“…In recent decades, the exploitation of unconventional reservoirs with abundant resources has drawn extensive attention, resulting from the rapid innovation of horizontal drilling and fracturing technology. Among unconventional reservoirs, tight oil reservoirs have become crucial substitute petroleum resources for covering the resource shortage of conventional oil reservoirs. − Practically, it has been reported that volumetric fracturing technology offers advantages in reservoir reconstruction, improving the flow conductivity and enhancing the extraction efficiency of petroleum resources. − Slick water fracturing, as the main system supporting volumetric fracturing technology, − is capable of improving the pump injection volume and reducing the friction of a pipe wall . Therein, the polyacrylamide (PAMs) drag reducer is the most crucial additive in slick water fracturing for enhancing the reservoir reconstruction result. , …”