A Physics-Constrained Data-Driven Workflow for Predicting Coalbed Methane Well Production Using Artificial Neural Network

Yang, Ruiyue; Qin, Xiaozhou; Liu, Wei; Huang, Zhongwei; Shi, Yu; Pang, Zhanxi; Zhang, Yiqun; Li, Jingbin; Wang, Tianyu

doi:10.2118/205903-pa

Cited by 24 publications

(9 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of computing, as we don't use bidirectional implementation, the architectural requirements are sim-pler. [40] also implemented a GRU-based model and they combine it with a multilayer perceptron (MLP) layer. In our model, we used the MLP in the dense layers.…”

Section: Related Workmentioning

confidence: 99%

The Golem: A General Data-Driven Model for Oil & Gas Forecasting Based on Recurrent Neural Networks

Martínez

Rocha

2023

IEEE Access

View full text Add to dashboard Cite

Oil & gas forecasting is one of the most critical issues in reservoir management. Physics-based simulations are the most common models used for production forecasts in oilfields. Previous works based on Machine Learning (ML) developed models focused on the oil rate as unique target variable, a forecasting by one-day output , and just one class of reservoir (synthetic or actual). This work introduces a general data-driven model based on Recurrent Neural Networks to forecast an adaptive sequence of timestamps for the complete production rates (oil, gas, and water), and we also included the wellbore pressure as target variable, for both classes of reservoirs as actual as synthetic. The first dataset was obtained from the synthetic benchmark UNISIM-II-H, which simulates a carbonate reservoir in the Brazilian pre-salt; the second dataset is from an actual reservoir, the Volve oilfield, a decommissioned reservoir in the Norwegian North Sea. The forecasting is calculated using an input sequence of daily values from the historical record of the production rates and the pressure; the output is also a set of the values to the next sequence of days for one selected production variable (oil, gas, water, or pressure). The size of both input and output sets is adaptive and its adjustment depends on the dataset size and the production time. We built the model and compared it between the Long Short-Term Memory (LSTM) and the Gated Recurrent Unit (GRU) implementations. We tuned the architectural parameters of the model, the input size of historical records, and the output forecasting days. We performed the training/testing procedures with several sizes for the training dataset from the target wellbore and tested with the remaining data to evaluate the model stability. We adopted the Symmetric Mean Absolute Percentage Error (SMAPE) and the coefficient of determination r-square (R 2 ) metrics to compare our forecasting values to the production rates and the pressure, most of the results for both synthetic and actual oilfields exhibited that the model can follow an accurate trend of the production rates and the pressure; and the output values are approximated. Forecasting values from the designed model exhibited closer values when compared to the expected data from the wellbores in most of the experiments, some cases exhibited an SMAPE lower than 2 and R 2 up to 0.99. The model can learn the behavior of each production variable according to the training set and the forecasting output can be adapted for a set of several timestamps.

show abstract

Section: Related Workmentioning

confidence: 99%

The Golem: A General Data-Driven Model for Oil & Gas Forecasting Based on Recurrent Neural Networks

Martínez

Rocha

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Qu et al [14] proposed a physics-informed MLP which could combine information regarding the static parameters of a fractured well with the input variables to predict fracture parameters. Yang et al [15] developed a hybrid NN called GRU-MLP. They used MLP to combine the static parameters of hydraulic fractures with the production predicted by GRU, so that the production predicted by MLP was physically constrained and had a lower bias.…”

Section: Review Of Researchmentioning

confidence: 99%

A Physics-Informed Neural Network Approach for Surrogating a Numerical Simulation of Fractured Horizontal Well Production Prediction

Jin,

Xia,

Jiang

2023

Energies

View full text Add to dashboard Cite

With the popularity of deep learning (DL), more and more studies are focusing on replacing time-consuming numerical simulations with efficient surrogate models to predict the production of multi-stage fractured horizontal wells. Previous studies on constructing surrogate models for the prediction of the production of fractured horizontal wells often relied on directly applying existing deep learning architectures without incorporating physical constraints into the model. When dealing with the large number of variables necessary for characterizing the properties of fractures, the input variables of proxy models are often oversimplified; meanwhile, lots of physical information is lost. Consequently, predictions are sometimes physically inconsistent with the underlying principles of the domain. In this study, by modifying the traditional Seq2Seq (LSTM–LSTM) deep learning architecture, a physics-informed encoder–decoder (PIED) architecture was developed to surrogate the numerical simulation codes for predicting the production of horizontal wells with unequal-length intersecting hydraulic fractures on a 2D plane. The encoder is a LSTM network, and the decoder consists of LSTM and fully connected layers. The attention algorithm is also applied in the Seq2Seq architecture. The PIED model’s encoder is capable of extracting the physical information related to fractures. And the attention module effectively passes on the most relevant physical information related to production to the decoder during the training process. By modifying Seq2Seq architecture, the decoder of the PIED incorporates the intermediate input, which is the constant production time, along with the extracted physical information to predict production values. The PIED model excels in extracting sufficient physical information from high-dimensional inputs while ensuring the integrity of the production time information. By considering the physical constraints, the model predicts production values with improved accuracy and generalization capabilities. In addition, a multi-layer perceptron (MLP) which is broadly used as a proxy model; a regular Seq2Seq model (LSTM–Attention–LSTM); and the PIED were compared via a case study, and their MAE values were shown to be 241.76, 184.07, 168.81, respectively. Therefore, the proposed model has higher accuracy and better generalization ability. In the case study, a comparative experiment was conducted by comparing LSTM–MLP (with an MAE of 221.50) and LSTM–LSTM to demonstrate that using LSTM as the decoder structure is better for predicting production series. Moreover, in the task of predicting production sequences, LSTM outperforms MLP. The Seq2Seq architecture demonstrated excellent performance in this problem, and it achieved a 48.4% reduction in MSE compared to MLP. Meanwhile, the time cost for build datasets was considered, and the proposed model was found to be capable of training in a small dataset (e.g., in the case study, 3 days were used to generate 450 samples for training.); thus, the proposed model has a certain degree of practicality.

show abstract

“…With the rapid development of AI, machine learning (ML) algorithms have been widely applied in petroleum engineering, including reservoir engineering, drilling, completion, production, etc. [15][16][17], and have broad application prospects. Production prediction is an important application of ML algorithms in oil and gas development.…”

Section: Introductionmentioning

confidence: 99%

A Combined Gated Recurrent Unit and Multi-Layer Perception Neural Network Model for Predicting Shale Gas Production

Qin

Liu

et al. 2023

Processes

Self Cite

View full text Add to dashboard Cite

Shale gas plays an important role in supplementing energy demand and reducing carbon footprint. A precise and effective prediction of shale gas production is important for optimizing completion parameters. This paper established a gated recurrent unit and multilayer perceptron combined neural network (GRU-MLP model) to forecast multistage fractured horizontal shale gas well production. A nondominated sorting genetic algorithm II (NSGA II) was introduced into the model to enable its automatic architectural optimization. In addition, embedded discrete fracture models (EDFM) and a reservoir simulator were used to generate training datasets. Meanwhile, a sensitivity analysis was carried out to find the variable’s importance and support the history matching. The results illustrated that the GRU-MLP model can precisely and efficiently predict the productivity of multistage fractured horizontal shale gas in a rapid and effective manner. Additionally, the model fits better at peak values of shale gas production. The GRU-MLP hybrid model has a higher accuracy within an acceptable computational time range compared to recurrent neural networks (RNN), long short-term memory (LSTM), and GRU models. The mean absolute percentage error (MAPE) and root mean square percentage error (RMSPE) for shale gas production generated by GRU-MLP model were 3.90% and 3.93%, respectively, values 84.87% and 84.88% smaller than those of the GRU model. Consequently, compared with a purely data-driven method, the physics-constrained data-driven method behaved better. The main results of the study will hopefully contribute to the intelligent development of shale gas production prediction.

show abstract

A Physics-Constrained Data-Driven Workflow for Predicting Coalbed Methane Well Production Using Artificial Neural Network

Cited by 24 publications

References 54 publications

The Golem: A General Data-Driven Model for Oil & Gas Forecasting Based on Recurrent Neural Networks

The Golem: A General Data-Driven Model for Oil & Gas Forecasting Based on Recurrent Neural Networks

A Physics-Informed Neural Network Approach for Surrogating a Numerical Simulation of Fractured Horizontal Well Production Prediction

A Combined Gated Recurrent Unit and Multi-Layer Perception Neural Network Model for Predicting Shale Gas Production

Contact Info

Product

Resources

About