Shale Gas Production Forecasting with Well Interference Based on Spatial-Temporal Graph Convolutional Network

Abstract One of the core assumptions of most deep learning-based data-driven models is that samples are independent. However, this assumption poses a key challenge in production forecasting - performance is influenced by well interference and reservoir connectivity. Most shale gas wells are hydraulically fractured and exist in complex fracture systems, and the neighbouring well characteristics should also be considered when constructing data-driven forecast models. Researchers have explored using the Graph Convolutional Network (GCN) to address this issue by incorporating neighbouring well characteristics into production forecasting models. However, applying GCN to field-scale studies is problematic, as it requires training on a full batch, leading to gigantic cache allocation. Additionally, the transductive nature of GCN poses challenges for direct generalization to unseen nodes. To overcome these limitations, we adopt the Graph Sampling and Aggregation (GraphSAGE) network architecture, which allows training large graphs with mini-batches and generalizing predictions for previously unseen nodes. By cooperating with the Gated Recurrent Unit (GRU) network, the proposed Spatial-Temporal (ST)- GraphSAGE model can capture cross-time relationships between the target and the neighbouring wells and generate promising prediction time series for the target wells, even if they are newly drilled wells. The data set is based on field data corresponding to 2,240 Montney shale gas wells and consists of formation properties, fracture parameters, production history and operational data. The algorithm aggregates the first-hop information to the target node for each timestep. The Encoder-Decoder (ED) architecture is employed to generate forecasts for the subsequent three-year production rate by using the one-year production history of the wells. The trained model enables the evaluation of production predictions for newly developed wells at any location. We evaluate the model's performance using P10, P50, and P90 of the test dataset's Root Mean Square Error (RMSE). Our method preserves the topological characteristics of wells and generalizes the prediction to unseen nodes while significantly reducing training complexity, making it applicable to larger oil/gas fields. By incorporating information from adjacent wells and integrating spatial-temporal data, our ST-GraphSAGE model outperforms the traditional GRU-ED model and shows enhanced interpretability.

Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.