Spatial-Temporal Graph-Level Feature Embedding for Shale Gas Production Forecasting with Well Interference
Bibliographic record
Abstract
Deep-learning (DL) models have been used for production forecasting in subsurface engineering applications, but it is often assumed that each well operates independently. Graph convolutional networks (GCNs) can incorporate data from neighboring wells. However, existing spatial-temporal (ST) GCN (ST-GCN) methods are mainly used for autoregressive tasks and face limitations in predicting newly developed wells with no prior history. In this study, we introduce an ST-graph-level feature embedding (GFE) (ST-GFE) method that fully utilizes temporal neighbor interactions for newly developed wells. It enhances forecasting by integrating a non-autoregressive encoder-decoder structure and aggregating the historical data from neighboring wells into a single feature vector. This aggregated vector, merging local and contextual information, contains richer information about the studied region. We evaluate ST-GFE using a data set of 6,605 Montney shale gas wells, incorporating formation properties, fracture parameters, and production history. ST-GFE significantly improves prediction accuracy for newly developed wells compared with the purely temporal models, such as recurrent neural network–based and transformer models. ST-GFE adapts to production changes in adjacent wells, including shut-in and infill drilling activities. Additionally, the ST-GFE model treats each well and its surrounding wells as a graph, enabling batch training and significantly reducing memory usage compared with transductive GCN approaches. Furthermore, the model dynamically updates its forecasts with real-time production data, enhancing precision and relevance. The xperimental results confirm that ST-GFE effectively leverages spatio-temporal dynamics and interactions between adjacent wells, broadening its applicability to various drilling and production scenarios.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".