Real-Time and Cloud-Based Well Monitoring, Part 2: Inflow Profiling Using Distributed Acoustic Sensing (DAS)
Bibliographic record
Abstract
Abstract The objective is to demonstrate how DAS, integrated with AI-driven acoustic diagnostics, can be used to derive high-resolution inflow profiles along the wellbore without interrupting production or relying on conventional logging tools. The approach is applicable to both vertical and horizontal wells where zonal performance differentiation is critical for optimization. The AI-based platform developed in this paper overcomes four key limitations of traditional DAS analytics. It enables real-time processing of massive data volumes, enhances spatial resolution to eliminate blind zones along the wellbore, accurately distinguishes true reservoir inflow from internal fluid motion, and reliably differentiates gas flow from other high-frequency noise sources. A novel AI-based data compression technique is employed to significantly reduce data volume, facilitating secure encryption and efficient cloud transmission. Signal processing methods are applied to extract frequency-specific responses, suppress artifacts, and identify phase- consistent patterns indicative of fluid entry points. The approach has been validated through multiple field trials and benchmarked against known well operations. Case studies from recent DAS logging campaigns illustrate the ability of the system to generate inflow profiles that align with expected production behavior across a range of reservoir conditions. In wells producing emulsions without gas co-production, the method successfully identified misleading indications of gas entry points typically misinterpreted in traditional DAS analyses. Gas typically exhibits rapid and random vibration patterns like those observed in ESPs. The AI-based platform can recognize these characteristic patterns, allowing it to determine whether a high-frequency event corresponds to actual gas entry or another source. The system also demonstrated robustness in detecting evolving flow regimes and phase changes over time, supporting its potential for continuous monitoring and post-workover evaluation. Identifying such disturbances is crucial for locating water production zones and planning workovers to block them and enhance oil production, a task the AI-based platform accomplishes by detecting phase change intervals along the well. The operator plans to use upcoming 3D seismic data to compare with the zonal phase change results along the wells and to evaluate the production response to an intervention in one of the wells discussed in this paper. This work highlights a novel integration of DAS sensing with real-time cloud computing and AI-based signal interpretation, offering a non-intrusive assistive technology to traditional production logging. Unlike conventional production logging methods that provide only periodic snapshots, DAS enables continuous, remote insights into zonal production behavior. These insights can support improved decision-making in reservoir management, artificial lift optimization, well integrity assessment, and early detection of flo0w anomalies in thermal operations.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| 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".