Automating Surfactant Design for Enhanced Oil Recovery: Accelerating Innovation in Oil and Gas Industry
Bibliographic record
Abstract
Designing a robust surfactant formulation for chemical enhanced oil recovery (EOR) application in oil and gas industry is challenging and robust.Speed and accuracy at design stage are critical.This work presents a novel methodology distinguished by its highly automated workflow, which combines patent search, analysis, structure generation, simulation and analysis to revolutionize surfactant design for enhanced oil recovery.At its core, this work utilizes computational chemistry simulations as the primary tool for surfactant development, eliminating the need for resource-intensive experimental testing.The main goal is to measure interfacial properties and uncover insights into the intricate relationship between molecule composition, structural modifications, and oil recovery potential.This dramatic paradigm shift holds the promise of accelerating chemical development by an astounding 90%.This study is a good illustration of the difficulty behind designing a surfactant from patent information.It revolves around the automated creation and optimization of surfactant structures gathered from relevant patents.The automated pipeline generates multiple structure candidates from each patent, then systematically investigating the influence of different factors on surfactant efficacy.Together with the automated molecule parameterization, new molecules are quickly created within an hour, while simulations can be halted based on early data assessment.The structure can then be directly redesigned using the learnt information from the computation.Therefore, this iterative approach enables rapid refinements on several molecules based on computational insights in a single day.The study's remarkable outcomes are rooted in its automated design prowess.Automation remains at the forefront even when dealing with complex patent information.By harnessing the power of automation, researchers can expedite the design and testing of novel chemicals for diverse applications, spanning from oil production to demulsification.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".