D3SAI: a data-driven platform for measuring interfacial tension using machine learning and drop shape analysis
Bibliographic record
Abstract
Abstract Interfacial tension in biphasic systems plays a key role across many industrial processes. We present a Data-Driven Drop Shape Analysis method (D3SAI) that uses XGBoost to accurately estimate interfacial tension. D3SAI uses a pendant drop image of a biphasic liquid as an input and determines the interfacial tension through image processing, feature extraction, and machine learning. The accuracy of each step has been evaluated using both synthetic and experimental pendant drops. D3SAI implements a traditional drop shape analysis approach to generate a large library of synthetic pendant drops. This step is necessary to support reliable model training. Then, certain physical properties of the drop profile are extracted to represent the shape characteristics of the pendant drops. The extracted features are used to train the XGBoost model to predict interfacial tension. Using drop features rather than coordinates significantly reduces the input size and as a result the cost of computation in the training process. This makes D3SAI easier to retrain on large datasets for a variety of drop shapes and applications. D3SAI estimates the interfacial tension of well-deformed drops with less than 1.2% inaccuracy. Tests on experimental images confirm that D3SAI provides consistent and accurate results, making it suitable for large-scale measurements. Moreover, D3SAI predicts the surface tension of less-deformed (circular) drops with less than 8% inaccuracy. Although less-deformed drops are not ideal for surface tension measurements, they are sometimes necessary, for example, when working with ultra-low tension systems.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".