An unsupervised shapelet-based method for quantification of nanostructured surface imaging
Bibliographic record
Abstract
Computational methods to quantify structure–property relationships of materials are lacking in comparison to the widespread availability of nanostructure image-based characterization techniques. There are several existing quantification methods to characterize self-assembled nanomaterials, however many techniques are infeasible for use in processing large-scale spatial variation and/or require significant manual image pre-processing. The use of shapelet functions to computationally quantify nanostructured materials is a promising approach that is generalized for arbitrary pattern types but the current state of the art, the response distance method, requires user/researcher supervision. This need for supervision, along with the computational complexity of the method, make it infeasible for use in fully-automated large-scale computational analysis of nanostructured surface images. The development of a fully-automated unsupervised method for quantification of nanostructured surfaces would enable the development of broadly applicable structure–property relationships for nanomaterials, leveraging large amounts of previously captured data (so-called meta-analyses). In this work, these issues with the shapelet-based response distance method are resolved through the development and validation of a multi-step machine learning process which enables unsupervised (fully-automated) analysis of nanostructure imaging. The presented method removes the need for any researcher knowledge regarding order symmetries and enables truly large-scale analysis (e.g., meta-analyses) of the vast amount of nanostructure imaging data currently available. The presented unsupervised shapelet-based response distance method also results in at least an order-of-magnitude reduction in computational complexity compared to the existing method, at the cost of some degree of generality. A software implementation of the presented unsupervised method is provided in the open-source shapelets Python package.
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 | 0.003 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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".