Leveraging Atmospheric-Pressure Spatial Atomic Layer Deposition and Machine Learning for Nanomaterial and Device Design
Bibliographic record
Abstract
The deposition and design of nanometre-scale oxide films is an integral component of the ongoing nanomaterial revolution, from cell phones, to batteries, to photovoltaics. Atmospheric-pressure spatial atomic layer deposition (AP-SALD) and chemical vapour deposition (AP-CVD) are two techniques that show great promise for commercialization, due to their speed and the vast array of materials and stoichiometries they can produce. However, this flexibility comes at the cost of complexity; the presence of oxygen during film deposition induces defects which may have advantageous or deleterious effects dependent on the application of the film. Machine learning is a statistical technique that allows us to make sense of such complex systems of interaction, without the need for expensive ab-initio simulations. Through this work, I demonstrate our capacity to deposit entirely new materials with our lab-scale AP-SALD/CVD system, and develop several characterization methods that will permit us to leverage the flexibility of that system to maximum effect. I developed a system for measuring the resistance of our films in-situ, demonstrating the effects of atmospheric oxygen on film properties, as well as implementing machine learning into our in-situ reflectance system providing accurate real-time measurements of film thickness and band gap. Next, I designed a gaussian process regression tool to assist researchers in finding accurate optical model parameters with our spectroscopic ellipsometer, much more quickly than previously possible. Lastly, I implemented a basic computer vision tool for tracking the degradation of perovskite and calcium thin films in real-time. To my knowledge, this work represents the first time that machine learning has been leveraged to improve the deposition of films by AP-SALD and to enhance the characterization of their properties and performance.
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) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.001 | 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".