Data-Driven Discovery of Multifunctional Organic Polymer Aerogels by Machine Learning-Assisted Large-Scale Property Screening
Bibliographic record
Abstract
Polyimide (PI) aerogels are next-generation thermal insulation materials. Due to their intrinsic nanoporous structures, they are ultralow density and have superior thermal stability, making them important materials in fields such as aeronautics, thermal management, energy storage, and life sciences. The material properties and performance of PI aerogels are strongly correlated to the types of monomers and cross-linking agents. However, the time-consuming and costly synthesis process poses challenges in exploring new formulations of multifunctional PI aerogels with optimized properties. To discover new aerogel formulations, this research utilizes different machine learning methods to model the relationship between pristine monomers, processing conditions, and the properties of cross-linked aerogels. In addition, we have utilized machine learning to discover and predict new chemical structures via large-scale property screening. By introducing the Morgan fingerprint method, the chemical structure, including the hybrid monomer backbone, was effectively used as input for machine learning. Random forest and Gaussian process regression models were trained to estimate the density, compression modulus, and decomposition temperature. Over 1,600,000 novel PI aerogel structures were generated and screened using the trained machine learning models. Consequently, several structural candidates were identified as multifunctional PI aerogels with optimized properties and will have superior performance to those of previously reported aerogels.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| 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 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".