AI Science Tracker
EN

Leveraging Large Language Models to Predict Atomic Oxygen Erosion of Polymers in Low Earth Orbit

Department of Chemical Engineering, University of California, Santa Barbara, Santa Barbara, California, USA · 22 Oct 2026 · materials

Discovery

Leveraging Large Language Models to Predict Atomic Oxygen Erosion of Polymers in Low Earth Orbit

Source check: Source checked. Not independent scientific confirmation.

Finding: On the restricted-group test, GPT-4o predicted erosion yield for polymer chemistries excluded from training; adding film thickness or layer count did not materially improve performance, indicating chemistry/exposure variables dominated those bulk descriptors in this dataset. 201 historical NASA-mission measurements, 55 chemistries; random and chemistry-disjoint restricted-group evaluation, with five restricted-group splits testing 29 held-out chemistries (26 for the thickness/layer ablation). Reported OME 0.154 and log-R² 0.719. This is retrospective prediction against measurements, not prospective or new flight validation.

Technology: Fine-tuned GPT-4o predicts polymer atomic-oxygen erosion yield from polymer chemistry and exposure descriptors; the model supplies the feature-ablation evidence for the reported descriptor finding.

Family GPT-4: profile · models page

Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Fine-tuned GPT-4o predicts polymer atomic-oxygen erosion yield from polymer chemistry and exposure descriptors; the model supplies the feature-ablation evidence for the reported descriptor finding.
Test and result
On the restricted-group test, GPT-4o predicted erosion yield for polymer chemistries excluded from training; adding film thickness or layer count did not materially improve performance, indicating chemistry/exposure variables dominated those bulk descriptors in this dataset.
Limitation / still unknown
201 historical NASA-mission measurements, 55 chemistries; random and chemistry-disjoint restricted-group evaluation, with five restricted-group splits testing 29 held-out chemistries (26 for the thickness/layer ablation). Reported OME 0.154 and log-R² 0.719. This is retrospective prediction against measurements, not prospective or new flight validation.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://arxiv.org/html/2611.12910

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary source full text Methods and Results; version/date checked against bibliographic record..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse materials discoveries.

Related catalog entries

Links use documented relationships where available, plus shared catalog context. A shared topic or model family does not establish a scientific dependency.