AI Science Tracker
EN

Long-Term Compressive Behavior Evaluation for SSC and Prediction Using Machine Learning Models with SHAP Interpretation.

Not stated in the abstract reviewed · 21 Oct 2026 · materials

Discovery

Long-Term Compressive Behavior Evaluation for SSC and Prediction Using Machine Learning Models with SHAP Interpretation.

Source check: Source checked. Not independent scientific confirmation.

Finding: Measurements through 720 days from 344 observations were used to train and evaluate BP-family, bagging and gradient-boosting models for seawater sea-sand concrete strength. Held-out predictions had reported R² values around 0.81–0.88, with age ranked highly by SHAP; the result is limited to this dataset.

Technology: BP-family neural networks; bagging; gradient boosting; SHAP

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
BP-family neural networks; bagging; gradient boosting; SHAP
Test and result
Measured compressive strength through 720 days for 344 observations; held-out model R² was about 0.81–0.88.
Limitation / still unknown
One study dataset and held-out evaluation do not establish performance across independently produced concrete mixtures or field structures.
Evidence sources and annotation context

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

Evidence sources: https://doi.org/10.3390/ma19204423

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 result-bearing material for the stated method, result and evaluation, with bibliographic version information..

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.