Identifying the spatial pattern and driving factors of nitrate in groundwater using a novel framework of interpretable stacking ensemble learning
Source check: Source checked. Not independent scientific confirmation.
Finding: An interpretable stacking ensemble mapped nitrate concentrations from 549 groundwater samples in Eden Valley. Spatial predictions estimated that 2.46% of sandstone aquifer area exceeded the cited drinking-water threshold and that 8.74% of high-prediction areas lay outside designated vulnerable zones. These are region-specific model estimates, not causal findings or new measurements.
Technology: The learned ensemble and SHAP ranked transmissivity, baseflow index, hydraulic conductivity, arable land and soil C:N as associated predictors.
Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.
- AI contribution
- The learned ensemble and SHAP ranked transmissivity, baseflow index, hydraulic conductivity, arable land and soil C:N as associated predictors.
- Test and result
- Models were evaluated by cross-validation and on held-out 2020–2021 wells; spatial estimates were derived from the fitted ensemble.
- Limitation / still unknown
- Predictions are geographically specific and depend on available well data; they do not establish contamination sources or measurements at unsampled locations.
Evidence sources and annotation context
Evidence context (descriptions follow the cited sources; test type is a catalog classification):
Evidence sources: https://link.springer.com/article/10.1007/s10653-024-02201-1
Source checked · editorial details
The source page was checked against this entry. Independent confirmation is not assessed by this label.
Source type: paper. Paper: linked separately.
Review date: 22 Nov 2026. Review scope: Primary full text, including Methods and Results; primary publication record or first result-bearing version checked..
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 2/5 · 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.