EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Reliability-calibrated explainable machine learning for scientific interpretation under spatial, resampling, and predictor-correlation uncertainty

Chibuike Chiedozie Ibebuchi

Machine Learning: Science and Technology · 01.08.2026 · 7 (4) · 045033

DOI: 10.1088/2632-2153/ae8a13 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Machine Learning: Science and Technology, online erschienen am 27.07.2026. Verfasst von Chibuike Chiedozie Ibebuchi. Die Arbeit nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Scientific machine learning increasingly uses explainable artificial intelligence (XAI) to interpret environmental prediction models, but highly ranked predictors are not necessarily reliable explanations across spatial, resampling, model, and predictor-correlation uncertainty. Here, we introduce a reliability-calibrated XAI framework for separating predictive importance from explanation reliability in scientific machine learning. The framework combines station-held-out validation, shapley additive explanations (SHAP)-based explanations, station-level bootstrap resampling, rank stability, phase-aware directional consistency, predictor ablation, and multimodel comparison into a reliability performance index (RPI), a bounded empirical reliability score that distinguishes influential predictors from stable explanations. We demonstrate the framework using winter streamflow prediction across the Chesapeake Bay watershed, linking daily discharge observations from 51 U.S. Geological Survey stations during 1990–2024 with time-safe lagged climate-mode predictors. Across tree-based models, station-held-out seasonal predictions achieved moderate spatially transferable skill, with mean cross-validated R 2 ≈ 0.48 . The RPI framework identified September Pacific Decadal Oscillation (PDO) conditions preceding winter by approximately three months as the most spatially transferable and explanation-stable predictor. This leading ranking was retained under additive, geometric, minimum-component, and threshold-based alternative RPI formulations. In a controlled grouped benchmark with known predictor roles, RPI recovered both materially important, directionally stable, spatially transferable drivers in the top two positions across all three model classes, whereas standard SHAP importance recovered only one. Phase-aware SHAP diagnostics showed consistent directional effects across PDO phase: positive September PDO states were associated with higher predicted DJF discharge anomalies. Model-independent diagnostics supported this direction. Station-level correlations were predominantly positive, with 90.2% of stations showing positive Spearman correlations between September PDO and winter discharge anomaly. Counterfactuals also predicted higher discharge under positive PDO conditions. These results demonstrate that feature importance alone is insufficient for scientific interpretation and that reliability-calibrated XAI provides a more conservative basis for identifying explanation-stable and physically consistent machine-learning relationships.

Zitieren

APA

Ibebuchi, C. C. (2026). Reliability-calibrated explainable machine learning for scientific interpretation under spatial, resampling, and predictor-correlation uncertainty. Machine Learning: Science and Technology, 7(4), 045033. https://doi.org/10.1088/2632-2153/ae8a13

Vancouver

Ibebuchi CC. Reliability-calibrated explainable machine learning for scientific interpretation under spatial, resampling, and predictor-correlation uncertainty. Machine Learning: Science and Technology. 2026;7(4):045033. doi:10.1088/2632-2153/ae8a13

BibTeX
@article{Ibebuchi2026,
  author = {Ibebuchi, Chibuike Chiedozie},
  title = {Reliability-calibrated explainable machine learning for scientific interpretation under spatial, resampling, and predictor-correlation uncertainty},
  journal = {Machine Learning: Science and Technology},
  year = {2026},
  volume = {7},
  number = {4},
  pages = {045033},
  doi = {10.1088/2632-2153/ae8a13}
}
Kostenlos starten →