Credal Wrapper for Uncertainty Modelling in Sparse Geological Data

Machine learning models for mineral exploration are trained on a few hundred sparse, expensive samples and used to decide where to drill next, so their epistemic uncertainty (EU), the part that more data could remove, matters as much as their predictions. Yet EU cannot be measured on real data, because the counterfactual that defines it is never observed, so estimators are graded by proxies such as out-of-distribution detection and calibration. We contribute a general simulation protocol that makes EU directly computable for a given model and can grade any EU estimator. It separates two estimands the literature conflates, reducible error and estimator spread, builds an oracle reference for each in a synthetic prospectivity field sampled by clustered drilling surveys, and compares uncertainty measures of an identical ensemble within each simulated world. We use it to ask when credal (imprecise-probability) measures are more faithful than Bayesian model averaging (BMA) in the sparse, low-class regime of geological classification. Three findings follow. First, the credal interval width recovers the epistemic ordering better than BMA when members are few ($\delta \rho \approx +0.06$ to $+0.07$ in rank correlation for $M\le 5$, $P<10^{-4}$), confirming the small-ensemble advantage reported for credal wrappers; the advantage vanishes by $M\approx 10$ and reverses at $M=40$. Second, the choice of credal functional matters more than the choice between credal and BMA: in binary (deposit versus barren) classification the entropy interval carries no epistemic signal ($\rho \approx 0.00$) while the interval width of the same credal set does. Third, the credal advantage does not widen as training data are thinned, so it compensates for few posterior samples rather than few data. On real drill-hole geochemistry from South Australia, a resampling oracle reproduces the first finding. The protocol applies to any EU estimator whose data-generating process can be simulated.