Response-balanced sampling relocates rather than improves accuracy in slope-stability surrogates under a fixed simulation budget

arXiv:2610.38815 · cs.CE · Submitted 2026-10-28 · Read on arXiv

cs.CE

Submitted: 2026-10-28

Updated: 2026-10-28

Comments: 36 pages, 4 figures, 5 tables, plus 82 pages of supplementary material (10 figures, 33 tables). Submitted to Data-Centric Engineering. Data: https://doi.org/10.5281/zenodo.23618253 ; code: https://github.com/bteodoru/surrogate-guided-slope-stability (release archived at https://doi.org/10.5281/zenodo.23727659)

License: http://creativecommons.org/licenses/by/4.0/

The gist: Machine-learning surrogates of slope stability learn factors of safety (FOS) that only physics-based analyses produce, so analyses are the budget to allocate.

Abstract

Machine-learning surrogates of slope stability learn factors of safety (FOS) that only physics-based analyses produce, so analyses are the budget to allocate. Because Latin hypercube sampling (LHS) of the parameters covers the FOS unevenly, a natural remedy is to choose part of the training points to even out the FOS distribution. We test this response-balanced sampling at a fixed budget. A random-forest screener trained on a 300-point LHS seed predicts the FOS of 200,000 candidates, and 300 further limit-equilibrium analyses are allocated to even out the FOS over the selection range, [0.5, 6]. The design is compared with 300 further LHS analyses over five realizations of the added points, on two test sets, under two independently tuned tree-ensemble families, with ablations throughout; an oracle drawing from 22,000 solved analyses meets the intended density exactly. The primary criterion is the log-scale root-mean-square error (log-RMSE) on the decision range, FOS in [0.5, 2), against continued LHS. Response-balanced sampling does not systematically improve accuracy; it relocates accuracy along the FOS axis, consistently across realizations, from [1, 2) to [0.5, 1), following the training density actually achieved, even when the intended density is met exactly. On the decision range no screener-selected design shows a demonstrated gain, and with known bin membership that verdict stands, in this design. Within the selection range, LHS gives [0.5, 1) 11-12% of the points against a log-uniform target's 27.9%, but [1, 2) already 35-37%: the region that is rare need not be where decisions are made.

Related papers