8–12 Jun 2026
Karlsruhe Institute of Technology, Campus north
Europe/Berlin timezone

Time-Aware Conformal Uncertainty Quantification with Physics-Consistent Projection for Radioactivity-Related Time-Series Prediction in Fusion Blankets

11 Jun 2026, 12:10
20m
FTU (Karlsruhe Institute of Technology, Campus north)

FTU

Karlsruhe Institute of Technology, Campus north

Hermann-von-Helmholtz-Platz 1, 76344 Eggenstein-Leopoldshafen

Speaker

Xiaokang Zhang (Institute of Plasma Physics, Hefei Institutes of Physical Science, Chinese Academy of Sciences)

Description

Machine-learning surrogates for coupled neutronics–activation calculations (OpenMC + FISPACT-II) reduce per-sample evaluation time from ~40 min to below one second, making rapid blanket design iteration feasible. Point predictions, however, do not suffice for safety-critical decisions. Activation inventory, decay heat, and contact dose rate span more than six orders of magnitude across time scales from hours to $10^5$ years; credible uncertainty intervals are therefore indispensable.

Standard conformal prediction (CP) produces miscalibrated intervals in this setting because (i) predictive residuals are non-stationary across irradiation and cooling regimes, and (ii) physical constraints—nonnegativity and monotonic decay—invalidate coverage guarantees when enforced as post-hoc corrections. We present SC-PIML+, a physics-constrained conformal framework comprising: (1) physics-informed feature engineering with capped half-life detrending; (2) time- and phase-stratified nonconformity scoring; (3) a convex projection operator preserving nonnegativity and smoothness in log-space, applied before calibration scoring to maintain coverage validity; and (4) a cross-conformal (CV+) extension with half-life-adaptive projection policy that increases effective calibration sample size by ~30×.

We evaluate SC-PIML+ on 224 CFETR PbLi blanket geometries with 15 prediction targets in four categories: breeding isotopes ($^3$H, $^6$Li, $^7$Li), aggregate safety indicators (decay heat, total activity, contact dose rate), PbLi-origin activation products ($^{210}$Po, $^{210}$Bi, $^{203}$Hg, $^{204}$Tl, $^{207}$Bi, $^{203}$Pb), and steel-origin activation products ($^{54}$Mn, $^{60}$Co, $^{55}$Fe). In a six-method benchmark, SC-PIML+ is the only method that meets nominal 95% prediction interval coverage on all 15 targets; Split Conformal covers 12, Conformalized Quantile Regression 11, and the base SC-PIML 13. Across 20 independent random data partitions the method passes 10.5 ± 2.4 targets on average; the remaining spread stems from finite-sample calibration ($n_\text{cal} \approx 30$), not from method instability. Because the conformal calibration is decoupled from the base learner, gradient-boosted trees, MLPs, and LSTMs all run through the same pipeline without modification. An operational out-of-distribution detection metric flags extrapolation cases for automatic fallback to direct FISPACT-II evaluation.

Formatted abstract uploaded? Done.

Author

Xiaokang Zhang (Institute of Plasma Physics, Hefei Institutes of Physical Science, Chinese Academy of Sciences)

Co-authors

Shanliang Zheng (Institute of Plasma Physics, Hefei Institutes of Physical Science, Chinese Academy of Sciences) Xilong Tong (University of Science and Technology of China) Yanshi Wei (University of Science and Technology of China)

Presentation materials

There are no materials yet.