CARM: Conformal Adaptive Risk Masking for Reliable Scientific Super-Resolution
Abstract
Deep learning-based super-resolution (SR) can reconstruct fine-scale Earth-observation fields from coarse observations, but reconstruction accuracy alone does not provide a calibrated rule for identifying reliable spatial regions. Conformal Mask Calibration (CMC), built on conformal risk control, converts a spatial uncertainty score into a trust mask and controls the expected worst-case local distortion under exchangeability. However, its fixed threshold can become miscalibrated in Earth-observation streams affected by seasonality and episodic events. We propose CARM (Conformal Adaptive Risk Masking), a statistical framework for adaptive spatial risk control under temporal distribution shift. CARM maintains experts with heterogeneous update rates and aggregates their threshold proposals online using an asymmetric surrogate loss, balancing rapid adaptation to distribution changes against stability during relatively stationary periods. All updates are causal and use only mature feedback available after a fixed delay, allowing CARM to operate with any SR model that provides a spatial uncertainty score. We prove that the time-averaged mask-conditioned risk converges to at most α at an O(1/T) rate, without distributional assumptions and for any choice of aggregation weights across experts. On a daily South China Sea chlorophyll-a SR stream, CARM reduces the empirical violation rate from 43.49% to 9.38% and the moving-average exceedance frequency from 47.29% to 1.22% at α=0.10, while retaining a non-trivial trusted region. Experiments on ERA5 wind and OSTIA sea-surface temperature further show consistent relative improvements across multiple SR backbones.
Related
- Beyond χ2: Ensemble null tests for reliable scientific discovery
- Adaptive Conformal Inference through the Lens of Blackwell Approachability
- SIGMA: Symmetry-aware, Intelligent, Geometric, Multi-faced Adaptive Traffic Control for Reliable Intelligent Transportation Systems
- Conformal Bootstrap for surfaces with boundary in Liouville CFT. Part II: spectral resolution and bootstrap
- Electromechanical Domain Wall Propagation in Dielectric Elastomers: An Exact Geometric Resolution via Conformal Mapping
BibTeX
@misc{zhang2026carm,
title = {{CARM: Conformal Adaptive Risk Masking for Reliable Scientific Super-Resolution}},
author = {Guangtao Zhang and Haonan Wu and Junxuan Gao and Zhengyang Liu and Zhaoxi Zeng and Zhihao Li and Jianguo Huang and Zhiqiang Liu},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.06151},
eprint = {2611.06151},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.06151},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - CARM: Conformal Adaptive Risk Masking for Reliable Scientific Super-Resolution
AU - Guangtao Zhang
AU - Haonan Wu
AU - Junxuan Gao
AU - Zhengyang Liu
AU - Zhaoxi Zeng
AU - Zhihao Li
AU - Jianguo Huang
AU - Zhiqiang Liu
PY - 2026
DA - 2026/11/04
PB - arXiv
DO - 10.48550/arxiv.2611.06151
UR - https://arxiv.org/abs/2611.06151
AB - Deep learning-based super-resolution (SR) can reconstruct fine-scale Earth-observation fields from coarse observations, but reconstruction accuracy alone does not provide a calibrated rule for identifying reliable spatial regions. Conformal Mask Calibration (CMC), built on conformal risk control, converts a spatial uncertainty score into a trust mask and controls the expected worst-case local distortion under exchangeability. However, its fixed threshold can become miscalibrated in Earth-observation streams affected by seasonality and episodic events. We propose CARM (Conformal Adaptive Risk Masking), a statistical framework for adaptive spatial risk control under temporal distribution shift. CARM maintains experts with heterogeneous update rates and aggregates their threshold proposals online using an asymmetric surrogate loss, balancing rapid adaptation to distribution changes against stability during relatively stationary periods. All updates are causal and use only mature feedback available after a fixed delay, allowing CARM to operate with any SR model that provides a spatial uncertainty score. We prove that the time-averaged mask-conditioned risk converges to at most α at an O(1/T) rate, without distributional assumptions and for any choice of aggregation weights across experts. On a daily South China Sea chlorophyll-a SR stream, CARM reduces the empirical violation rate from 43.49% to 9.38% and the moving-average exceedance frequency from 47.29% to 1.22% at α=0.10, while retaining a non-trivial trusted region. Experiments on ERA5 wind and OSTIA sea-surface temperature further show consistent relative improvements across multiple SR backbones.
ER -