Towards Intrinsically Calibrated Uncertainty Quantification in Industrial Data-Driven Models via Diffusion Sampler

TL;DR

This paper introduces a diffusion-based sampling method that inherently provides well-calibrated uncertainty estimates for industrial data-driven models, improving safety and decision-making.

Contribution

A novel diffusion sampler framework that produces intrinsically calibrated uncertainty estimates without post-hoc adjustments for industrial applications.

Findings

Achieves better uncertainty calibration than existing methods.

Improves predictive accuracy in synthetic and real industrial datasets.

Demonstrates scalability and practical benefits in industrial scenarios.

Abstract

In modern process industries, data-driven models are important tools for real-time monitoring when key performance indicators are difficult to measure directly. While accurate predictions are essential, reliable uncertainty quantification (UQ) is equally critical for safety, reliability, and decision-making, but remains a major challenge in current data-driven approaches. In this work, we introduce a diffusion-based posterior sampling framework that inherently produces well-calibrated predictive uncertainty via faithful posterior sampling, eliminating the need for post-hoc calibration. In extensive evaluations on synthetic distributions, the Raman-based phenylacetic acid soft sensor benchmark, and a real ammonia synthesis case study, our method achieves practical improvements over existing UQ techniques in both uncertainty calibration and predictive accuracy. These results highlight diffusion samplers as a principled and scalable paradigm for advancing uncertainty-aware modeling in industrial applications.