Behind the Noise: Conformal Quantile Regression Reveals Emergent Representations

TL;DR

This paper introduces a machine learning method using conformal quantile regression ensembles to denoise scientific images, provide uncertainty estimates, and reveal interpretable latent structures without labels, aiding scientific analysis.

Contribution

It presents a novel denoising framework that uncovers meaningful emergent representations in noisy imaging data without supervision, combining uncertainty calibration with interpretability.

Findings

Effective denoising of real-world geobiochemical images

Uncovers interpretable spatial and chemical features

Supports confident scientific interpretation and experimental planning

Abstract

Scientific imaging often involves long acquisition times to obtain high-quality data, especially when probing complex, heterogeneous systems. However, reducing acquisition time to increase throughput inevitably introduces significant noise into the measurements. We present a machine learning approach that not only denoises low-quality measurements with calibrated uncertainty bounds, but also reveals emergent structure in the latent space. By using ensembles of lightweight, randomly structured neural networks trained via conformal quantile regression, our method performs reliable denoising while uncovering interpretable spatial and chemical features -- without requiring labels or segmentation. Unlike conventional approaches focused solely on image restoration, our framework leverages the denoising process itself to drive the emergence of meaningful representations. We validate the approach on real-world geobiochemical imaging data, showing how it supports confident interpretation and guides experimental design under resource constraints.