SuperBench: A Super-Resolution Benchmark Dataset for Scientific Machine Learning

TL;DR

SuperBench is a new benchmark dataset designed to evaluate super-resolution methods on scientific data, addressing the need for standardized testing in Scientific Machine Learning to improve data fidelity and physical property preservation.

Contribution

This paper introduces SuperBench, the first comprehensive benchmark dataset for super-resolution in scientific data, facilitating validation and comparison of SR methods in SciML.

Findings

Deep learning SR methods perform well on some tasks but struggle with fine-scale features.

Limitations of current SR methods in preserving physical properties are identified.

SuperBench enables assessment of SR robustness and physics preservation in scientific data.

Abstract

Super-resolution (SR) techniques aim to enhance data resolution, enabling the retrieval of finer details, and improving the overall quality and fidelity of the data representation. There is growing interest in applying SR methods to complex spatiotemporal systems within the Scientific Machine Learning (SciML) community, with the hope of accelerating numerical simulations and/or improving forecasts in weather, climate, and related areas. However, the lack of standardized benchmark datasets for comparing and validating SR methods hinders progress and adoption in SciML. To address this, we introduce SuperBench, the first benchmark dataset featuring high-resolution datasets, including data from fluid flows, cosmology, and weather. Here, we focus on validating spatial SR performance from data-centric and physics-preserved perspectives, as well as assessing robustness to data degradation tasks. While deep learning-based SR methods (developed in the computer vision community) excel on certain tasks, despite relatively limited prior physics information, we identify limitations of these methods in accurately capturing intricate fine-scale features and preserving fundamental physical properties and constraints in scientific data. These shortcomings highlight the importance and subtlety of incorporating domain knowledge into ML models. We anticipate that SuperBench will help to advance SR methods for science.