提出实用框架，让机器学习模型更好助力气候研究。
How Can Machine Learning Emulators Best Support Climate Science?
- 从气候与机器学习双视角构建可落地的模拟器开发框架。
- 强调易用性与任务明确性，提升模型在科研中的实际价值。
- 适合气候科学家和机器学习研究者跨领域协作参考。
几十年来，基于物理的气候模型为气候决策提供重要支持，但其应用受限于巨大的计算与技术需求。机器学习（ML）模拟器有望降低计算成本，然而在实际中，气候学家常直接跳过模拟器，而机器学习研究者则多将其作为方法展示，未能证明其实际效用。原因包括访问困难、专业知识缺乏以及对机器学习物理合理性的担忧。本文探讨了这些局限，并提出一个兼顾气候科学与机器学习视角的模拟器开发框架。我们主张设计易于采用、任务清晰且可靠性可验证的模拟器，这将推动机器学习方法在应用气候研究中的真正落地。
原文摘要 · Abstract (English)
For decades, physics-based climate models have been used to provide insights for climate decision-making. Their application is, however, constrained by significant computational and technical demands. Machine learning (ML) emulators offer a way to reduce these high computational costs; yet, it remains challenging to use ML emulators effectively in climate research. In practice, climate scientists often bypass emulators altogether, and machine learning researchers frequently develop them as methodological showcases without proving their practical utility. The reasons are diverse, ranging from limited accessibility and a lack of specialized knowledge to broader concerns about the physical grounding of ML methods. Here, we discuss limitations and introduce a framework for guiding emulator development, considering both climate science and machine learning perspectives. We argue that designing easy-to-adopt emulators that address clearly defined tasks and demonstrate their reliability is essential. This offers a promising path towards making machine-learning approaches more relevant and usable for applied climate research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。