从开普勒到牛顿:可解释的人工智能在科学发现中的作用(CS)

观察—假设—预测—实验循环的研究范式已经被研究人员实践了多年的科学发现。然而，随着大规模和小规模科学研究中的数据爆炸，有时很难手动分析数据并提出新的假设来驱动科学发现的周期。

本文介绍了一种可解释的人工智能辅助科学发现范式。关键是使用可解释AI (XAI)来帮助导出数据或模型解释和科学发现。我们展示了如何将计算和数据密集型方法——以及实验和理论方法——无缝集成到科学研究中。为了展示人工智能辅助科学发现的过程，并向人类历史上最伟大的思想家致敬，我们展示了(可解释的)人工智能如何通过第谷·布拉赫的天文观测数据重新发现开普勒的行星运动定律和牛顿的万有引力定律，他的作品引领了16-17世纪的科学革命。这项工作也强调了可解释AI(与黑箱AI相比)在科学发现中的重要性，它帮助人类预防或更好地为未来可能发生的技术奇点做好准备。

原文题目：From Kepler to Newton: the Role of Explainable AI in Science Discovery

原文：The research paradigm of the Observation--Hypothesis--Prediction--Experimentation loop has been practiced by researchers for years towards scientific discovery. However, with the data explosion in both mega-scale and milli-scale scientific research, it has been sometimes very difficult to manually analyze the data and propose new hypothesis to drive the cycle for scientific discovery.

In this paper, we introduce an Explainable AI-assisted paradigm for science discovery. The key is to use Explainable AI (XAI) to help derive data or model interpretations and science discoveries. We show how computational and data-intensive methodology -- together with experimental and theoretical methodology -- can be seamlessly integrated for scientific research. To demonstrate the AI-assisted science discovery process, and to pay our respect to some of the greatest minds in human history, we show how Kepler's laws of planetary motion and Newton's law of universal gravitation can be rediscovered by (explainable) AI based on Tycho Brahe's astronomical observation data, whose works were leading the scientific revolution in the 16-17th century. This work also highlights the importance of Explainable AI (as compared to black-box AI) in science discovery to help humans prevent or better prepare for the possible technological singularity which may happen in the future.