arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.06852cs.AIcs.CE
收藏

利用人工智能帮助科学发现气候转折点

Using Artificial Intelligence to aid Scientific Discovery of Climate Tipping Points

Johns Hopkins University Applied Physics Laboratory(约翰斯·霍普金斯大学应用物理实验室);Johns Hopkins University(约翰斯·霍普金斯大学);Duke University(杜克大学)
Jennifer Sleeman, David Chung, Chace Ashcraft, Jay Brett, Anand Gnanadesikan, Yannis Kevrekidis, Marisa Hughes, Thomas Haine, Marie-Aude Pradal, Renske Gelderlo… 展开作者

Jennifer Sleeman, David Chung, Chace Ashcraft, Jay Brett, Anand Gnanadesikan, Yannis Kevrekidis, Marisa Hughes, Thomas Haine, Marie-Aude Pradal, Renske Gelderloos, Caroline Tang, Anshu Saksena, Larry White

摘要:

我们提出了一种混合人工智能(AI)气候建模方法,使气候建模者在科学发现中使用基于深度神经网络和数学方法建模动态系统的新组合的气候目标模拟方法。模拟是以神经符号语言为基础的,既能对人工智能方法学到的东西进行问答,又能提供一种可解释的手段。我们描述了如何将这种方法应用于发现气候临界点,特别是大西洋经向翻转环流(AMOC)的崩溃。我们展示了这种方法是如何能够预测AMOC崩溃的高度准确性,使用海洋相互作用的替代气候模型。我们还展示了神经符号方法性能的初步结果之间的自然语言的问题和象征性的学习表示翻译。我们的人工智能方法显示了有希望的早期结果,可能使更快的气候临界点相关研究成为可能,否则计算是不可行的。

英文摘要:

We propose a hybrid Artificial Intelligence (AI) climate modeling approach that enables climate modelers in scientific discovery using a climate-targeted simulation methodology based on a novel combination of deep neural networks and mathematical methods for modeling dynamical systems. The simulations are grounded by a neuro-symbolic language that both enables question answering of what is learned by the AI methods and provides a means of explainability. We describe how this methodology can be applied to the discovery of climate tipping points and, in particular, the collapse of the Atlantic Meridional Overturning Circulation (AMOC). We show how this methodology is able to predict AMOC collapse with a high degree of accuracy using a surrogate climate model for ocean interaction. We also show preliminary results of neuro-symbolic method performance when translating between natural language questions and symbolically learned representations. Our AI methodology shows promising early results, potentially enabling faster climate tipping point related research that would otherwise be computationally infeasible.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑