Quantitative causality, causality-guided scientific discovery, and causal machine learning
This work addresses the problem of making causality analysis quantitative and efficient for researchers in AI and various scientific disciplines, representing a foundational advancement rather than an incremental step.
The paper tackles the challenges of incorporating causality into AI algorithms, such as vagueness and computational inefficiency, by establishing a rigorous formalism over 18 years, leading to applications in fields like geoscience, quantum mechanics, and neuroscience, with examples including the anthropogenic cause of global warming and El Niño Modoki prediction.
It has been said, arguably, that causality analysis should pave a promising way to interpretable deep learning and generalization. Incorporation of causality into artificial intelligence (AI) algorithms, however, is challenged with its vagueness, non-quantitiveness, computational inefficiency, etc. During the past 18 years, these challenges have been essentially resolved, with the establishment of a rigorous formalism of causality analysis initially motivated from atmospheric predictability. This not only opens a new field in the atmosphere-ocean science, namely, information flow, but also has led to scientific discoveries in other disciplines, such as quantum mechanics, neuroscience, financial economics, etc., through various applications. This note provides a brief review of the decade-long effort, including a list of major theoretical results, a sketch of the causal deep learning framework, and some representative real-world applications in geoscience pertaining to this journal, such as those on the anthropogenic cause of global warming, the decadal prediction of El Niño Modoki, the forecasting of an extreme drought in China, among others.