Neuro-Symbolic Bi-Directional Translation -- Deep Learning Explainability for Climate Tipping Point Research
This addresses the challenge of making deep learning models more interpretable for climate scientists, particularly in researching tipping points like AMOC collapse, but it appears incremental as it builds on existing neuro-symbolic AI concepts.
The authors tackled the problem of explainability and interpretability in deep learning for climate simulation by proposing a neuro-symbolic approach called NS-QAPT, which translates between domain-specific questions and executable programs to aid in climate tipping point discovery, showing early compelling results.
In recent years, there has been an increase in using deep learning for climate and weather modeling. Though results have been impressive, explainability and interpretability of deep learning models are still a challenge. A third wave of Artificial Intelligence (AI), which includes logic and reasoning, has been described as a way to address these issues. Neuro-symbolic AI is a key component of this integration of logic and reasoning with deep learning. In this work we propose a neuro-symbolic approach called Neuro-Symbolic Question-Answer Program Translator, or NS-QAPT, to address explainability and interpretability for deep learning climate simulation, applied to climate tipping point discovery. The NS-QAPT method includes a bidirectional encoder-decoder architecture that translates between domain-specific questions and executable programs used to direct the climate simulation, acting as a bridge between climate scientists and deep learning models. We show early compelling results of this translation method and introduce a domain-specific language and associated executable programs for a commonly known tipping point, the collapse of the Atlantic Meridional Overturning Circulation (AMOC).