Given that observational and numerical climate data are being produced at
ever more prodigious rates, increasingly sophisticated and automated analysis
techniques have become essential. Deep learning is quickly becoming a standard
approach for such analyses and, while great progress is being made, major
challenges remain. Unlike commercial applications in which deep learning has
led to surprising successes, scientific data is highly complex and typically
unlabeled. Moreover, interpretability and detecting new mechanisms are key to
scientific discovery. To enhance discovery we present a complementary
physics-based, data-driven approach that exploits the causal nature of
spatiotemporal data sets generated by local dynamics (e.g. hydrodynamic flows).
We illustrate how novel patterns and coherent structures can be discovered in
cellular automata and outline the path from them to climate data.