D-CIPHER: Discovery of Closed-form Partial Differential Equations
This addresses the challenge of modeling natural phenomena from noisy or infrequent data for scientists, representing a novel method rather than an incremental improvement.
The paper tackles the problem of discovering closed-form partial differential equations from data, which is challenging due to equation-data mismatch and large search spaces, and demonstrates that D-CIPHER can discover many well-known equations beyond current methods.
Closed-form differential equations, including partial differential equations and higher-order ordinary differential equations, are one of the most important tools used by scientists to model and better understand natural phenomena. Discovering these equations directly from data is challenging because it requires modeling relationships between various derivatives that are not observed in the data (equation-data mismatch) and it involves searching across a huge space of possible equations. Current approaches make strong assumptions about the form of the equation and thus fail to discover many well-known systems. Moreover, many of them resolve the equation-data mismatch by estimating the derivatives, which makes them inadequate for noisy and infrequently sampled systems. To this end, we propose D-CIPHER, which is robust to measurement artifacts and can uncover a new and very general class of differential equations. We further design a novel optimization procedure, CoLLie, to help D-CIPHER search through this class efficiently. Finally, we demonstrate empirically that it can discover many well-known equations that are beyond the capabilities of current methods.