Neural partial differential equations for chaotic systems

Video Abstract Video Abstract: Neural partial differential equations for chaotic systems When predicting complex systems one typically relies on differential equation which can often be incomplete, missing unknown influences or higher order effects. By augmenting the equations with artificial neural networks we can compensate these deficiencies. We show that this can be used to predict paradigmatic, high-dimensional chaotic partial differential equations even when only short and incomplete datasets are available. The forecast horizon for these high dimensional systems is about an order of magnitude larger than the length of the training data.

Automated summary

By augmenting differential equations with artificial neural networks, it is possible to predict complex systems even with short and incomplete datasets. This approach is effective for high-dimensional chaotic systems and can forecast a horizon significantly longer than the training data length.