Many engineering problems involve spatial-temporal dynamics. We often forecast these by solving large sets of coupled partial differential equations, which is expensive. For applications needing a prediction quickly, this is often not feasible. Recent methods, such as neural operators or sequence-to-sequence learning, offer different ways to approach this. We are experimenting with both of these methods right now. We are also exploring using graph neural networks, which are more amenable to domains with irregular boundaries than typical convolutional neural networks, and sequence-to-sequence learning, with an LSTM in both the encoder and decoder, enabling the predicted sequence to have a different length than the input sequence. We are also looking into probabilistic approaches, that can predict the uncertainty in addition to the variable itself

Please contact me if you are interested!