1 code implementation • 28 Apr 2022 • Onur Bilgin, Thomas Vergutz, Siamak Mehrkanoon
In this way, the proposed GCN-FFNN model learns from two types of input representations, i. e. grid and graph data, obtained via the discretization of the PDE domain.
1 code implementation • 28 Jun 2021 • Onur Bilgin, Paweł Mąka, Thomas Vergutz, Siamak Mehrkanoon
We show that compared to the classical encoder transformer, 3D convolutional neural networks, LSTM, and Convolutional LSTM, the proposed TENT model can better learn the underlying complex pattern of the weather data for the studied temperature prediction task.