Skip to main content

Table 4 CAE-space architecture for hypothetical dam break of Miles-Iles river

From: Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencoders

Layer

Nb of filters

Kernel size

Activation function

Output shape

Encoder-space

    

Input

–

–

–

\(10,200\times 1\)

Conv-pool

32

3–5

PReLU

\(2040\times 32\)

Conv-pool

64

3–5

PReLU

\(408\times 64\)

Flatten

–

–

–

26112

Dense

-

–

PReLU

120

Dense (output)

–

–

PReLU

\(L_{x}=50\)

Decoder-space

    

Input

–

–

–

\(L_{x}=50\)

Dense

–

–

PReLU

120

Dense

–

–

PReLU

\(26\,112\)

Reshape

–

–

–

\(408\times 64\)

Conv-Upsamp

64

3–5

PReLU

\(2040\times 64\)

Conv-Upsamp

32

3–5

PReLU

\(10200\times 32\)

Conv (output)

1

3

PReLU

\(10200\times 1\)