Table 1 Training schemes used in our ML study; scheme variants labeled with an asterisk exclude the plastic strain from the considered features

1/1*

all simulation data

all experimental data

\(\rho ,\dot{\gamma },(\varepsilon _{\mathrm {p}})\)

2/2*

subset of all data (\(88\%\))

subset of all data (\(12\%)\)

\(\rho ,\dot{\gamma },(\varepsilon _{\mathrm {p}})\)

3/3*

subset of experimental data (\(84\%\))

subset of experimental data (\(16\%\))

\(\rho ,\dot{\gamma },(\varepsilon _{\mathrm {p}})\)

4/4*

subset of simulation data (\(90\%\))

subset of simulation data (\(10\%\))

\(\rho ,\dot{\gamma },(\varepsilon _{\mathrm {p}})\)