Table 2.

Test Case 4: metrics of methods comparison

	NRMSE		Number of trainable parameters				Wall time (s)
	training	testing	${\mathcal{NN}}_{\mathrm{enc}}$	${\mathcal{NN}}_{\mathrm{dec}},{\mathcal{NN}}_{\mathrm{rec}}$	${\mathcal{RNN}}_{\mathrm{dyn}}$	total	offline	online
FOM								807.210
AE/ODE	6.96 ⋅ 10−2	7.83 ⋅ 10−2	594,889	597,574	1269	1193,732	75,315	0.191
AE/ODE-e2e	3.97 ⋅ 10−2	4.23 ⋅ 10−2	594,889	597,574	1269	1193,732	95,479	0.188
LDNet	7.31 ⋅ 10−3	7.57 ⋅ 10−3	0	2276	513	2789	90,349	0.139

Training and test errors obtained with the different methods, number of trainable parameters, and wall time associated with the offline phase and online phase. See caption of Fig. 1 for more details.