Figures & data
Figure 1. Framework of a generic PINN (Karniadakis et al. Citation2021).
![Figure 1. Framework of a generic PINN (Karniadakis et al. Citation2021).](/cms/asset/285e9a9a-4368-4309-9adf-66e3c1fcf4c1/ngrk_a_2315301_f0001_oc.jpg)
Figure 2. Illustration of implementing AD based on the chain rule (Rao, Sun, and Liu Citation2021).
![Figure 2. Illustration of implementing AD based on the chain rule (Rao, Sun, and Liu Citation2021).](/cms/asset/42c5ed5f-5900-46be-b821-66aa973a6679/ngrk_a_2315301_f0002_oc.jpg)
Figure 4. Memory cell of an LSTM-based neural network (Yu et al. Citation2019).
![Figure 4. Memory cell of an LSTM-based neural network (Yu et al. Citation2019).](/cms/asset/fe8d019c-495c-434b-bb82-c562ae4bf278/ngrk_a_2315301_f0004_oc.jpg)
Table 1. Various domain decomposition methods for PINNs.
Figure 5. Framework of convolutional neural network (Zhang and Yin Citation2021).
![Figure 5. Framework of convolutional neural network (Zhang and Yin Citation2021).](/cms/asset/5793c3c7-a2fb-48d0-aa1e-09797581cc65/ngrk_a_2315301_f0005_oc.jpg)
Figure 6. Fixed sampling methods: (a) uniform; (b) normal sampling; (c) Latin hypercube sampling; (d) Sobol' sequence; (e) Halton sequence; (f) Hammersley sequence.
![Figure 6. Fixed sampling methods: (a) uniform; (b) normal sampling; (c) Latin hypercube sampling; (d) Sobol' sequence; (e) Halton sequence; (f) Hammersley sequence.](/cms/asset/07a723ce-1d1a-4e7f-98ec-978a01752dc7/ngrk_a_2315301_f0006_oc.jpg)
Data availability statement
All data that support the findings of this study are available from the corresponding author upon reasonable request.