Organizations: Financial University under the Government of the Russian Federation, Leningradsky Prospect, 49, Moscow, 109456, Russia. · The Scientific Research Institute of Goznak, Mytnaya Str. 17, Moscow, 115162, Russia. · MIREA—Russian Technological University 78 Vernadsky Avenue, Moscow, 119454, Russia. · Central Economics and Mathematics Institute of the Russian Academy of Sciences , Nakhimovsky Prospect, 47, Moscow, 117418, Russia.
The scientific computation methods development in conjunction with artificial intelligence technologies remains a hot research topic. Finding a balance between lightweight and accurate computations is a solid foundation for this direction. The study presents a neural operator based on the dynamic mode decomposition algorithm (DMD), mapping functional spaces, which combines DMD and deep learning (DL) for spatiotemporal processes efficient modeling. Solving PDEs for various initial and boundary conditions requires significant computational resources. The method suggested automatically extracts key modes and system dynamics using them to construct predictions, reducing computational costs compared to traditional numerical methods. The approach has demonstrated its efficiency through comparative analysis of performance with closest analogues DeepONet and FNO in the heat equation, Laplaces equation, and Burgers equation solutions approximation, where it achieves high reconstruction accuracy.
Figures & tables
Figure 1: Conceptual neural network architecture
Figure 2: Example implementation of neural network architecture
Parameter
Value
Number of samples
1000
Grid size
10 × 10
Number of iterations
50
Boundary value range
U∼(−10,10)
Fixed corner values
0 (Dirichlet condition)
Table 1: Data generation parameters for Laplace equation
Figure 3: Experimental results for the Laplace equation under various boundary conditions
Figure 4: Training and test loss functions for the Laplace equation
Training
Test
Epoch
Loss
Epoch
Loss
0
12.103361
0
10.639065
10
3.567372
10
3.901556
20
1.646200
20
3.254108
30
1.479754
30
3.473141
40
1.407965
40
1.460085
Table 2: Training and test losses over epochs for Laplace equation
Parameter
Value
Number of samples
1000
Spatial grid size
10 × 10
Number of time steps
50
Thermal diffusivity α
0.5
Random initial condition
Corners: U∼(−25,25)
Fixed random seed
Yes (for reproducibility)
Table 3: Data generation parameters
Figure 5: Experimental results for heat equation
Figure 6: Error functions for heat equation
Training
Test
Epoch
Loss
Epoch
Loss
0
83.191646
0
73.319000
10
2.536713
10
1.407479
20
1.244828
20
1.612512
30
1.072387
30
1.256115
40
0.866407
40
0.229214
Table 4: Heat Equation Training and Test Losses
Parameter
Value
Number of samples
1000
Grid size
10 × 10
Number of time steps
50
Initial condition range
U,V∼(−25,25)
Viscosity coefficient ν
U(0.01,0.1)
Time step Δt
0.0001
Table 5: Data generation parameters for Burgers’ equation
Figure 7: Experimental results for Burgers’ equation
Figure 8: Error functions for Burgers’ equation
Training
Test
Epoch
Loss
Epoch
Loss
0
78.371226
0
35.133656
10
0.300840
10
0.173647
20
0.250105
20
0.563705
30
0.089552
30
0.373777
40
0.066569
40
0.024333
Table 6: Burgers’ Equation Training and Test Losses