fig4

Intelligent data-informed study of ionospheric TEC dynamics: learning partial differential equations via PINN, PDE-Net2, and SINDy

Figure 4. Comparison of MAE error maps of reconstructed TEC maps using PDE-Net2, PINN, and SINDy at (A) from 00:00 to 08:00 UT on March 22, 2011, (B) from 00:00 to 08:00 UT on September 23, 2011, with unit: tecU(1016 electrons/m3). MAE: Mean absolute error; TEC: total electron content; PDE: partial differential equation; PINN: physics-informed neural network; SINDy: sparse identification of nonlinear dynamics.

Intelligence & Robotics
ISSN 2770-3541 (Online)

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/

Portico

All published articles are preserved here permanently:

https://www.portico.org/publishers/oae/