Gradient-enhanced PINN with residual unit for studying forward-inverse problems of variable coefficient equations

• Published in: Physica. D Vol. 481; p. 134764
• Main Authors: Zhou, Hui-Juan, Chen, Yong
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.11.2025
• Subjects: Data-driven solution; Function discovery; Physics-informed neural network; Residual network; Variable coefficient equation; Physics-informed neural network; Function discovery; Variable coefficient equation; Residual network; Data-driven solution

Physics-informed neural network (PINN) is a powerful emerging method for studying forward-inverse problems of partial differential equations (PDEs), even from limited sample data. Variable coefficient PDEs, which model real-world phenomena, are of considerable physical significance and research valu...