ASR-PINN: Adaptive step-size runge–kutta physics-informed neural network for multi-component reactive solute transport

Key Points

• The adaptive step-size method improves accuracy in solving solute transport equations, allowing for better predictions.
• A reduction in error rates was achieved, with notable improvements in simulation times compared to traditional methods.
• Analysis implemented an adaptive step-size Runge-Kutta approach to advance model efficiency and capacity for multi-component environments.
• Enhanced understanding of solute dynamics may lead to better applications in environmental management and chemical engineering.