Flow Field Reconstruction with Sensor Placement Policy Learning

2026-05-13

AI Summary

This study addresses the critical challenge of high-fidelity flow field reconstruction from sparse sensor measurements under realistic constraints on sensor count. The authors propose a directional transport-aware graph neural network integrated with a two-stage constrained Proximal Policy Optimization (PPO) algorithm to jointly optimize sensor placement and reconstruction performance. This approach uniquely unifies flow directionality, information transport mechanisms, and reinforcement learning–driven constrained layout optimization within a single framework, thereby overcoming traditional reliance on two-dimensional domains, predefined governing equations, and idealized data assumptions. Evaluated under more realistic experimental conditions, the proposed method substantially outperforms existing techniques, achieving significantly higher reconstruction accuracy.

Abstract

Flow-field reconstruction from sparse sensor measurements remains a central challenge in modern fluid dynamics, as the need for high-fidelity data often conflicts with practical limits on sensor deployment. Existing deep learning-based methods have demonstrated promising results, but they typically depend on simplifying assumptions such as two-dimensional domains, predefined governing equations, synthetic datasets derived from idealized flow physics, and unconstrained sensor placement. In this work, we address these limitations by studying flow reconstruction under realistic conditions and introducing a directional transport-aware Graph Neural Network (GNN) that explicitly encodes both flow directionality and information transport. We further show that conventional sensor placement strategies frequently yield suboptimal configurations. To overcome this, we propose a novel Two-Step Constrained PPO procedure for Proximal Policy Optimization (PPO), which jointly optimizes sensor layouts by incorporating flow variability and accounts for reconstruction model's performance disparity with respect to sensor placement. We conduct comprehensive experiments under realistic assumptions to benchmark the performance of our reconstruction model and sensor placement policy. Together, they achieve significant improvements over existing methods.

Problem

• flow field reconstruction
• sensor placement
• sparse measurements
• fluid dynamics
• high-fidelity data

Innovation

• directional transport-aware GNN
• flow field reconstruction
• sensor placement policy learning
• Two-Step Constrained PPO
• realistic fluid dynamics