Flow Field Reconstruction with Sensor Placement Policy Learning

TL;DR

This paper introduces a flow reconstruction method using a flow-aware GNN and a joint sensor placement policy learned via a two-step PPO, addressing realistic constraints and outperforming existing approaches.

Contribution

It presents a novel GNN model that encodes flow directionality and a PPO-based sensor placement policy optimized for realistic conditions.

Findings

The proposed GNN outperforms existing models in flow reconstruction accuracy.

The joint sensor placement policy significantly improves sensor configuration effectiveness.

Experiments demonstrate substantial performance gains over traditional methods.

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.