PhySense: Sensor Placement Optimization for Accurate Physics Sensing

TL;DR

PhySense introduces a joint learning framework that optimizes sensor placement and reconstructs physical fields simultaneously, significantly improving accuracy in physics sensing tasks across various benchmarks.

Contribution

It presents a novel two-stage framework combining deep learning and gradient-based optimization for sensor placement and physical field reconstruction.

Findings

Achieves state-of-the-art accuracy in physics sensing benchmarks.

Discovers informative sensor placements not previously considered.

Proves theoretical guarantees aligning with classical variance-minimization principles.

Abstract

Physics sensing plays a central role in many scientific and engineering domains, which inherently involves two coupled tasks: reconstructing dense physical fields from sparse observations and optimizing scattered sensor placements to observe maximum information. While deep learning has made rapid advances in sparse-data reconstruction, existing methods generally omit optimization of sensor placements, leaving the mutual enhancement between reconstruction and placement on the shelf. To change this suboptimal practice, we propose PhySense, a synergistic two-stage framework that learns to jointly reconstruct physical fields and to optimize sensor placements, both aiming for accurate physics sensing. The first stage involves a flow-based generative model enhanced by cross-attention to adaptively fuse sparse observations. Leveraging the reconstruction feedback, the second stage performs sensor placement via projected gradient descent to satisfy spatial constraints. We further prove that the learning objectives of the two stages are consistent with classical variance-minimization principles, providing theoretical guarantees. Extensive experiments across three challenging benchmarks, especially a 3D geometry dataset, indicate PhySense achieves state-of-the-art physics sensing accuracy and discovers informative sensor placements previously unconsidered. Code is available at this repository: https://github.com/thuml/PhySense.