From Sparse Sensors to Continuous Fields: STRIDE for Spatiotemporal Reconstruction

2026-02-04

AI Summary

This work addresses the challenge of reconstructing high-dimensional spatiotemporal fields from sparse point sensor measurements by proposing STRIDE, a two-stage framework. First, a temporal encoder maps short-window observations into a latent state; then, a modulated implicit neural representation (INR) decoder reconstructs the continuous field at arbitrary spatiotemporal coordinates. Integrating a Fourier multi-component multilayer neural network (FMMNN) backbone with stable optimization strategies, STRIDE establishes— for the first time—theoretical connections between delayed observability and finite-dimensional embeddings, enabling generalization across trajectories, parameter configurations, and grid resolutions. Evaluated on four benchmark systems involving chaotic dynamics and wave propagation, STRIDE significantly outperforms strong baselines, achieving super-resolution reconstruction while maintaining robustness under extreme sensor sparsity and noisy conditions.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Reconstructing high-dimensional spatiotemporal fields from sparse point-sensor measurements is a central challenge in learning parametric PDE dynamics. Existing approaches often struggle to generalize across trajectories and parameter settings, or rely on discretization-tied decoders that do not naturally transfer across meshes and resolutions. We propose STRIDE (Spatio-Temporal Recurrent Implicit DEcoder), a two-stage framework that maps a short window of sensor measurements to a latent state with a temporal encoder and reconstructs the field at arbitrary query locations with a modulated implicit neural representation (INR) decoder. Using the Fourier Multi-Component and Multi-Layer Neural Network (FMMNN) as the INR backbone improves representation of complex spatial fields and yields more stable optimization than sine-based INRs. We provide a conditional theoretical justification: under stable delay observability of point measurements on a low-dimensional parametric invariant set, the reconstruction operator factors through a finite-dimensional embedding, making STRIDE-type architectures natural approximators. Experiments on four challenging benchmarks spanning chaotic dynamics and wave propagation show that STRIDE outperforms strong baselines under extremely sparse sensing, supports super-resolution, and remains robust to noise.

Problem

• spatiotemporal reconstruction
• sparse sensors
• parametric PDE dynamics
• high-dimensional fields
• generalization

Innovation

• STRIDE
• Implicit Neural Representation
• Spatiotemporal Reconstruction
• FMMNN
• Sparse Sensing