SENDAI: A Hierarchical Sparse-measurement, EfficieNt Data AssImilation Framework

TL;DR

SENDAI is a hierarchical data assimilation framework that effectively reconstructs full spatial fields from sparse sensor data by integrating simulation priors with learned corrections, outperforming existing methods especially in complex landscapes.

Contribution

The paper introduces SENDAI, a novel hierarchical sparse-measurement data assimilation framework that combines simulation priors with learned corrections for improved spatiotemporal reconstruction.

Findings

Achieves up to 185% SSIM improvement over traditional baselines.

Outperforms recent high-frequency methods by 36%.

Effectively preserves critical spatial structures and gradients.

Abstract

Bridging the gap between data-rich training regimes and observation-sparse deployment conditions remains a central challenge in spatiotemporal field reconstruction, particularly when target domains exhibit distributional shifts, heterogeneous structure, and multi-scale dynamics absent from available training data. We present SENDAI, a hierarchical Sparse-measurement, EfficieNt Data AssImilation Framework that reconstructs full spatial states from hyper sparse sensor observations by combining simulation-derived priors with learned discrepancy corrections. We demonstrate the performance on satellite remote sensing, reconstructing MODIS (Moderate Resolution Imaging Spectroradiometer) derived vegetation index fields across six globally distributed sites. Using seasonal periods as a proxy for domain shift, the framework consistently outperforms established baselines that require substantially denser observations -- SENDAI achieves a maximum SSIM improvement of 185% over traditional baselines and a 36% improvement over recent high-frequency-based methods. These gains are particularly pronounced for landscapes with sharp boundaries and sub-seasonal dynamics; more importantly, the framework effectively preserves diagnostically relevant structures -- such as field topologies, land cover discontinuities, and spatial gradients. By yielding corrections that are more structurally and spectrally separable, the reconstructed fields are better suited for downstream inference of indirectly observed variables. The results therefore highlight a lightweight and operationally viable framework for sparse-measurement reconstruction that is applicable to physically grounded inference, resource-limited deployment, and real-time monitor and control.