From Proxies to Fields: Spatiotemporal Reconstruction of Global Radiation from Sparse Sensor Sequences

TL;DR

This paper introduces TRON, a neural operator architecture that accurately reconstructs global environmental fields from sparse sensor data, significantly outperforming traditional methods in speed and accuracy across various scientific domains.

Contribution

The paper presents TRON, a novel neural operator designed for inverse spatiotemporal reconstruction of environmental fields from sparse, non-uniform data, enabling fast and accurate predictions.

Findings

Achieves sub-second inference with less than 0.1% relative L2 error.

Generalizes across over 65,000 locations and 8,400 days.

Provides >58,000X speedup over Monte Carlo estimators.

Abstract

Accurate reconstruction of latent environmental fields from sparse and indirect observations is a foundational challenge across scientific domains-from atmospheric science and geophysics to public health and aerospace safety. Traditional approaches rely on physics-based simulators or dense sensor networks, both constrained by high computational cost, latency, or limited spatial coverage. We present the Temporal Radiation Operator Network (TRON), a spatiotemporal neural operator architecture designed to infer continuous global scalar fields from sequences of sparse, non-uniform proxy measurements. Unlike recent forecasting models that operate on dense, gridded inputs to predict future states, TRON addresses a more ill-posed inverse problem: reconstructing the current global field from sparse, temporally evolving sensor sequences, without access to future observations or dense labels. Demonstrated on global cosmic radiation dose reconstruction, TRON is trained on 22 years of simulation data and generalizes across 65,341 spatial locations, 8,400 days, and sequence lengths from 7 to 90 days. It achieves sub-second inference with relative L2 errors below 0.1%, representing a >58,000X speedup over Monte Carlo-based estimators. Though evaluated in the context of cosmic radiation, TRON offers a domain-agnostic framework for scientific field reconstruction from sparse data, with applications in atmospheric modeling, geophysical hazard monitoring, and real-time environmental risk forecasting.