arXiv cs.AI· Kazuma Kobayashi, Tapas Tripura, Jay Phil Yoo, Samrendra Roy, Diab Abueidda, Seid Koric, Souvik Chakraborty, Syed Bahauddin Alam·· 13 小时前AI 评分29
TRON：从稀疏传感器序列重建全球辐射场的时空神经算子
Spatiotemporal Reconstruction of Global Radiation from Sparse Sensor Sequences
AI 导读
研究者提出时空神经算子 TRON，可从稀疏间接的传感器历史数据中学习代理变量到物理场的映射。在宇宙辐射制图上，TRON 用 12 个中子监测站的历史数据重建 65。
正文 · 原文
Abstract:Much of the physical world is inaccessible to direct measurement and can be reached only through the sparse traces it leaves in other observable variables. Here we introduce the Temporal Radiation Operator Network (TRON), a spatiotemporal neural operator that learns proxy-to-field mappings, reconstructing otherwise unobserved physical fields from sparse, indirect sensor histories. For cosmic-radiation mapping, TRON reconstructs sea-level effective dose at 65,341 locations from histories of 12 neutron monitors, achieving 0.096\% mean relative $L_2$ error against EXPACS-generated reference fields in a chronologically held-out year; batched GPU inference evaluates a global field in approximately $\sim$1~ms, compared with $\sim$57.6~s for EXPACS on one CPU thread. On measured weather networks, TRON reconstructs temperature at held-out stations from thermometer or barometer histories, outperforming interpolation, calendar-based and hypsometric baselines. These results establish proxy-to-field reconstruction as a general route to recovering spatially distributed physical information beyond the direct reach of sparse sensor networks.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Signal Processing (eess.SP) |
| Cite as: | arXiv:2506.12045 [cs.LG] |
| (or arXiv:2506.12045v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2506.12045 arXiv-issued DOI via DataCite |
Submission history
From: Syed Bahauddin Alam [view email]
[v1]
Sat, 24 May 2025 16:24:10 UTC (4,063 KB)
[v2]
Sun, 6 Sep 2026 22:43:10 UTC (17,572 KB)
[v3]
Tue, 20 Oct 2026 19:27:50 UTC (6,550 KB)
来源：arXiv cs.AI · arxiv.org