用时间感知网络提升臭氧卫星数据的空间分辨率
Time-aware UNet and super-resolution deep residual networks for spatial downscaling
- 在UNet和残差网络中加入时间编码模块，融合时空信息
- 在意大利臭氧数据上，精度提升且收敛速度加快
- 适合需要高精度环境监测的研究者使用
大气污染物的卫星数据通常仅以粗略空间分辨率提供，限制了其在局部环境分析与决策中的应用。空间降尺度方法旨在将粗分辨率卫星数据转化为高分辨率场。本文针对对流层臭氧数据，采用两种主流深度学习架构——超分辨率残差网络（SRDRN）和基于编码器-解码器结构的UNet，分别引入轻量级时间模块，通过正弦或径向基函数（RBF）编码观测时间，并将时间特征与空间表示融合。所提时间感知扩展在意大利臭氧降尺度案例研究中评估，结果表明，仅略微增加计算复杂度，时间模块显著提升降尺度性能与收敛速度。
原文摘要 · Abstract (English)
Satellite data of atmospheric pollutants are often available only at coarse spatial resolution, limiting their applicability in local-scale environmental analysis and decision-making. Spatial downscaling methods aim to transform the coarse satellite data into high-resolution fields. In this work, two widely used deep learning architectures, the super-resolution deep residual network (SRDRN) and the encoder-decoder-based UNet, are considered for spatial downscaling of tropospheric ozone. Both methods are extended with a lightweight temporal module, which encodes observation time using either sinusoidal or radial basis function (RBF) encoding, and fuses the temporal features with the spatial representations in the networks. The proposed time-aware extensions are evaluated against their baseline counterparts in a case study on ozone downscaling over Italy. The results suggest that, while only slightly increasing computational complexity, the temporal modules significantly improve downscaling performance and convergence speed.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。