用预训练模型从多光谱图像重建高光谱数据，提升温室气体监测能力
Multispectral to Hyperspectral using Pretrained Foundational model
- 基于Transformer的模型，利用预训练+微调策略融合多源遥感数据
- 在Sentinel-2/EnMAP和HLS-S30/EMIT数据对上实现高光谱重建
- 适合从事大气监测、遥感图像重建的研究者参考
高光谱成像提供详细的光谱信息，具有监测甲烷（CH4）和二氧化氮（NO2）等温室气体的巨大潜力。然而，其应用受限于有限的空间覆盖范围和较低的重访频率。相比之下，多光谱成像虽具备更广的空间与时间覆盖，但缺乏精确识别温室气体所需的光谱精细度。为此，本文提出基于光谱与空间-光谱变换器的模型，从多光谱输入重建高光谱数据。模型在EnMAP和EMIT数据集上进行预训练，并分别在时空对齐的（Sentinel-2, EnMAP）与（HLS-S30, EMIT）图像对上进行微调。该方法有望结合高光谱与多光谱系统的优点，增强大气监测能力。
原文摘要 · Abstract (English)
Hyperspectral imaging provides detailed spectral information, offering significant potential for monitoring greenhouse gases like CH4 and NO2. However, its application is constrained by limited spatial coverage and infrequent revisit times. In contrast, multispectral imaging delivers broader spatial and temporal coverage but lacks the spectral granularity required for precise GHG detection. To address these challenges, this study proposes Spectral and Spatial-Spectral transformer models that reconstruct hyperspectral data from multispectral inputs. The models in this paper are pretrained on EnMAP and EMIT datasets and fine-tuned on spatio-temporally aligned (Sentinel-2, EnMAP) and (HLS-S30, EMIT) image pairs respectively. Our model has the potential to enhance atmospheric monitoring by combining the strengths of hyperspectral and multispectral imaging systems.
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。