PulseAugur
实时 15:32:58
English(EN) HLS-GPT: A Generative Pretrained Transformer (GPT) for Continental-Scale NASA Harmonized Landsat and Sentinel-2 (HLS) Reflectance Reconstruction Across All Bands on Arbitrary Dates

HLS-GPT Transformer 重建 NASA 卫星反射率数据

研究人员开发了 HLS-GPT,这是一个大规模生成式预训练 Transformer 模型,旨在重建 NASA 的 Harmonized Landsat 和 Sentinel-2 (HLS) 地表反射率数据。该模型利用分层 Transformer 架构处理不同的光谱波段配置,并对单像素时间序列进行操作。HLS-GPT 在美国本土的大量数据上进行了训练,在各种地表条件下展现出强大的重建能力,并在评估中优于传统方法和 NASA-IBM Prithvi 模型。 AI

影响 该模型提升了 AI 在处理和重建复杂卫星图像以进行环境监测方面的能力。

排序理由 该集群描述了一篇详细介绍用于卫星数据重建的新型 AI 模型的研究论文。

在 arXiv cs.CV 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.CV TIER_1 English(EN) · Junjie Li, Hankui K. Zhang, David P. Roy ·

    HLS-GPT: A Generative Pretrained Transformer (GPT) for Continental-Scale NASA Harmonized Landsat and Sentinel-2 (HLS) Reflectance Reconstruction Across All Bands on Arbitrary Dates

    arXiv:2606.18115v1 Announce Type: new Abstract: Recent deep learning methods for Landsat and Sentinel-2 reflectance time series reconstruction remain limited by restricted spectral coverage, limited geographic scalability, or patch-based designs with short temporal contexts. We p…

  2. arXiv cs.CV TIER_1 English(EN) · David P. Roy ·

    HLS-GPT: A Generative Pretrained Transformer (GPT) for Continental-Scale NASA Harmonized Landsat and Sentinel-2 (HLS) Reflectance Reconstruction Across All Bands on Arbitrary Dates

    Recent deep learning methods for Landsat and Sentinel-2 reflectance time series reconstruction remain limited by restricted spectral coverage, limited geographic scalability, or patch-based designs with short temporal contexts. We present HLS-GPT, a large-scale generative pretrai…