用自监督学习重建三维云结构，提升气候预测精度
3D Cloud reconstruction through geospatially-aware Masked Autoencoders
- 基于MSG卫星图像和CloudSat雷达数据，采用掩码自编码器进行无监督预训练
- 在匹配的图像-云剖面数据上微调，3D云重构精度超越U-Net等主流方法
- 引入地理空间编码，显著提升预测效果，适合气候建模与遥感研究者
云在地球辐射平衡中起关键作用，其复杂性导致气候模型存在较大不确定性。实时三维云数据对提升气候预测至关重要。本研究利用MSG/SEVIRI静止卫星影像与CloudSat/CPR云剖面雷达反射率数据，重构三维云结构。首先对未标注的MSG图像应用自监督学习方法——掩码自编码器（MAE）和地理感知的SatMAE进行预训练，随后在匹配的图像-剖面数据对上微调模型。结果表明，该方法优于当前最优的U-Net等模型，且地理空间编码进一步提升了预测性能，展示了自监督学习在云结构重建中的巨大潜力。
原文摘要 · Abstract (English)
Clouds play a key role in Earth's radiation balance with complex effects that introduce large uncertainties into climate models. Real-time 3D cloud data is essential for improving climate predictions. This study leverages geostationary imagery from MSG/SEVIRI and radar reflectivity measurements of cloud profiles from CloudSat/CPR to reconstruct 3D cloud structures. We first apply self-supervised learning (SSL) methods-Masked Autoencoders (MAE) and geospatially-aware SatMAE on unlabelled MSG images, and then fine-tune our models on matched image-profile pairs. Our approach outperforms state-of-the-art methods like U-Nets, and our geospatial encoding further improves prediction results, demonstrating the potential of SSL for cloud reconstruction.
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。