← 研踪 PaperTrailarXiv:2611.24243 · v1
End-to-End Landsat Land Surface Temperature Reconstruction with AlphaEarth Embeddings
首次提交 2026-11-18 19:21
版本更新 2026-11-18 19:21
雷达观测 2026-11-19 15:04
摘要
Land surface temperature (LST) data at Landsat's 30 m resolution is important for many applications, but cloud contamination prevents its spatially continuous observations. Here, we propose AE, an end-to-end U-Net that integrates annual temperature cycle (ATC), coarse LST from Earth system modeling, and AlphaEarth embeddings for Landsat LST reconstruction. The ATC supplies a physics-guided thermal prior, the coarse LST provides a temporal background, and the U-Net converts the embedding field into day-specific fine-scale correction using observed pixels. Experimental results on four seasonally distributed Landsat 8/9 scenes over New York City in 2022 show that AE achieves 0.78 K mean absolute error and 1.01 K root mean squared error, reducing error by 60.1% relative to baseline method without spatial correction and by 3.7% relative to the same U-Net guided by annual mean spectral reflectance. Sensitivity analysis shows stable performance regardless of distance to clear pixels and percentage of blocked pixels. Independent validation with ECOSTRESS LST shows that Earth foundation model embeddings have better performance than annual mean spectral bands for LST reconstruction.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-18 19:21 · 最新观测版本
End-to-End Landsat Land Surface Temperature Reconstruction with AlphaEarth Embeddings
Land surface temperature (LST) data at Landsat's 30 m resolution is important for many applications, but cloud contamination prevents its spatially continuous observations. Here, we propose AE, an end-to-end U-Net that integrates annual temperature cycle (ATC), coarse LST from Earth system modeling, and AlphaEarth embeddings for Landsat LST reconstruction. The ATC supplies a physics-guided thermal prior, the coarse LST provides a temporal background, and the U-Net converts the embedding field into day-specific fine-scale correction using observed pixels. Experimental results on four seasonally distributed Landsat 8/9 scenes over New York City in 2022 show that AE achieves 0.78 K mean absolute error and 1.01 K root mean squared error, reducing error by 60.1% relative to baseline method without spatial correction and by 3.7% relative to the same U-Net guided by annual mean spectral reflectance. Sensitivity analysis shows stable performance regardless of distance to clear pixels and percentage of blocked pixels. Independent validation with ECOSTRESS LST shows that Earth foundation model embeddings have better performance than annual mean spectral bands for LST reconstruction.
查看此版本解读 →查看此版本原文 ↗