WGAST：基於弱監督生成網絡的時空融合每日10米地表溫度估算

WGAST: Weakly-Supervised Generative Network for Daily 10 m Land Surface Temperature Estimation via Spatio-Temporal Fusion

August 8, 2025

作者: Sofiane Bouaziz, Adel Hafiane, Raphael Canals, Rachid Nedjai

cs.AI

摘要

城市化、氣候變遷和農業壓力正日益增加對精確及時環境監測的需求。地表溫度（LST）是此背景下的一個關鍵變量，並通過遙感衛星進行反演。然而，這些系統面臨著空間與時間分辨率之間的權衡。雖然時空融合方法提供了有前景的解決方案，但少有方法能夠實現每日10米分辨率的LST估算。在本研究中，我們提出了WGAST，一種基於Terra MODIS、Landsat 8和Sentinel-2時空融合的弱監督生成網絡，用於每日10米LST估算。WGAST是首個為此任務設計的端到端深度學習框架。它採用了條件生成對抗架構，其生成器由四個階段組成：特徵提取、融合、LST重建和噪聲抑制。第一階段使用一組編碼器從輸入中提取多層次潛在表示，這些表示隨後在第二階段通過餘弦相似度、歸一化和時間注意力機制進行融合。第三階段將融合特徵解碼為高分辨率LST，接著使用高斯濾波器抑制高頻噪聲。訓練遵循基於物理平均原則的弱監督策略，並通過PatchGAN判別器進行強化。實驗表明，WGAST在定量和定性評估中均優於現有方法。與表現最佳的基線相比，WGAST平均降低了17.18%的RMSE，並提高了11.00%的SSIM。此外，WGAST對雲導致的LST具有魯棒性，並能有效捕捉細尺度熱模式，這一點已通過33個地面傳感器得到驗證。代碼可在https://github.com/Sofianebouaziz1/WGAST.git獲取。

English

Urbanization, climate change, and agricultural stress are increasing the demand for precise and timely environmental monitoring. Land Surface Temperature (LST) is a key variable in this context and is retrieved from remote sensing satellites. However, these systems face a trade-off between spatial and temporal resolution. While spatio-temporal fusion methods offer promising solutions, few have addressed the estimation of daily LST at 10 m resolution. In this study, we present WGAST, a Weakly-Supervised Generative Network for Daily 10 m LST Estimation via Spatio-Temporal Fusion of Terra MODIS, Landsat 8, and Sentinel-2. WGAST is the first end-to-end deep learning framework designed for this task. It adopts a conditional generative adversarial architecture, with a generator composed of four stages: feature extraction, fusion, LST reconstruction, and noise suppression. The first stage employs a set of encoders to extract multi-level latent representations from the inputs, which are then fused in the second stage using cosine similarity, normalization, and temporal attention mechanisms. The third stage decodes the fused features into high-resolution LST, followed by a Gaussian filter to suppress high-frequency noise. Training follows a weakly supervised strategy based on physical averaging principles and reinforced by a PatchGAN discriminator. Experiments demonstrate that WGAST outperforms existing methods in both quantitative and qualitative evaluations. Compared to the best-performing baseline, on average, WGAST reduces RMSE by 17.18% and improves SSIM by 11.00%. Furthermore, WGAST is robust to cloud-induced LST and effectively captures fine-scale thermal patterns, as validated against 33 ground-based sensors. The code is available at https://github.com/Sofianebouaziz1/WGAST.git.