This study investigates whether the geospatial and multimodal features encoded in \textit{Earth Embeddings} can effectively guide deep learning (DL) regression models for regional surface height mapping. In particular, we focused on AlphaEarth Embeddings at 10 m spatial resolution and evaluated their capability to support terrain height inference using a high-quality Digital Surface Model (DSM) as reference. U-Net and U-Net++ architectures were thus employed as lightweight convolutional decoders to assess how well the geospatial information distilled in the embeddings can be translated into accurate surface height estimates. Both architectures achieved strong training performance (both with $R^2 = 0.97$), confirming that the embeddings encode informative and decodable height-related signals. On the test set, performance decreased due to distribution shifts in height frequency between training and testing areas. Nevertheless, U-Net++ shows better generalization ($R^2 = 0.84$, median difference = -2.62 m) compared with the standard U-Net ($R^2 = 0.78$, median difference = -7.22 m), suggesting enhanced robustness to distribution mismatch. While the testing RMSE (approximately 16 m for U-Net++) and residual bias highlight remaining challenges in generalization, strong correlations indicate that the embeddings capture transferable topographic patterns. Overall, the results demonstrate the promising potential of AlphaEarth Embeddings to guide DL-based height mapping workflows, particularly when combined with spatially aware convolutional architectures, while emphasizing the need to address bias for improved regional transferability.

翻译：本研究探讨了嵌入在《地球嵌入》中的地理空间与多模态特征是否能有效指导深度学习回归模型进行区域地表高度制图。具体而言，我们聚焦于空间分辨率为10米的AlphaEarth嵌入，并利用高质量数字表面模型作为参考基准，评估其支持地形高度推断的能力。为此，我们采用U-Net和U-Net++架构作为轻量级卷积解码器，以评估嵌入中提取的地理空间信息能在多大程度上转化为准确的地表高度估计。两种架构均取得了优异的训练性能（两者$R^2$均达0.97），证实了嵌入编码了信息丰富且可解码的高度相关信号。在测试集上，由于训练与测试区域间高度频率的分布偏移，模型性能有所下降。尽管如此，与标准U-Net相比（$R^2$ = 0.78，中位数差 = -7.22米），U-Net++表现出更好的泛化能力（$R^2$ = 0.84，中位数差 = -2.62米），这表明其对分布失配具有更强的鲁棒性。虽然测试集的均方根误差（U-Net++约为16米）和残差偏差凸显了泛化方面仍存在的挑战，但强相关性表明嵌入捕获了可迁移的地形模式。总体而言，研究结果证明了AlphaEarth嵌入在指导基于深度学习的高度制图工作流程方面具有广阔潜力，尤其是在与具备空间感知能力的卷积架构结合时，同时强调了解决偏差问题以提升区域可迁移性的必要性。