AlphaEarth Embeddings 用于作物分类的系统评估
Evaluating AlphaEarth Embeddings for Crop Classification: Separability, Temporal Dynamics, and Cross-Regional Transferability
Google 的 AlphaEarth 卫星 embedding 到底好不好用？这篇研究拿美国和印度的田间数据测了，发现分类强但跨洲迁移弱，做遥感的朋友可以看看选特征的思路。
arXiv 一项研究在田间尺度数据上评估了 Google 的 64 维 AlphaEarth embedding 在作物分类中的表现。基于 2017-2023 年美国 CONUS 与 2021 年印度北部数据，embedding 在 Bhattacharyya/Mahalanobis 距离上比传统特征高最多一个数量级（玉米/大豆为 3.9 vs 0.10），并能捕捉多年轮作动态（可分性比 1.784 vs 1.003）。但在跨大陆迁移上，harmonic 与 NDVI 特征更强，美国到印度的 Macro F1 为 0.493 vs 0.326。结论是表征丰富度与跨区域可迁移性之间存在权衡，混合特征建模效果更均衡。
Evaluating AlphaEarth Embeddings for Crop Classification: Separability, Temporal Dynamics, and Cross-Regional Transferability
Earth Observation (EO)-based agricultural monitoring is shifting from pixel-level spectral analysis toward representation-driven modeling, yet systematic evaluation of learned representations across spatial, temporal, and domain-generalization dimensions remains limited. Geospatial foundation models generate high-dimensional embeddings encoding spatio-temporal land-surface properties, but their utility for agricultural applications remains insufficiently understood. This study presents a representation-agnostic evaluation framework integrating geometric separability, temporal dynamics, spatial robustness, and cross-regional generalisation. A 64-dimensional AlphaEarth embedding space is benchmarked against Sentinel-2 reflectance, NDVI-derived phenology, and harmonic features using field-scale data from the Conterminous United States (CONUS; 2017-2023) and Northern India (2021). Traditional features achieve strong linear separability (Fisher ratio), while embeddings provide superior distribution-aware separation -- Bhattacharyya and Mahalanobis distances up to an order of magnitude higher for spectrally similar pairs (e.g. Corn/Soybeans: 3.9 vs. 0.10). Embeddings uniquely capture multi-year crop rotation dynamics, reaching a separability ratio of 1.784 versus a maximum of 1.003 across all engineered features, and exhibit lower residual spatial autocorrelation of errors (mean Moran's $I \approx 0.17$). However, harmonic and NDVI features show stronger cross-continental transferability (US $\to$ India Macro F1: 0.493 vs. 0.326 for embeddings), reflecting better distributional alignment. The combined feature space yields balanced performance, supporting hybrid modeling. These findings reveal a fundamental trade-off between representational richness and cross-region transferability, providing a structured framework for feature selection in large-scale crop classification.