评估AlphaEarth嵌入在作物分类中的应用:可分性、时间动态与跨区域迁移能力
Evaluating AlphaEarth Embeddings for Crop Classification: Separability, Temporal Dynamics, and Cross-Regional Transferability
AI总结:
本研究提出整合多维度的评估框架,对比AlphaEarth嵌入与传统特征在作物分类中的表现,发现嵌入可分性更强但跨区域迁移更弱,为特征选择提供依据。
摘要:
基于地球观测(EO)的农业监测正从像素级光谱分析转向表征驱动建模,但针对学习到的表征在空间、时间和领域泛化维度的系统评估仍有限。地理空间基础模型生成编码时空地表属性的高维嵌入,但其在农业应用中的效用仍未被充分理解。本研究提出一种与表征无关的评估框架,整合几何可分性、时间动态、空间鲁棒性与跨区域泛化能力。利用美国本土(CONUS;2017-2023年)和印度北部(2021年)的田间尺度数据,将64维AlphaEarth嵌入空间与Sentinel-2反射率、NDVI衍生物候及谐波特征进行基准测试。传统特征实现较强的线性可分性(Fisher比率),而嵌入提供更优的分布感知可分性——光谱相似对(如玉米/大豆)的Bhattacharyya和Mahalanobis距离高达一个数量级(3.9 vs. 0.10)。嵌入能独特捕捉多年作物轮作动态,可分性比达1.784,而所有工程特征的最大值为1.003,且误差的残差空间自相关性更低(平均Moran's I≈0.17)。然而,谐波和NDVI特征表现出更强的跨大陆迁移能力(美国→印度宏F1:0.493 vs. 嵌入的0.326),反映出更好的分布对齐。组合特征空间实现平衡性能,支持混合建模。这些发现揭示了表征丰富性与跨区域迁移能力之间的基本权衡,为大规模作物分类的特征选择提供结构化框架。
英文摘要:
Earth Observation (EO)-based agricultural monitoring is shifting from pixel-level spectral analysis toward representation-driven modeling, yet systematic evaluation of learned representations remains limited. Geospatial foundation models (FMs) generate high-dimensional embeddings encoding complex spatio-temporal land-surface properties, but their utility and interpretability for agricultural applications remain insufficiently understood. This study presents a representation-agnostic framework evaluating a 64-dimensional AlphaEarth embedding space against Sentinel-2 reflectance, NDVI phenology, and harmonic features across geometric separability, temporal dynamics, spatial robustness, and cross-regional generalisation 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, yielding a separability ratio of 1.784, versus a maximum of 1.003 for all engineered features. Under spatially explicit validation, embeddings exhibit lower residual spatial autocorrelation of errors (mean Moran's $I \approx 0.17$), reducing reliance on geographic proximity. However, harmonic features show stronger cross-continental transferability (US $\to$ India Macro F1: 0.493 vs. 0.326 for embeddings), with NDVI showing a similar advantage. The combined feature space yields balanced performance. These findings reveal a trade-off between representational richness and cross-region transferability, providing a framework for feature selection in large-scale crop classification.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。