测试大模型嵌入在跨国家玉米产量预测中的表现，发现效果不佳。
Do Foundation Model Embeddings Improve Cross-Country Crop Yield Generalisation? A Leave-One-Country-Out Evaluation in Sub-Saharan Africa
- 用留一国交叉验证法评估嵌入特征的跨国家泛化能力
- 所有特征在跨国家预测中均出现负R²，泛化性能差
- 适合关注农业预测泛化问题的研究者参考
准确预测撒哈拉以南非洲小农户玉米产量对粮食安全规划至关重要，但现有基准多报告国内性能，高估了实际泛化能力。本文在5个非洲国家共6,404个玉米田观测数据上，采用留一国交叉验证，评估地理空间基础模型嵌入（Prithvi-EO-1.0-100M和ViT-Base）与传统哨兵-2光谱特征的性能。结果显示：国内随机交叉验证获得中等R²，但跨国家测试时所有特征表现均差，且全为负R²。冻结的Prithvi-EO嵌入未优于人工设计的光谱特征。研究认为主要瓶颈是国家间产量分布差异，而非表征质量，并公开可复现的负向基准供未来研究使用。
原文摘要 · Abstract (English)
Accurate predictions of smallholder maize yields across national boundaries are critical for food security planning in sub-Saharan Africa, yet most published benchmarks report within-country performance that overstates true generalisability. This paper evaluates whether geospatial foundation model embeddings, specifically Prithvi-EO-1.0-100M and ViT-Base, outperform traditional Sentinel-2 spectral features under a Leave-One-Country-Out cross-validation scheme on 6,404 maize field observations from five African countries. The results show a clear generalisability gap: within-country random cross-validation yields moderate R^2 values, but all feature sets perform poorly under cross-country testing, with universally negative R^2. Frozen Prithvi-EO embeddings provide no meaningful advantage over engineered spectral features for cross-country prediction in this setting. The paper argues that the main limitation is a shift in yield distribution between countries rather than representation quality and releases a reproducible negative benchmark for future work.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。