Do Foundation Model Embeddings Improve Cross-Country Crop Yield Generalisation? A Leave-One-Country-Out Evaluation in Sub-Saharan Africa

• URL: http://arxiv.org/abs/2605.08113v1
• Date: Mon, 27 Apr 2026 22:03:20 GMT
• Title: Do Foundation Model Embeddings Improve Cross-Country Crop Yield Generalisation? A Leave-One-Country-Out Evaluation in Sub-Saharan Africa
• Abstract summary: This paper evaluates whether geospatial foundation model embeddings, specifically Prithvi-EO-1.0-100M and ViT-Base, outperform traditional Sentinel-2 spectral features.<n>Results show a clear generalisability gap: within-country random cross-validation yields moderate R2 values, but all feature sets perform poorly under cross-country testing.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: 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.

Related papers

• A Modelling and Evaluation Framework for EuroCrops-Driven Sentinel-2 Crop Segmentation [78.66324246922831]
  This work presents a pipeline for generating semantic-segmentation-ready agricultural datasets from Sentinel-2 imagery and EuroCrops parcel-level annotations.<n>The dataset contains 67,337 patches from five European countries and uses a reduced taxonomy of ten crop classes plus background.<n>A four-level U-Net with Group Normalization was trained using 10 Sentinel-2 spectral bands and a composite loss combining class-weighted cross-entropy and Dice loss.
  arXiv  Detail & Related papers  (2026-05-30T11:20:29Z)
• Few-shot Cross-country Generalization of Tabular Machine Learning and Foundation Models for Childhood Anemia Prediction under Distribution Shift [1.0456326026076763]
  Childhood anemia affects around 40% of children aged 6-59 months globally.<n>We used DHS data from 16 countries across Africa, Asia, Latin America, the Caucasus, and the Middle East.<n>Child age, altitude, and height-for-age z-score as dominant predictors, followed by wealth and maternal education.
  arXiv  Detail & Related papers  (2026-05-26T06:20:20Z)
• Can Persona-Prompted LLMs Emulate Subgroup Values? An Empirical Analysis of Generalisability and Fairness in Cultural Alignment [75.88231994139132]
  We show that even state-of-the-art models like GPT-4.1 achieve only 57.4% accuracy in predicting modal preferences.<n>We find significant pre-existing performance biases, where models better emulate young, male, Chinese, and Christian personas.
  arXiv  Detail & Related papers  (2026-04-14T15:06:13Z)
• Conformal PM2.5 Mapping Under Spatial Covariate Shift: Satellite-Reanalysis Fusion for Africa's Green Industrial Transition [0.0]
  Africa's green industrialization imperative demands reliable infrastructure for monitoring air quality.<n>We present a satellite-reanalysis PM2.5 fusion system trained on 2,068,901 records from 404 monitoring locations in 29 African countries.
  arXiv  Detail & Related papers  (2026-04-05T02:17:50Z)
• Evidence-based Distributional Alignment for Large Language Models [58.65469623911573]
  We propose Evi-DA, an evidence-based alignment technique that improves the fidelity and robustness of LLM-based distribution estimation.<n>Given a target country, Evi-DA retrieves related World Values Survey items and their answer distributions, predicts a coarse Welzel value signature for each option, and infers the country-conditioned answer distribution in a structured format.
  arXiv  Detail & Related papers  (2026-03-03T03:34:06Z)
• Cross-modal Proxy Evolving for OOD Detection with Vision-Language Models [59.242742594156546]
  CoEvo is a test-time framework that performs bidirectional, sample-conditioned adaptation of both textual and visual proxies.<n>CoEvo achieves state-of-the-art performance, improving AUROC by 1.33% and reducing FPR95 by 45.98% on ImageNet-1K compared to strong negative-label baselines.
  arXiv  Detail & Related papers  (2026-01-13T12:08:26Z)
• RefineBench: Evaluating Refinement Capability of Language Models via Checklists [71.02281792867531]
  We evaluate two refinement modes: guided refinement and self-refinement.<n>In guided refinement, both proprietary LMs and large open-weight LMs can leverage targeted feedback to refine responses to near-perfect levels within five turns.<n>These findings suggest that frontier LMs require breakthroughs to self-refine their incorrect responses.
  arXiv  Detail & Related papers  (2025-11-27T07:20:52Z)
• SAFE: A Novel Approach to AI Weather Evaluation through Stratified Assessments of Forecasts over Earth [18.705966042259405]
  Stratified Assessments of Forecasts over Earth (SAFE) is a package for elucidating the stratified performance of a set of predictions made over Earth.<n>SAFE integrates various data domains to stratify by different attributes associated with geospatial gridpoints.<n>To demonstrate its importance, we utilize SAFE to benchmark a zoo of state-of-the-art AI-based weather prediction models.
  arXiv  Detail & Related papers  (2025-10-30T03:22:55Z)
• Out-of-Distribution Generalization in Climate-Aware Yield Prediction with Earth Observation Data [0.0]
  We benchmark two state-of-the-art deep learning models, GNN-RNN and MMST-ViT, under realistic out-of-distribution conditions.<n>GNN-RNN demonstrates superior generalization with positive correlations under geographic shifts, while MMST-ViT performs well in-domain but degrades sharply under OOD conditions.
  arXiv  Detail & Related papers  (2025-10-08T03:27:12Z)
• Less is More: Fewer Interpretable Region via Submodular Subset Selection [54.07758302264416]
  This paper re-models the above image attribution problem as a submodular subset selection problem. We construct a novel submodular function to discover more accurate small interpretation regions. For correctly predicted samples, the proposed method improves the Deletion and Insertion scores with an average of 4.9% and 2.5% gain relative to HSIC-Attribution.
  arXiv  Detail & Related papers  (2024-02-14T13:30:02Z)
• A weakly supervised framework for high-resolution crop yield forecasts [2.924891685949017]
  We propose a deep learning framework that uses high resolution inputs and low resolution labels to produce crop yield forecasts. The framework is calibrated by weak supervision from low resolution crop area and yield statistics.
  arXiv  Detail & Related papers  (2022-05-18T15:52:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.