Foundation Models Meet Agriculture: Challenges Beyond Pretraining
cs.LG
Submitted: 2026-08-31
Updated: 2026-08-31
License: http://creativecommons.org/licenses/by/4.0/
The gist: Global food security and sustainable climate action increasingly rely on robust, scalable agricultural monitoring.
Terminology
Abstract
Global food security and sustainable climate action increasingly rely on robust, scalable agricultural monitoring. Earth observation foundation models have emerged as powerful, label-efficient tools across general remote sensing domains, yet early attempts to deploy them for agricultural applications have yielded surprisingly poor results. We hypothesize that this performance gap stems from the extreme heterogeneity of agricultural landscapes and the inherent inability of current earth observation foundation models to adapt to task-specific nuances. In this work, we systematically evaluate two critical bottlenecks hindering the deployment of foundation models in agricultural tasks, benchmarking two earth observation foundation models, a foundation model designed for tabular data, and conventional supervised baselines across seven real-world agricultural datasets spanning yield prediction, phenology estimation, and crop classification. First, we identify a pretraining-deployment modality gap: agricultural downstream tasks frequently require diverse, non-imagery data modalities that earth observation foundation models are architecturally unequipped to ingest, while a foundation model built for tabular data handles this heterogeneity more naturally. Second, we formalize the agricultural task space across five structural axes to demonstrate why current models fail to generalize reliably, resulting in highly unstable model rankings across evaluation settings. By characterizing these structural and modal gaps, our insights highlight the friction between general-purpose architectures and specialized agricultural downstream data, providing a strategic roadmap for developing the next generation of domain-aware foundation models.
Sources
- AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
- TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis
- Why do tree-based models still outperform deep learning on tabular data?
- Foundation Models for Generalist Geospatial Artificial Intelligence
- TerraMind: Large-Scale Generative Multimodality for Earth Observation
- California Crop Yield Benchmark: Combining Satellite Image, Climate, Evapotranspiration, and Soil Data Layers for County-Level Yield Forecasting of Over 70 Crops
- Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution
- PANGAEA: A Global and Inclusive Benchmark for Geospatial Foundation Models
- MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation Learning
- From General to Specialized: The Need for Foundational Models in Agriculture
- Benchmarking Geospatial Foundation Models for Agriculture Applications
- GEO-Bench-2: From Performance to Capability, Rethinking Evaluation in Geospatial AI
- On the Promises and Challenges of Multimodal Foundation Models for Geographical, Environmental, Agricultural, and Urban Planning Applications
- Lightweight, Pre-trained Transformers for Remote Sensing Timeseries
- Galileo: Learning Global & Local Features of Many Remote Sensing Modalities
- Neural Plasticity-Inspired Multimodal Foundation Model for Earth Observation
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks