# From General to Specialized: The Need for Foundational Models in Agriculture

arXiv: https://arxiv.org/abs/2507.05390 · HTML: https://mlsanity.com/paper/2507.05390/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 82 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Builds on (most cited first, 22 of 22)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2202.11214/) (2022)
- [SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery](https://mlsanity.com/paper/2207.08051/) (2022)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [Pangu-Weather: A 3D High-Resolution Model for Fast and Accurate Global Weather Forecast](https://mlsanity.com/paper/2211.02556/) (2022)
- [Scaling transformer neural networks for skillful and reliable medium-range weather forecasting](https://mlsanity.com/paper/2312.03876/) (2023)
- [Lightweight, Pre-trained Transformers for Remote Sensing Timeseries](https://mlsanity.com/paper/2304.14065/) (2023)
- [Self-attention for raw optical Satellite Time Series Classification](https://mlsanity.com/paper/1910.10536/) (2019)
- [AnySat: One Earth Observation Model for Many Resolutions, Scales, and Modalities](https://mlsanity.com/paper/2412.14123/) (2024)
- [Using satellite imagery to understand and promote sustainable development](https://mlsanity.com/paper/2010.06988/) (2020)
- [MMST-ViT: Climate Change-aware Crop Yield Prediction via Multi-Modal Spatial-Temporal Vision Transformer](https://mlsanity.com/paper/2309.09067/) (2023)
- [End-to-End Learned Early Classification of Time Series for In-Season Crop Type Mapping](https://mlsanity.com/paper/1901.10681/) (2019)
- [Coupling Machine Learning and Crop Modeling Improves Crop Yield Prediction in the US Corn Belt](https://mlsanity.com/paper/2008.04060/) (2020)
- [Embedding-based Retrieval with LLM for Effective Agriculture Information Extracting from Unstructured Data](https://mlsanity.com/paper/2308.03107/) (2023)
- [GPT-4 as an Agronomist Assistant? Answering Agriculture Exams Using Large Language Models](https://mlsanity.com/paper/2310.06225/) (2023)
- [Early- and in-season crop type mapping without current-year ground truth: generating labels from historical information via a topology-based approach](https://mlsanity.com/paper/2110.10275/) (2021)
- [Large language models can help boost food production, but be mindful of their risks](https://mlsanity.com/paper/2403.15475/) (2024)
- [On the Generalizability of Foundation Models for Crop Type Mapping](https://mlsanity.com/paper/2409.09451/) (2024)
- [MultiMAE Meets Earth Observation: Pre-training Multi-modal Multi-task Masked Autoencoders for Earth Observation Tasks](https://mlsanity.com/paper/2505.14951/) (2025)
- [Hybrid Phenology Modeling for Predicting Temperature Effects on Tree Dormancy](https://mlsanity.com/paper/2501.16848/) (2025)
- [A weakly supervised framework for high-resolution crop yield forecasts](https://mlsanity.com/paper/2205.09016/) (2022)
- [A Bayesian hierarchical framework for fusion of remote sensing data: An example with solar-induced fluorescence](https://mlsanity.com/paper/2503.03901/) (2025)

## Built on by (most cited first, 2 of 2)

- [Benchmarking foundation models for hyperspectral image classification: Application to cereal crop type mapping](https://mlsanity.com/paper/2510.11576/) (2025)
- [Foundation Models Meet Agriculture: Challenges Beyond Pretraining](https://mlsanity.com/paper/2608.30392/) (2026)

## Abstract (arXiv)

Food security remains a global concern as population grows and climate change intensifies, demanding innovative solutions for sustainable agricultural productivity. Recent advances in foundation models have demonstrated remarkable performance in remote sensing and climate sciences, and therefore offer new opportunities for agricultural monitoring. However, their application in challenges related to agriculture-such as crop type mapping, crop phenology estimation, and crop yield estimation-remains under-explored. In this work, we quantitatively evaluate existing foundational models to assess their effectivity for a representative set of agricultural tasks. From an agricultural domain perspective, we describe a requirements framework for an ideal agricultural foundation model (CropFM). We then survey and compare existing general-purpose foundational models in this framework and empirically evaluate two exemplary of them in three representative agriculture specific tasks. Finally, we highlight the need for a dedicated foundational model tailored specifically to agriculture.