Harvesting AlphaEarth: Benchmarking the Geospatial Foundation Model for Agricultural Downstream Tasks

2025-12-30

arXiv.org

AI Summary

This study addresses the lack of systematic evaluation of geospatial foundation models like AlphaEarth in agricultural downstream tasks and their comprehensive comparison against traditional remote sensing approaches. We present the first application of AlphaEarth embeddings to three major U.S. agricultural tasks—crop yield prediction, tillage practice mapping, and cover crop mapping—leveraging both public and proprietary datasets. Machine learning models based on AlphaEarth features are rigorously compared with those using conventional remote sensing features across multiple spatial scales and regions. Results demonstrate that AlphaEarth achieves strong performance in yield prediction and county-level tillage mapping when trained locally; however, it exhibits limited spatial transferability, low interpretability, and insufficient temporal sensitivity. These findings provide critical empirical insights and practical guidance for deploying foundation models in real-world agricultural applications.

Technology Category

• Computer Vision: Remote Sensing / Geospatial AI
• Machine Learning: Other Foundations of Machine Learning
• Humans and AI: Other Foundations of Human Computation & AI

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Geospatial foundation models (GFMs) have emerged as a promising approach to overcoming the limitations in existing featurization methods. More recently, Google DeepMind has introduced AlphaEarth Foundation (AEF), a GFM pre-trained using multi-source EOs across continuous time. An annual and global embedding dataset is produced using AEF that is ready for analysis and modeling. The internal experiments show that AEF embeddings have outperformed operational models in 15 EO tasks without re-training. However, those experiments are mostly about land cover and land use classification. Applying AEF and other GFMs to agricultural monitoring require an in-depth evaluation in critical agricultural downstream tasks. There is also a lack of comprehensive comparison between the AEF-based models and traditional remote sensing (RS)-based models under different scenarios, which could offer valuable guidance for researchers and practitioners. This study addresses some of these gaps by evaluating AEF embeddings in three agricultural downstream tasks in the U.S., including crop yield prediction, tillage mapping, and cover crop mapping. Datasets are compiled from both public and private sources to comprehensively evaluate AEF embeddings across tasks at different scales and locations, and RS-based models are trained as comparison models. AEF-based models generally exhibit strong performance on all tasks and are competitive with purpose-built RS-based models in yield prediction and county-level tillage mapping when trained on local data. However, we also find several limitations in current AEF embeddings, such as limited spatial transferability compared to RS-based models, low interpretability, and limited time sensitivity. These limitations recommend caution when applying AEF embeddings in agriculture, where time sensitivity, generalizability, and interpretability is important.

Problem

• geospatial foundation model
• agricultural monitoring
• remote sensing
• downstream tasks
• model evaluation

Innovation

• Geospatial Foundation Model
• AlphaEarth
• Agricultural Downstream Tasks
• Remote Sensing Benchmarking
• Crop Yield Prediction