# Physically Interpretable AlphaEarth Foundation Model Embeddings Enable LLM-Based Land Surface Intelligence

arXiv: https://arxiv.org/abs/2602.10354 · HTML: https://mlsanity.com/paper/2602.10354/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 48 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data](https://mlsanity.com/paper/2507.22291/) (2025)
- [On the Opportunities and Challenges of Foundation Models for Geospatial Artificial Intelligence](https://mlsanity.com/paper/2304.06798/) (2023)
- [Foundation Models for Remote Sensing and Earth Observation: A Survey](https://mlsanity.com/paper/2410.16602/) (2024)
- [Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agents](https://mlsanity.com/paper/2509.23141/) (2025)
- [GeoGPT: Understanding and Processing Geospatial Tasks through An Autonomous GPT](https://mlsanity.com/paper/2307.07930/) (2023)
- [On the Foundations of Earth and Climate Foundation Models](https://mlsanity.com/paper/2405.04285/) (2024)
- [Empowering LLM Agents with Geospatial Awareness: Toward Grounded Reasoning for Wildfire Response](https://mlsanity.com/paper/2510.12061/) (2025)

## Built on by (most cited first, 6 of 6)

- [What on Earth is AlphaEarth? Hierarchical structure and functional interpretability for global land cover](https://mlsanity.com/paper/2603.16911/) (2026)
- [Characterizing AlphaEarth Embedding Geometry for Agentic Environmental Reasoning](https://mlsanity.com/paper/2604.18715/) (2026)
- [Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping](https://mlsanity.com/paper/2608.12663/) (2026)
- [Mini-JEPA Foundation Model Fleet Enables Agentic Hydrologic Intelligence](https://mlsanity.com/paper/2605.14120/) (2026)
- [Earth Observation Foundation Models for Terrestrial Ecohydrology: From Representation Learning to Process Inference](https://mlsanity.com/paper/2608.15282/) (2026)
- [Applying foundation model embeddings towards urban livability evaluation](https://mlsanity.com/paper/2609.09429/) (2026)

## Abstract (arXiv)

Satellite foundation models produce dense embeddings whose physical interpretability remains poorly understood, limiting their integration into environmental decision systems. Using 12.1 million samples across the Continental United States (2017--2023), we first present a comprehensive interpretability analysis of Google AlphaEarth's 64-dimensional embeddings against 26 environmental variables spanning climate, vegetation, hydrology, temperature, and terrain. Combining linear, nonlinear, and attention-based methods, we show that individual embedding dimensions map onto specific land surface properties, while the full embedding space reconstructs most environmental variables with high fidelity (12 of 26 variables exceed R2 > 0.90; temperature and elevation approach R2 = 0.97). The strongest dimension-variable relationships converge across all three analytical methods and remain robust under spatial block cross-validation (mean Delta R2 = 0.017) and temporally stable across all seven study years (mean inter-year correlation r = 0.963). Building on these validated interpretations, we then developed a Land Surface Intelligence system that implements retrieval-augmented generation over a FAISS-indexed embedding database of 12.1 million vectors, translating natural language environmental queries into satellite-grounded assessments. An LLM-as-Judge evaluation across 360 query--response cycles, using four LLMs in rotating generator, system, and judge roles, achieved weighted scores of μ = 3.74 ± 0.77 (scale 1--5), with grounding (μ = 3.93) and coherence (μ = 4.25) as the strongest criteria. Our results demonstrate that satellite foundation model embeddings are physically structured representations that can be operationalized for environmental and geospatial intelligence.