When local gains fail to transfer: Frozen Earth-observation embeddings across wildfires

arXiv:2609.34602 · cs.LG · Submitted 2026-09-28 · Read on arXiv

cs.LG

Submitted: 2026-09-28

Updated: 2026-09-28

Comments: 18 pages, 5 figures, 8 tables

Code: https://github.com/ucam-eo/tessera

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Embeddings — 1× in this paper · explained in 2 episodes

Sources

• AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
• No One Knows the State of the Art in Geospatial Foundation Models
• Foundation Models for Generalist Geospatial Artificial Intelligence
• Exploring the potential of AlphaEarth and TESSERA embeddings for Fine-scale Local Climate Zone Mapping: A case study across five cities in Switzerland
• Lightweight, Pre-trained Transformers for Remote Sensing Timeseries
• Evaluating AlphaEarth Foundations Embeddings for Wildfire Susceptibility Mapping

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: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks