TerraNova: A Foundation Model for the Anthropocene
Carlos Rodriguez-Pardo, Massimo Tavoni
cs.LG, cs.AI, cs.CY, econ.EM, stat.ML
Submitted: 2026-07-31
Comments: 32 pages, 16 figures. Supplementary Information (full methodological specification, ablation programme, extended results, computational cost; 157 pages) available at the project page: https://carlosrodriguezpardo.es/projects/TerraNova/
Code: https://github.com/Clay-foundation/model
Project page: https://carlosrodriguezpardo.es/projects/TerraNova
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- General Geospatial Inference with a Population Dynamics Foundation Model
- Word Embeddings: A Survey
- AlphaEarth Foundations: An embedding field model for accurate and efficient global mapping from sparse label data
- LoRA: Low-Rank Adaptation of Large Language Models
- VeRA: Vector-based Random Matrix Adaptation
- Decoupled Weight Decay Regularization
- UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
- FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators
- Neural Conditional Transport Maps
- Representation Learning with Contrastive Predictive Coding
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