发表机构
Politecnico di Milano; RFF-CMCC European Institute on Economics and the Environment (EIEE); Euro-Mediterranean Center on Climate Change (CMCC)（米兰理工大学; RFF-CMCC欧洲经济与环境研究所; 欧洲地中海气候变化中心）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TerraNova是适配原生几何的基础模型，融合地球物理与社会数据，可重建密集场、适配未见变量，兼具地理空间编码能力与国家层面功能。
AI 中文摘要
人类世的核心问题是将地球物理系统与人类社会建模为一个耦合系统，但目前没有任何学习表示能覆盖两者的观测广度。我们认为该障碍源于几何层面：地球物理系统以忽略政治边界的连续场形式被测量，而社会数据则按行政单位统计；地球系统基础模型适配前者的几何结构，将其与后者耦合需对边界进行有损平均。我们提出TerraNova，这一基础模型在1024个原生几何的物理与社会记录上训练，包括512个网格化地球系统场和512个国家指标。专用编码器表示位置、国家、时间和任务，跨模态Transformer将其融合为共享时空状态，超网络生成每个查询的解码器，其证据头返回预测分布。两个对比目标耦合该表示：一是每个国家与其领土内坐标间的人口加权对齐，二是与预训练的地理空间嵌入（承载图像衍生语义）的对齐。通过该解码器读取的表示，在与专用地理空间编码器竞争力相当的同时，覆盖了后者未表示的维度（时间、海洋和不确定性），并支持国家层面的能力；冻结的主干网络可从稀疏观测重建密集场，且能在消费级硬件上数分钟内适配未见变量。
英文摘要
A defining problem of the Anthropocene is to model the physical Earth and human societies as one coupled system, yet no learned representation spans their observational breadth. We argue the obstacle is geometric: the physical Earth is measured as continuous fields that ignore political borders, whereas societies are reported for administrative units. Earth-system foundation models serve the first geometry; coupling it to the second has required lossy averaging over borders. We introduce TerraNova, a foundation model trained on 1,024 physical and societal records in their native geometries: 512 gridded Earth-system fields and 512 national indicators. Dedicated encoders represent location, country, time and task, cross-modal transformers fuse them into a shared spatiotemporal state, and a hypernetwork generates a per-query decoder whose evidential head returns a predictive distribution. Two contrastive objectives couple the representation: a population-weighted alignment between each country and coordinates in its territory, and one to pretrained geospatial embeddings carrying image-derived semantics. Read out through that decoder, the representation is competitive with purpose-built geospatial encoders while spanning axes they do not represent (time, oceans and uncertainty) and supporting country-level capabilities. The frozen backbone reconstructs dense fields from sparse observations and adapts to unseen variables in minutes on consumer hardware.
Comments32 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/
