Mini-JEPA基础模型舰队实现智能水文智能
Mini-JEPA Foundation Model Fleet Enables Agentic Hydrologic Intelligence
AI总结：
本文提出Mini-JEPA基础模型舰队，通过路由代理为特定问题选择传感器，提升水文分析精度，实验显示其在土壤湿度、干旱和降水预测中优于AlphaEarth。
摘要：
地理基础模型将多光谱观测压缩成密集嵌入，广泛应用于自然语言环境推理系统。单一行星级模型如Google AlphaEarth能处理广泛特征，但可能牺牲专业水文信号。此类通用模型往往不可用、昂贵且需要大规模计算。我们提出Mini-JEPAs：由小型传感器专用的联合嵌入预测架构（JEPA）基础模型组成的舰队，由路由代理咨询以处理专门问题。我们预训练了五个2200万参数的Mini-JEPAs，共享相同的视觉Transformer主干、JEPA食谱和64维输出空间，使用Sentinel-2光学、Sentinel-1 SAR、MODIS热、多时相Sentinel-2物候和地形-土壤堆栈进行预训练。每个Mini-JEPA重建与其传感器匹配的变量，交叉验证的R²达到0.97（海拔）、0.97（温度）和0.81（降水量）。五个流形在几何结构上不同，全球参与比从8.9到20.2，局部内在维度从2.3到9.0。联合地形-土壤和物候模型在土壤湿度、干旱和降水量预测中超越AlphaEarth单独使用（ΔR²最高达0.031）。路由LLM读取每种模态的参考并选择合适的传感器，对定制问题集的命中率完美。在配对LLM-法官评估中，双检索AlphaEarth和路由舰队在物理匹配问题上优于AlphaEarth单独使用（Cohen's d = 1.10，p = 0.031）。本地训练的Mini-JEPAs可以以适度的计算能力用于水文智能。
英文摘要：
Geospatial foundation models compress multispectral observations into dense embeddings increasingly used in natural-language environmental reasoning systems. A single planetary-scale model, e.g. Google AlphaEarth, handles broad characterization well but may compromise on specialized hydrologic signals. Such generalist models are also often inaccessible, expensive, and require large-scale compute. We propose Mini-JEPAs: a fleet of small sensor-specialized Joint Embedding Predictive Architecture (JEPA) foundation models consulted by a routing agent for specialized questions. We pretrained five 22M-parameter Mini-JEPAs sharing an identical Vision Transformer backbone, JEPA recipe, and 64-d output space, using Sentinel-2 optical, Sentinel-1 SAR, MODIS thermal, multi-temporal Sentinel-2 phenology, and a topography-soil stack. Each Mini-JEPA reconstructs the variable matched to its sensor, with cross-validated $R^2$ reaching 0.97 for elevation, 0.97 for temperature, and 0.81 for precipitation. The five manifolds differ in geometric structure, with global participation ratios from 8.9 to 20.2 and local intrinsic dimensionalities from 2.3 to 9.0. Joint topography-soil and phenology models add predictive value beyond AlphaEarth alone for soil moisture, aridity, and precipitation ($ΔR^2$ up to 0.031). A router LLM reads per-modality references and selects appropriate sensors with a perfect hit rate over a curated question set. In paired LLM-as-Judge evaluation, dual retrieval over AlphaEarth and the routed fleet outperforms AlphaEarth alone on physics-matched questions (Cohen's $d = 1.10$, $p = 0.031$). Locally-trained Mini-JEPAs can be operationalized for hydrologic intelligence with modest compute.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
