---
title: "Basin2Vec: Learning Basin-Centric Embeddings for Scalable Hydrological Modeling"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.05164v1"
permalink: "https://feed.astralor.com/items/itm_e8c4ec1ef05e522173bc157e"
published: "2026-11-03T16:36:09.000Z"
score: 57
channel: "tech"
tags: ["RAG","Basin2Vec","Learning Basin-Centric Embeddings","Scalable Hydrological Modeling","Reliable","Existing","Earth"]
---

# Basin2Vec: Learning Basin-Centric Embeddings for Scalable Hydrological Modeling

## At a glance

Reliable streamflow prediction across time and in ungauged basins requires representations that capture hydrologically relevant basin characteristics. Existing methods rely on either fixed handcrafted attributes or gene…

## Key points

- Reliable streamflow prediction across time and in ungauged basins requires representations that capture hydrologically relevant basin characteristics.
- Existing methods rely on either fixed handcrafted attributes or general-purpose Earth observation embeddings not tailored to basin structure.
- We introduce \textbf{Basin2Vec}, a self-supervised framework that learns compact basin representations from hydroclimatic and physiographic data without observed streamflow.

## Full text

Reliable streamflow prediction across time and in ungauged basins requires representations that capture hydrologically relevant basin characteristics. Existing methods rely on either fixed handcrafted attributes or general-purpose Earth observation embeddings not tailored to basin structure. We introduce \textbf{Basin2Vec}, a self-supervised framework that learns compact basin representations from hydroclimatic and physiographic data without observed streamflow. Basin2Vec organizes representation learning around basin scale and relationships across space and time. Across multiple forecasting architectures, it consistently outperforms predefined attributes and general-purpose geospatial embeddings in temporal generalization and zero-shot spatial transfer. Basin2Vec provides average relative gains of up to 8.3% temporally and achieves 3.5x the median predictive performance of the strongest baselines on unseen basins. These results demonstrate the effectiveness of basin-centric pretraining for transferable hydrologic prediction. Code is available at https://github.com/Muhammad-Talha-MT/basin2vec

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_e8c4ec1ef05e522173bc157e