---
format: "aidr-story-markdown/v1"
id: "d821bdd998378180671201ad9d7e7519c57545005fbd48620c0adc72086f31d1"
canonical_url: "https://aidr.today/d821bdd9?lang=en"
title: "LLM-enhanced spatio-temporal learning for grid-level docked bike sharing demand prediction"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-06T04:00:00.000Z"
category: "Research"
topics: ["llm"]
source_urls: ["https://arxiv.org/abs/2610.03834"]
summary: "A Large Language Model drives a semantic shockwave mechanism that converts free-form urban text into quantified spatial-temporal perturbation fields, which are injected into a Zero-Inflated Adaptive Spatio-Temporal Graph Convolutional Network for grid-level docked bike sharing demand prediction."
---

# LLM\-enhanced spatio\-temporal learning for grid\-level docked bike sharing demand prediction

> [Open the canonical story](<https://aidr.today/d821bdd9?lang=en>)

**Published:** 2026-10-06T04:00:00.000Z
**Category:** Research
**Topics:** llm

## Summary

A Large Language Model drives a semantic shockwave mechanism that converts free\-form urban text into quantified spatial\-temporal perturbation fields, which are injected into a Zero\-Inflated Adaptive Spatio\-Temporal Graph Convolutional Network for grid\-level docked bike sharing demand prediction\.

## Sources

- [Story source](<https://arxiv.org/abs/2610.03834>)