---
schema_version: '1.0'
id: news-20260719-349054
url: https://gotosocial.chinng-lab-srv.dev/planning-for-cooler-cities-a-multimodal-ai-framework-for-predicting-and-mitigating-urban-heat-stress-through-urban-landscape-transformation/
url_hash: 34905410b5be786d182e582949e4da34ada51ee0bc294955bdf3649a00dd4b51
canonical_url: https://gotosocial.chinng-lab-srv.dev/planning-for-cooler-cities-a-multimodal-ai-framework-for-predicting-and-mitigating-urban-heat-stress-through-urban-landscape-transformation
source: ghost-chinng-lab
category: news/science
category_raw: 科学・研究
region: JP
tags:
- 科学・研究
- 都市設計
- 気候適応
- 予測温度
- Cooler
- Stress
lang: ja
published_at: '2026-07-19T00:16:23Z'
fetched_at: '2026-07-19T03:39:23.161357Z'
updated_at: '2026-07-19T03:39:39Z'
status: published
content_hash: null
content_changed_at: null
license_note: full
summary: 都市熱環境を1m解像度で予測・緩和するマルチモーダルAIフレームワークGSM-UTCIを提案。GIS・気象データをFiLM条件付けで統合し、R2=0.9151、誤差0.41℃の高精度を実現。樹木配置・舗装材の効果を定量化でき、都市設計の意思決定支援に活用可能。気候適応と都市計画の融合を示す学術的貢献。
summary_source: llm
summary_en: Pro  multimodal AI framework GSM-UTCI to predict and mitigate urban thermal
  environments at 1m resolution. Integrated GIS and meteorological data with FiLM
  conditions to achieve high accuracy of R2=0.9151 and error 0.4 C. It is possible
  to意思決定ntify the effect of tree arrangement and paving material, and it can be used
  for decision making of urban design. Academic contributions to fusion of climate
  adaptation and urban planning。
entities:
- name: 都市設計
  type: concept
- name: FORBES JAPAN
  type: organization
- name: US cities
  type: UNKNOWN
key_facts: []
related: []
related_auto:
- name: Canada
  type: location
  weight: 1.0
title: 'Planning for Cooler Cities: A Multimodal AI Framework for Predicting and Mitigating
  Urban Heat Stress through Urban Landscape Transformation'
---

# Planning for Cooler Cities: A Multimodal AI Framework for Predicting and Mitigating Urban Heat Stress through Urban Landscape Transformation

## TL;DR
都市熱環境を1m解像度で予測・緩和するマルチモーダルAIフレームワークGSM-UTCIを提案。GIS・気象データをFiLM条件付けで統合し、R2=0.9151、誤差0.41℃の高精度を実現。樹木配置・舗装材の効果を定量化でき、都市設計の意思決定支援に活用可能。気候適応と都市計画の融合を示す学術的貢献。

## Key Points
- 科学・研究 / 都市設計 / 気候適応 / 予測温度 / Cooler / Stress

## Details
(本文なし。リンク先参照)

## Source
元記事: [Planning for Cooler Cities: A Multimodal AI Framework for Predicting and Mitigating Urban Heat Stress through Urban Landscape Transformation](https://gotosocial.chinng-lab-srv.dev/planning-for-cooler-cities-a-multimodal-ai-framework-for-predicting-and-mitigating-urban-heat-stress-through-urban-landscape-transformation/) — published 2026-07-19T00:16:23Z