A BIM–CIM integrated low-carbon decision-making method for urban renewal scenarios combining NSGA-II and energy consumption simulation
BIM-CIM統合によるNSGA-IIとエネルギー消費シミュレーションを組み合わせた都市再生シナリオの低炭素意思決定手法 (AI 翻訳)
Xuejun Wang, Qibin Han
🤖 gxceed AI 要約
日本語
本論文は、BIM-CIMフレームワークにNSGA-IIとエネルギーシミュレーションを統合し、都市再生における低炭素意思決定を支援する手法を提案する。実験では、収束距離が165.40から50世代後に105.20に減少し、年間エネルギー消費量と炭素排出量に明確な相乗効果が確認された。この手法は、複数スケールのパラメータ生成と進化的探索を連携させ、データ駆動型の都市環境構成を実現する。
English
This paper proposes a BIM-CIM integrated decision-making method combining NSGA-II and energy simulation for low-carbon urban renewal. Experiments show convergence distance decreasing from 165.40 to 105.20 over 50 generations, with clear synergy between energy use and carbon emissions. The framework links multi-scale parametric generation with evolutionary search for data-driven urban design.
Unofficial AI-generated summary based on the public title and abstract. Not an official translation.
📝 gxceed 編集解説 — Why this matters
日本のGX文脈において
日本ではSSBJや建築物省エネ法の強化が進み、都市再生における低炭素化が重要課題となっている。本手法はBIM/CIMを用いた統合的アプローチを提供し、日本のスマートシティやZEB普及に貢献する可能性がある。
In the global GX context
Globally, urban renewal is a key focus for decarbonization, with BIM-CIM integration emerging as a best practice. This method provides a computational pipeline for multi-objective optimization of energy and carbon, applicable to cities adopting TCFD/ISSB-aligned climate strategies.
👥 読者別の含意
🔬研究者:This paper demonstrates a verified computational pipeline that integrates multi-scale parametric generation with evolutionary search, useful for those studying AI-driven urban energy optimization.
🏢実務担当者:Urban planners and construction firms can adopt this BIM-CIM-based method to optimize energy use and carbon emissions in renewal projects, supporting compliance with green building standards.
🏛政策担当者:Policymakers can leverage this framework to design incentives for low-carbon urban renewal and integrate it into city-level climate action plans.
📄 Abstract（原文）
Purpose To address the fragmented multi-scale spatial data and the challenge of integrating energy assessment into multi-objective optimization for urban renewal, this paper proposes a low-carbon decision-making method integrating NSGA-II and energy consumption simulation within a BIM–CIM framework. Design/methodology/approach First, a multi-objective low-carbon decision framework is established. Then, through a unified parametric approach, deep coupling between energy simulation and evolutionary optimization is achieved. Multi-level building-city parameters are bidirectionally mapped to optimization variables. A physics-based energy simulation model constructs objectives for operational energy and carbon emissions, allowing simulation results to directly guide non-dominated sorting and elitist evolution. The process ultimately outputs constraint-satisfying solutions with spatial consistency, forming a constrained Pareto optimal set. Findings Experiments show the population’s convergence distance decreased from 165.40 initially to 105.20 by the 50th generation, with continued convergence thereafter. Annual energy use and carbon emissions show clear synergy, peaking in low-carbon evaluation at 90.85 kWh/m2 and 27.80 kgCO2/m2, with a score of 0.672. Originality/value The presented framework establishes a verified computational pipeline linking multi-scale parametric generation with evolutionary search mechanisms for guiding data-driven urban environment configurations.
🔗 Provenance — このレコードを発見したソース
- openalex https://doi.org/10.1108/sasbe-02-2026-0081first seen 2026-07-13 05:53:23
🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。
gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。