融合多源大数据的城市建筑能耗碳排放时空分布与情景模拟研究

In the context of global warming，energy conservation and emission reduction in urban buildings have become an important way to control greenhouse gas emissions and combat climate changes. However, there is a serious lack of carbon emission statistics at the building scale in China's cities. Thus the assessment and prediction of carbon emission in urban buildings are of great significance for China to promote energy conservation and emission reduction and to develop low-carbon cities. Considering the existent problems in the current researches, this project will use advanced technologies, such as data mining, geographical simulation and optimization, to establish the spatio-temporal distribution and scenario prediction models for urban building carbon emissions under the influences of social economic development and building space structure by combining multi-source big data. The main contents of our project include: 1) analyzing quantificationally the influence mechanism of carbon emission intensity of urban buildings; 2) evaluating the spatio-temporal distributions of carbon emissions for various urban buildings by combining multi-source big data; 3) simulation prediction of carbon emissions in urban buildings based on system dynamics and 3D cellular automata model. Through the assessment and prediction of carbon emissions in urban buildings, this project aims to provide scientific basis and decision-making supports for formulating scientific strategies of energy development and low-carbon economic development, and implementing effective policies of energy conservation and emission reduction.

在全球变暖大背景下，建筑节能减排已成为控制温室气体排放，应对气候变化的重要途径。然而，我国城市在建筑物尺度的碳排放统计数据存在严重缺失，因此开展城市建筑碳排放的评估与预测，对我国促进建筑节能减排，发展低碳城市具有重要的意义。针对目前研究存在的问题，本项目拟引入多源大数据，利用数据挖掘、地理模拟与优化等先进技术，建立社会经济发展和城市建筑空间结构影响下的建筑能耗碳排放时空分布快速评估与情景预测模型。具体研究内容包括：1）定量分析城市建筑碳排放强度的影响机制；2）结合多源大数据评估城市不同功能类型建筑的碳排放时空分布；3）基于系统动力学与三维元胞自动机模型的城市建筑碳排放情景模拟预测。本项目旨在通过对城市建筑碳排放的评估与预测，为制定科学能源发展战略、低碳经济发展战略，实施有效的节能减排政策提供理论依据和决策参考。

在全球变暖的背景下，为了保障城市能源消耗、经济发展、环境保护的协调发展，有必要全面掌握城市建筑碳排放的实际状况，加强建筑能源领域的宏观管理和科学决策，以减少温室气体排放。本项目利用多源大数据，结合规划理论、空间模拟优化、系统动力学理论以及遥感、GIS等多项技术手段，开展了城市碳排放空间分布以及情景模拟研究，并取得以下重要成果，包括：基于夜间灯光遥感影像的城市不透水面提取与评估研究；基于随机森林模型的城市扩张三维特征时空变化及机制分析；基于面板数据模型的城市空间结构、社会经济与碳排放的关系研究；城市三维空间结构对碳排放的影响研究；耦合社会经济和空间结构因素的城市碳排放情景模拟与预测；基于FLUS-InVEST模型的中国未来土地利用变化对碳储量影响模拟。项目成果能够揭示城市空间结构对碳排放的影响机理，为建设未来可持续的低碳城市空间发展模式提供科学手段和技术支持。在项目期间共发表学术论文9 篇，培养研究生3名。