居民源2019-2023年碳排放清单产品
收藏资源简介：
居民生活消费碳排放与城市形态、社区功能密切相关，本清单产品以郑州市为研究案例，成功实现了对此类面源的精细化空间解析。通过耦合多源卫星遥感数据（如XCO₂、NO₂作为间接指标）、LandScan高精度人口网格、建筑三维信息、夜间灯光及分区县能源消费统计数据，利用XGBoost等机器学习模型，生成了2019-2023年月度、1公里分辨率的居民生活源碳排放空间分布产品。该模型能够学习碳排放与多维空间特征间的复杂非线性关系。质量验证方面，产品在宏观上与市级能源统计总量校准，在微观上利用地基观测验证了其空间分异模式的合理性。该清单产品清晰地揭示了碳排放与社区人口密度、建筑类型、收入水平等因素的关联，可用于识别高排放社区，为城市能源规划、社区节能改造、绿色建筑推广提供靶向性决策支持，未来亦可与智慧城市系统结合，探索基于碳排放感知的个性化绿色电力消费激励方案。清单产品为栅格格式。(协议共享)
Residential consumption-based carbon emissions are closely correlated with urban morphology and community functions. Taking Zhengzhou as the research case, this inventory product has successfully achieved refined spatial analysis of such non-point source carbon emissions. By coupling multi-source satellite remote sensing data (e.g., XCO₂ and NO₂ as indirect indicators), high-precision LandScan population grids, 3D building information, nighttime light data, and county-level energy consumption statistics, and leveraging machine learning models such as XGBoost, this product has generated spatially distributed residential carbon emission datasets with monthly temporal resolution and 1-kilometer spatial resolution covering the period 2019–2023. This model can learn the complex nonlinear relationships between carbon emissions and multi-dimensional spatial features. For quality validation, the product is calibrated against the total municipal energy consumption statistics at the macro scale, while the rationality of its spatial differentiation patterns is verified via ground-based observations at the micro scale. This inventory product clearly reveals the correlations between carbon emissions and factors such as community population density, building types, and income level. It can be used to identify high-emission communities, providing targeted decision-making support for urban energy planning, community energy-saving renovation, and green building promotion. In the future, it can also be integrated with smart city systems to explore personalized incentive schemes for green electricity consumption based on carbon emission perception. The inventory product is in raster format. (Shared under agreement)
