Spatial distribution of energy consumption: Integrating climate and macro-statistics for insights from clustering and sensitivity analysis

•Temperature is the main factor causing the cooling and heating load on residential buildings.•Radiation, humidity, & wind are secondary factors causing residential cooling & heating loads.•K-means algorithm effectively clusters the comprehensive climate-energy dataset.•Climate impacts vary by cluster, tailored energy management needed. Limited comprehensive methods exist for studying spatial energy consumption distribution, integrating statistical and energy data. This paper introduces a novel approach for analyzing residential heating and cooling energy demand distribution. It employs clustering algorithms to study climate variables’ impact on energy demand distribution and assesses building energy demand intensity regionally, taking China as a case study. Initially compiling a dataset comprising climate characteristics, socioeconomic factors, and energy demand through data collection and simulation, the study compares clustering algorithms, highlighting the effectiveness of K-means in clustering high-dimensional climate-energy datasets. K-means analysis reveals temperature-based daily methods significantly affect building energy intensity, alongside factors like radiation intensity and humidity impacting regional energy demand variably. Additionally, climate’s influence on residential building energy consumption intensity varies regionally, with total energy demand influenced by population and economic factors. This paper offers insights for energy management and policy formulation.