City type-oriented modeling electric power consumption in China using NPP-VIIRS nighttime stable light data

摘要: Abstract Accelerating urbanization has created tremendous pressure on the global environment and energy supply, making accurate estimates of use great importance. Most current models for estimating electric power consumption (EPC) from nighttime light (NTL) imagery are oversimplified, ignoring influential social economic factors. Here we propose first classifying cities by focus then separately each category’s EPC using NTL data. We tested this approach statistical employment data 198 Chinese cities, 2015 Visible Infrared Imaging Radiometer Suite (VIIRS), annual electricity statistics. used cluster analysis sector to divide into three types (industrial, service, technology education), established a linear regression model city’s EPC. Compared with estimation results before city classification (R2: 0.785), R2 modeled service education increased 0.866 0.830, respectively. However, industrial were less consistent due their more complex structure. In general, modeling helps reflect factors affecting relationship between NTL, process reasonable improving accuracy results.