Monthly electricity consumption data at 1 km × 1 km grid for 280 cities in China from 2012 to 2019.

ABSTRACT: High spatio-temporal resolution estimates of electricity consumption are essential for formulating effective energy transition strategies. However, the data availability is limited by complex spatio-temporal heterogeneity and insufficient multi-source feature fusion. To address these issues, this study introduces an innovative downscaling method that combines multi-source data with machine learning and spatial interpolation techniques. The method's accuracy showed significant improvements, with determination coefficients (R²) increasing by 30.1% and 33.4% over the baseline model in two evaluation datasets. With this advanced model, we estimated monthly electricity consumption across 1 km x 1 km grid for 280 Chinese cities from 2012 to 2019. Our dataset is highly consistent with

SUBMITTER: Yan X 

PROVIDER: S-EPMC11322163 | biostudies-literature | 2024 Aug

REPOSITORIES: biostudies-literature