Cedup: Spatio-Temporal Carbon Emissions Distribution Urban Patterns in China Created by Incremental Learning Modeling

Abstract

Carbon emissions reduction has become a world consensus. Cities have an essential role to play in addressing emission reductions. However, Previous studies have ignored the differences in carbon emission patterns between provinces and cities, so top-down carbon emission accounting results have been biased. Therefore, this study employed an incremental learning ensemble model and a Savitzky-Golay algorithm to create carbon emissions distribution urban patterns (CEDUP) based on nighttime light (NTL) and regional development characteristics (GDP, population, patents, industry structure). The performance of the proposed method is substantially better than its counterparts in terms of city-level estimation (R-square boosted by 20.64%). This research shows significant differences in carbon emission mechanisms between provinces and cities and that carbon emissions are time-continuous. Carbon emissions per capita are peaking in China's cities, but some heavy industrial cities are still surging. CEDUP provides accurate and dynamic monitoring of municipal emissions in China.

Keywords: Urban carbon emissions, Spatio-temporal, Incremental learning ensemble model, China