Carbon Emissions Estimation and Spatiotemporal Analysis of China at City Level Based on Multi-Dimensional Data and Machine Learning

Carbon emissions caused by the massive consumption of energy have brought enormous pressure on Chinese government. Accurately and rapidly characterizing spatiotemporal characteristics city-level carbon is crucial for policy decision making. Based multi-dimensional data, including nighttime light (NTL) land use (LU) surface temperature (LST) added-value secondary industry (AVSI) a deep neural network ensemble (DNNE) model was built to analyze nonlinear relationship between data province-level emission statistics (CES) data. The were estimated, analyzed. As compared released partial cities, results showed that DNNE based could well estimate In addition, according linear trend analysis standard deviational ellipse (SDE) China from 2001 2019, we concluded changes in at city level accordance with development China’s economy. Furthermore, can provide useful reference scientific formulation, implementation, evaluation reduction policies.