Top-Down Finer-Scale CO2 Emission Across Nations
Abstract
Elevated atmospheric carbon dioxide levels contribute to global warming, necessitating urgent emission reduction. Identifying sources is crucial. This study develops end-to-end models for high-resolution national estimation using remote sensing. Our methodology involves three steps. First, a machine learning-based model establishes relationships between satellite-derived column average and weather conditions, including anthropogenic proxies. This model generates daily 1 km2 spatial maps. The second step separates dominant accumulated and regional enhancement due to anthropogenic activities, challenging due to being small and often near measurement noise. Addressing this, we adopt a geometrically connected segmentation to identify emission and non-emission sources, establishing relationships for maps at a weekly frequency. The final step involves to emission conversion, challenging due to dispersion processes. We customize an integrated mass balance method for weekly, 1 km2 spatial $XCO{_2}) emissions mapping. Our approach aligns closely with reported annual the Kingdom of Saudi Arabia (KSA) emissions, showcasing high-resolution emissions tracking and a departure from traditional bottom-up approaches, enabling near real-time (NRT) finer to country-level emission monitoring, circumventing delays associated with annual reporting.