BEIJING, Sept. 14 (Xinhua) -- Chinese researchers have developed a hybrid framework to trace sources and change of on-road carbon dioxide emissions in real time with 30-meter resolution, according to a research article recently published in the journal Sustainable Cities and Society.

This technology is being applied in Shenzhen, south China's Guangdong Province, and is expected to be used in more cities in the future to assess and promote carbon dioxide reduction on urban roads.

Urban expansion and population mobility have driven a continuous rise in road carbon dioxide emissions -- posing significant challenges in terms of local climate regulation, public health and carbon neutrality.

A key limitation of previous carbon emission inventories is their coarse spatial resolution, according to Wang Li, corresponding author of the paper and a researcher at the Aerospace Information Research Institute of the Chinese Academy of Sciences.

This lack of detail makes it difficult to capture fine-scale variations in emissions from different road segments or over time. Consequently, it becomes even more challenging to accurately trace the sources of emissions or to explain what causes them, Wang said.

The development of precise monitoring methods for performing multi-factor analysis of on-road carbon dioxide levels is considered of great importance for their effective reduction.

Wang and his team developed their framework combining Panoptic-Artificial Intelligence (Panoptic-AI) and a mobile observation framework to predict the hourly 30-meter resolution of the on-road carbon dioxide concentration and provide a daytime dynamic carbon dioxide increment prediction in urban traffic networks.

This development integrates AI with panoramic cameras, high-precision greenhouse-gas analyzers and meteorological sensors to synchronously acquire multi-source data on road carbon dioxide concentrations, traffic volumes, building layouts, vegetation cover and meteorological conditions, during mobile surveys.

The research team achieved an average identification accuracy of over 93 percent for emission sources. Meanwhile, this framework can quantify the influence of individual factors such as traffic conditions, surrounding land cover and meteorological variables -- thereby clearly revealing the spatio-temporal dynamics and driving mechanisms of carbon emissions.

"This technique represents an innovative deployment of AI in environmental monitoring, as well as enabling a multi-dimensional and full-spectrum carbon monitoring system combined with conventional emission inventories and satellite-based greenhouse-gas monitoring technologies," said Wang.