CO₂ is the main greenhouse gas. Urban spatial development, land use, and so on may be affected by CO₂ and climate change. The main questions studied in this paper are as follows: What are the drivers of CO₂ emissions of expanding megacities? How can they be analyzed from different perspectives? Do the results differ for megacities at different stages of development? Based on the XGBoost model, this paper explored the complex factors affecting CO₂ emissions by using data of four Chinese megacities, Beijing, Tianjin, Shanghai, and Chongqing, from 2003 to 2017. The main findings are as follows: The XGBoost model has better applicability and accuracy in predicting carbon emissions of expanding megacities, with root mean square error (RMSE) as low as 0.036. Under the synergistic effect of multiple factors, population, land size, and gross domestic product are still the primary driving forces of CO₂ emissions. Population density and population become more important in the single-factor analysis. The key drivers of CO₂ emissions in megacities at respective developmental stages are different. This paper provides methods and tools for accurately predicting CO₂ emissions and measuring the critical drivers. Furthermore, it could provide decision support for megacities to make targeted carbon-emission-reduction strategies based on their own developmental stages.

Chinese cities contributes a large amount of CO₂ emissions. Reducing CO₂ emissions through urban governance is an important issue. Despite the increasing attention paid on the CO₂ emission prediction, few studies consider the collective and complex influence of governance element system. To predict and regulate CO₂ emissions through comprehensive urban governance elements, this paper use the random forest model through the data from 1903 Chinese county-level cities in 2010, 2012 and 2015, and establish a CO₂ forecasting platform based on the effects of urban governance elements. The results are as follows: (1) The municipal utility facilities element, the economic development & industrial structure element, and the city size &structure and road traffic facilities elements are crucial for residential, industrial and transportation CO₂ emissions, respectively; (2) Governance elements have nonlinear relationship with CO₂ emissions and most of the relations present obvious threshold effects; (3) Random forest can be used to predict CO₂ emissions more accurately than can other predictive models. These findings can be used to conducts the CO₂ scenario simulation and help government formulate active governance measurements.

With the rapid development of the Internet of Things (IoT) in the 5G age, the construction of smart cities around the world consequents on the exploration of carbon reduction path based on IoT technology is an important direction for global low carbon city research. Carbon dioxide emissions in small cities are usually higher than that in large and medium cities. However, due to the huge difference in data environment between small cities and Medium-large sized cities, the weak hardware foundation of the IoT, and the high input cost, the construction of a small city smart carbon monitoring platform has not yet been carried out. This paper proposes a real-time estimate model of carbon emissions at the block and street scale and designs a smart carbon monitoring platform that combines traditional carbon control methods with IoT technology. It can exist long-term data by using real-time data acquired with the sensing device. Therefore, the dynamic monitoring and management of low-carbon development in small cities can be achieved. The contributions are summarized as follows: (1) Intelligent thermoelectric systems, industrial energy monitoring systems, and intelligent transportation systems are three core systems of the monitoring platform. Carbon emission measurement methods based on sample monitoring, long-term data, and real-time data have been established, they can solve the problem of the high cost of IoT equipment in small cities. (2) Combined with long-term data, the real-time correction technology, they can dispose of the matter of differences in carbon emission measurement under diverse scales.

Low-carbon governance at the county level has been an important issue for sustainable development due to the large contributions to carbon emission. However, the experiences of carbon emission governance at the county level are lacking. This paper discusses 5 carbon emission governance zones for 1753 counties. The zoning is formed according to a differentiated zoning method based on a multi-indicator evaluation to judge if the governance had better focus and had formulated a differentiated carbon emission governance system. According to zoning results, there is 1 high-carbon governance zone, 2 medium-carbon governance zones, and 2 low-carbon zones. The extensive high-carbon governance zone and medium-carbon zones are key governance areas, in which the counties are mainly located in the northern plain areas and southeast coastal areas and have contributed 51.88% of total carbon emissions. This paper proposes differentiated governance standards for each indicator of the 5 zones. The differentiated zoning method mentioned in this paper can be applied to other governance issues of small-scale regions.