Search

Among the critical global crises curbing world development and sustainability, air quality degradation has been a long-lasting and increasingly urgent one and it has been sufficiently proven to pose severe threats to human health and social welfare. A higher level of model prediction accuracy can play a fundamental role in air quality assessment and enhancing human well-being. In this paper, four types of machine learning models—random forest model, ridge regression model, support vector machine model, extremely randomized trees model—were adopted to predict PM2.5 concentration in ten cities in the Jing-Jin-Ji region of north China based on multi-sources spatiotemporal data including air quality and meteorological data in time series. Data were fed into the model by using the rolling prediction method which is proven to improve prediction accuracy in our experiments. Lastly, the comparative experiments show that at the city level, RF and ExtraTrees models have better predictive results with lower mean absolute error (MAE), root mean square error (RMSE), and higher index of agreement (IA) compared to other selected models. For seasonality, level four models all have the best prediction performances in winter time and the worst in summer time, and RF models have the best prediction performance with the IA ranging from 0.93 to 0.98 with an MAE of 5.91 to 11.68 μg/m3. Consequently, the demonstration of how each model performs differently in each city and each season is expected to shed light on environmental policy implications. [ABSTRACT FROM AUTHOR]

Due to rapid urbanization and increasing energy consumption, human society poses increasing pressure on the surrounding ecosystems that it depends on. As a result, evaluation of urban development should view cities as complex ecosystems including human and natural elements. This paper establishes a carbon balance index (CBI) for an urban ecosystem based on its socio-economic development and land use and land cover change in Xiamen, a rapidly urbanizing coastal city in southeast China. Dynamic changes in CBI can quantitatively indicate the sustainability of the urbanization process from a carbon cycling perspective. Results show that Xiamen's carbon balance condition experienced three stages: the period 1987–2002 where CBI decreased slightly, 1992–2002 where CBI moderately increased from 1.4 to 4.2, and 2003–2011 where CBI rapidly increased from 5.2 to 17.3. The carbon imbalance increased with the expansion of urban scale and urbanization. By stepwise multiple regression analysis, it was found that the main influencing factors of CBI are urbanization rate, industrial coal consumption, length of roadway network and forest area, and city managers should take these factors into consideration to achieve low-carbon city development. Finally, the CBI for the year 2030 is predicted based on CO2emissions and sequestration scenarios. [ABSTRACT FROM AUTHOR]