Air pollution is a hotspot of wide concern in Chinese cities. With the worsening of air pollution, urban agglomerations face an increasingly complex environment for air quality monitoring, hindering sustainable and high-quality development in China. More effective methods for predicting air quality are urgently needed. In this study, we employed seven single models and ensemble learning algorithms and constructed a hybrid learning algorithm, the LSTM-SVR model, totaling eight machine learning algorithms, to predict the Air Quality Index in six major urban agglomerations in China. We comprehensively compared the predictive performance of the eight algorithmic models in different urban agglomerations. The results reveal that, in areas with higher levels of air pollution, the situation for model prediction is more complicated, leading to a decline in predictive accuracy. The constructed hybrid model LSTM-SVR demonstrated the best predictive performance, followed by the ensemble model RF, both of which effectively enhanced the predictive accuracy in heavily polluted areas. Overall, the predictive performance of the hybrid and ensemble models is superior to that of the single-model prediction methods. This study provides AI technological support for air quality prediction in various regions and offers a more comprehensive discussion of the performance differences between different types of algorithms, contributing to the practical application of air pollution control.

The escalating issue of air pollution in China’s rapidly developing urban areas has prompted increased attention to the role of meteorological conditions in PM_2.5 pollution. This study examines the spatiotemporal distribution of PM_2.5 concentrations and their relationship with meteorological factors in six major Chinese urban agglomerations from 2017 to 2020, using daily average data. Statistical and spatial analysis techniques are employed, alongside the construction of eight machine learning models for prediction purposes. The study also compares the feature importance of various meteorological factors impacting PM_2.5 concentrations. Results reveal significant regional differences in both average PM_2.5 levels and meteorological influences. The Multilayer Perceptron (MLP) model demonstrates the highest prediction accuracy for PM_2.5 concentrations. According to the MLP model’s feature importance identification, temperature is the most significant factor affecting PM_2.5 concentrations across all urban agglomerations, while wind speed and precipitation have the least impact. Contributions from air pressure and dew point temperature, however, vary among different urban agglomerations. This research considers the impact of urban agglomerations and meteorological conditions on PM_2.5 and also offers valuable artificial intelligence-based insights into the key meteorological factors influencing PM_2.5 concentrations in diverse regions, thereby informing the development of effective air pollution control policies.

China’s minimum grain procurement price program aims to boost grain production and ensure food self-sufficiency. It may also affect the already very high levels of chemical fertilizer and pesticides consumption, but little is known about these potential side-effects. In this paper, we apply panel data regression techniques to a large rural household-level data set for the period 1997–2010 to examine whether and how the minimum grain procurement price program affected households’ agrochemical use. We find that the minimum grain procurement price program negatively affected both chemical fertilizer and pesticides use, with pesticides use being more responsive than the use of fertilizer. The higher wheat and rice prices that resulted from the program stimulated the use of agrochemicals, but they also stimulated area expansion which contributed to lower agrochemical use per unit of land. These counteracting indirect effects were overshadowed by the large negative direct effect of the minimum procurement price of rice on the use of fertilizer and pesticides.