Full Coverage Estimation of the PM Concentration Across China Based on an Adaptive Spatiotemporal Approach<sub/>

Particulate pollution threatens the ecological environment, air quality, and public health. Therefore, it has become an increasing concern for the public and governments in recent decades. In this study, a full coverage PM2.5 (aerodynamic diameter of less than 2.5 $\mu \text{m}$ ) estimation strategy is proposed based on spatiotemporal machine learning approaches, including the convolutional neural network with long short-term memory (CNN-LSTM) and random forest (RF). The RF estimates PM2.5 by considering the features of a single pixel, while the introduction of the CNN-LSTM (size of 7 $\times7\,\,\times4$ ) assists in exploiting the spatiotemporal correlation of surrounding pixel features. Compared with linear models and empirical spatiotemporal weight methods, our CNN-LSTM+RF avoids the uncertainty and complexity owing to actual measurements of the surrounding sites. In addition, full coverage is achieved using both satellite data and reanalysis data. Results showed that the root mean square error (RMSE) and coefficient of determination ( $R^{2}$ ) of the CNN-LSTM+RF were 12.790 $\mu \text{g}/\text{m}^{3}$ and 0.910, respectively, in sample-based cross-validation (CV). From the perspective of the season, the best performance of the CNN-LSTM+RF was found in autumn ( $R^{2}$ of 0.915), and the lowest was in summer ( $R^{2}$ of 0.848). In the meantime, for the different regions of China, the CNN-LSTM+RF also showed stable performance. The proposed method can generate high-precision continuous PM2.5 distribution maps that provide beneficial support for improving environmental and public health, and provide a reference for using deeper networks.