Predicting high-resolution air quality using machine learning: Integration of large eddy simulation and urban morphology data

Accurately predicting air pollutants, especially in urban areas with well-defined spatial structures, is crucial. Over the past decade, machine learning techniques have been widely used to forecast urban air quality. However, traditional machine learning approaches have limitations in accuracy and interpretability for predicting pollutants. In this study, we propose a convolutional neural network (CNN) model to predict the spatial distribution of CO concentration in Nanjing urban area at 10 m resolution. Our model incorporates various factors as input, such as building height, topography, emissions, and is trained against the outputs simulated by the parallelized large-eddy simulation model (PALM). The PALM model has 48 different scenarios that varied in emissions, wind speeds, and wind directions. The results display a strong consistency between the two models. Furthermore, we evaluate the performance of our model using a 10-fold cross-validation and out-of-sample cross-validation approach. This yields a robust correlation (with both R2 > 0.8) and a low RMSE between the CO predicted by the PALM and CNN models, which demonstrates the generalization capability of our CNN model. The CNN can extract crucial features from the resulted weight contribution map. This map indicates that the CO concentration at a location is more influenced by nearby buildings and emissions than distant ones. The interpretable patterns uncovered by our model are related to neighborhood effects, wind speeds, directions, and the impact of orientation on urban CO distribution. The model also shows high prediction accuracy (R > 0.8) when applied to another city. Overall, the integration of our CNN framework with the PALM model enhances the accuracy of air quality predictions, while enabling a fluid dynamic laws interpretation, providing effective tools for air quality management.

Cloud System Evolution in the Trades-CSET: Following the Evolution of Boundary Layer Cloud Systems with the NSF/NCAR GV

The Cloud System Evolution in the Trades (CSET) study was designed to describe and explain the evolution of the boundary layer aerosol, cloud, and thermodynamic structures along trajectories within the north-Pacific trade-winds. The study centered on 7 round-trips of the NSF NCAR Gulfstream V (GV) between Sacramento, CA and Kona, Hawaii between 1 July and 15 August 2015. The CSET observing strategy was to sample aerosol, cloud, and boundary layer properties upwind from the transition zone over the North Pacific and to resample these areas two days later. GFS forecast trajectories were used to plan the outbound flight to Hawaii with updated forecast trajectories setting the return flight plan two days later. Two key elements of the CSET observing system were the newly developed HIAPER Cloud Radar (HCR) and the High Spectral Resolution Lidar (HSRL). Together they provided unprecedented characterizations of aerosol, cloud and precipitation structures that were combined with in situ measurements of aerosol, cloud, precipitation, and turbulence properties. The cloud systems sampled included solid stratocumulus infused with smoke from Canadian wildfires, mesoscale cloud-precipitation complexes, and patches of shallow cumuli in very clean environments. Ultra-clean layers observed frequently near the top of the boundary layer were often associated with shallow, optically thin, layered veil clouds. The extensive aerosol, cloud, drizzle and boundary layer sampling made over open areas of the Northeast Pacific along 2-day trajectories during CSET is unprecedented and will enable modeling studies of boundary layer cloud system evolution and the role of different processes in that evolution.