Search

Satellite‐derived aerosol optical depth (AOD) is negatively impacted by cloud cover and surface reflectivity. As these issues lead to biases, they need to be discarded, which significantly increases the amount of missing data within an image. This paper presents a unique application of the partial convolutional neural network (PCNN) for imputing missing data from the Geostationary Ocean Color Imager (GOCI) by training the PCNN model with the Community Multiscale Air Quality model simulated AOD. The PCNN model outperforms various models and algorithms for imputing GOCI images with a significant amount of missing data (45% of the data set has at least 80% missing pixels) and distance to the nearest known pixel within the GOCI image. Once trained, the model requires significantly less processing time and fewer resources than the other models and methods. The model allows the accurate imputation of remote sensing images within significant amounts of missing data. Plain Language Summary: Satellite measurements provide surface and atmospheric data over large areas across the globe. Cloud cover and surface reflectivity cause significant errors in the satellite measurements. This phenomenon forces data to be excluded, reducing the available data for analysis and research. Statistical and machine learning approaches, such as Kriging and K‐Nearest Neighbor, are used to estimate or interpolate the missing data based on spatial distribution. Unfortunately, these methods are not always accurate or require extensive computational resources. We utilize a deep‐learning model, partial convolutional neural network (PCNN), to fill in the missing data efficiently and accurately within East Asia satellite images. This model was trained with data from the Community Multiscale Air Quality model with missing masks from the Geostationary Ocean Color Imager satellite images. The results show that the PCNN model works better than the other models when dealing with more missing data and larger distances from the nearest available measurement. Our model was also more accurate than several of the other methods when comparing imputed remote sensing images to surface measurements across seven cities in East Asia. The system has the potential to provide research advancements by accurately and efficiently filling in missing remote sensing data. Key Points: We implemented a partial convolutional neural network for the imputation of missing remote sensing dataThe model is trained with air quality modeling data and validated with remote sensing and in situ dataThe neural network model outperformed the Kriging Gaussian process regression method in accuracy and performance [ABSTRACT FROM AUTHOR]

As the deep learning algorithm has become a popular data analytic technique, atmospheric scientists should have a balanced perception of its strengths and limitations so that they can provide a powerful analysis of complex data with well-established procedures. Despite the enormous success of the algorithm in numerous applications, certain issues related to its applications in air quality forecasting (AQF) require further analysis and discussion. This study addresses significant limitations of an advanced deep learning algorithm, the convolutional neural network (CNN), in two common applications: (i) a real-time AQF model, and (ii) a post-processing tool in a dynamical AQF model, the Community Multi-scale Air Quality Model (CMAQ). In both cases, the CNN model shows promising accuracy for ozone prediction 24 hours in advance in both the United States and South Korea (with an overall index of agreement exceeding 0.8). For the first case, we use the wavelet transform to determine the reasons behind the poor performance of CNN during the nighttime, cold months, and high ozone episodes. We find that when fine wavelet modes (hourly and daily) are relatively weak or when coarse wavelet modes (weekly) are strong, the CNN model produces less accurate forecasts. For the second case, we use the dynamic time warping (DTW) distance analysis to compare post-processed results with their CMAQ counterparts (as a base model). For CMAQ results that show a consistent DTW distance from the observation, the post-processing approach properly addresses the modeling bias with predicted IOAs exceeding 0.85. When the DTW distance of CMAQ-vs-observation is irregular, the post-processing approach is unlikely to perform satisfactorily. Awareness of the limitations in CNN models will enable scientists to develop more accurate regional or local air quality forecasting systems by identifying the affecting factors in high concentration episodes. [ABSTRACT FROM AUTHOR]

From hourly ozone observations obtained from three regions⸻Houston, Dallas, and West Texas⸻we investigated the contributions of meteorology to changes in surface daily maximum 8-h average (MDA8) ozone from 2000 to 2019. We applied a deep convolutional neural network and Shapely additive explanation (SHAP) to examine the complex underlying nonlinearity between variations of surface ozone and meteorological factors. Results of the models showed that between 2000 and 2019, specific humidity (38% and 27%) and temperature (28% and 37%) contributed the most to ozone formation over the Houston and Dallas metropolitan areas, respectively. On the other hand, the results show that solar radiation (50%) strongly impacted ozone variation over West Texas during this time. Using a combination of the Kolmogorov-Zurbenko (KZ) filter and multiple linear regression, we also evaluated the influence of meteorology on ozone and quantified the contributions of meteorological parameters to trends in surface ozone formation. Our findings showed that in Houston and Dallas, meteorology influenced ozone variations to a large extent. The impacts of meteorology on West Texas, however, showed meteorological factors had fewer influences on ozone variabilities from 2000 to 2019. This study showed that SHAP analysis and the KZ approach can investigate the contributions of the meteorological factors on ozone concentrations and help policymakers enact effective ozone mitigation policies. [Display omitted] • Deep CNN examined the nonlinearity between meteorology and ozone variations. • Specific humidity, radiation, and temperature most contributed to ozone variations. • Meteorology influenced ozone variations to a larger extent over Houston and Dallas. • The impacts of meteorology had fewer influences on ozone variations in West Texas. [ABSTRACT FROM AUTHOR]

Chemical transport models simulate ambient air pollution concentrations by considering emission, transport and deposition mechanism, and other physical processes. Despite their advancements over the past decades, the models exhibit significant model-measurement errors, especially during high concentration episodes. Furthermore, biases within meteorological predictions, emission estimates, initial and boundary conditions, and other model inputs can propagate into the final predictions. This research introduces a new generation of post-processing application for real-time air quality forecasts that employ the physical process of a numerical model in conjunction with an advanced deep learning algorithm. We use a deep convolutional neural network (CNN) to map ozone precursors from Community Multiscale Air Quality (CMAQ) and meteorological parameters from the weather research and forecasting (WRF) model (as inputs variables) to observed hourly ozone concentrations at a monitoring station (as a target). Our results show that the CMAQ-CNN model significantly improves the performance of the CMAQ model in both accuracy and bias. The absolute correlation coefficient is improved by 0.16 on average. The CMAQ-CNN model improves simulated ozone peaks for almost all cases and reduces the bias of CMAQ predictions by an average of more than 20 ppb (or 40%). Systematic improvements in CMAQ-CNN simulations suggest that the deep learning model is effective at reproducing accurate estimates of ground-level air quality concentrations. While this study focuses on ozone in the United States and outputs of CMAQ, the proposed approach can be applied to any measured air pollution parameters or numerical model in a mesoscale resolution. • CNN model bias corrects the hourly ozone concentration of CMAQ model. • The study was conducted for various air-quality monitoring station in the US. • The generalized model has the better performance over standalone model. • Generalized model was also faster in processing bias correction. • The average biases were reduced by 40%. [ABSTRACT FROM AUTHOR]

In this study, we use a deep convolutional neural network (CNN) to develop a model that predicts ozone concentrations 24 h in advance. We have evaluated the model for 21 continuous ambient monitoring stations (CAMS) across Texas. The inputs for the CNN model consist of meteorology (e.g., wind field, temperature) and air pollution concentrations (NO x and ozone) from the previous day. The model is trained for predicting next-day, 24-hour ozone concentrations. We acquired meteorological and air pollution data from 2014 to 2017 from the Texas Commission on Environmental Quality (TCEQ). For 19 of the 21 stations in the study, results show that the yearly index of agreement (IOA) is above 0.85, confirming the acceptable accuracy of the CNN model. The results also show the model performed well, even for stations with varying monthly trends of ozone concentrations (specifically CAMS-012, located in El-Paso, and CAMS-013, located in Fort Worth, both with IOA=0.89). In addition, to ensure that the model was robust, we tested it on stations where fewer meteorological variables are monitored. Although these stations have fewer input features, their performance is similar to that of other stations. However, despite its success at capturing daily trends, the model mostly underpredicts the daily maximum ozone, which provides a direction for future study and improvement. As this model predicts ozone concentrations 24 h in advance with greater accuracy and computationally fewer resources, it can serve as an early warning system for individuals susceptible to ozone and those engaging in outdoor activities. [ABSTRACT FROM AUTHOR]