Abstract
Abstract. As the deep learning algorithm has become a popular data analysis 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 h in advance in both the United States of America 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 indexes of agreement exceeding 0.85. When the DTW distance of CMAQ versus 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.
Highlights
Atmospheric scientists have shown significant interest in applying machine learning (ML) algorithms in their field, for air quality forecasting, remote sensing data retrieval, and hurricane tracking
The deep convolutional neural network (CNN) model (Krizhevsky et al, 2012) is a common deep learning architecture that has long been used in numerous applications (Deng and Yu, 2014; Schmidhuber, 2015; Goodfellow et al, 2016; Litjens et al, 2017; Chen et al, 2018; Kamilaris and Prenafeta-Boldú, 2018; Higham and Higham, 2019)
Note that index of agreement (IOA) is a standardized measure of the degree of model prediction error and varies between 0 and 1
Summary
Atmospheric scientists have shown significant interest in applying machine learning (ML) algorithms in their field, for air quality forecasting, remote sensing data retrieval, and hurricane tracking. The focus of these studies was the general performance of the model ML models compared to that of conventional statistical models rather than identifying the shortcomings of such models in explaining the uncertainties of prediction models. Such examples can be found in studies by Eslami et al (2019, 2020a, b), Choi et al (2019), Sayeed et al (2020), and Lops et al (2019). To achieve more reasonable outcomes, we must first explore the current challenges we face when forecasting ambient air quality and assess how or even whether ML
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
