A deep recurrent neural network system based on a long short-term memory (LSTM) model was developed for daily PM₁₀ and PM_2.5 predictions in South Korea. The structural and learnable parameters of the newly developed system were optimized from iterative model training. Independent variables were obtained from ground-based observations over 2.3 years. The performance of the particulate matter (PM) prediction LSTM was then evaluated by comparisons with ground PM observations and with the PM concentrations predicted from two sets of 3-D chemistry-transport model (CTM) simulations (with and without data assimilation for initial conditions). The comparisons showed, in general, better performance with the LSTM than with the 3-D CTM simulations. For example, in terms of IOAs (index of agreements), the PM prediction IOAs were enhanced from 0.36–0.78 with the 3-D CTM simulations to 0.62–0.79 with the LSTM-based model. The deep LSTM-based PM prediction system developed at observation sites is expected to be further integrated with 3-D CTM-based prediction systems in the future. In addition to this, further possible applications of the deep LSTM-based system are discussed, together with some limitations of the current system.

In this paper, we propose a new temperature prediction model based on deep learning by using real observed weather data. To this end, a huge amount of model training data is needed, but these data should not be defective. However, there is a limitation in collecting weather data since it is not possible to measure data that have been missed. Thus, the collected data are apt to be incomplete, with random or extended gaps. Therefore, the proposed temperature prediction model is used to refine missing data in order to restore missed weather data. In addition, since temperature is seasonal, the proposed model utilizes a long short-term memory (LSTM) neural network, which is a kind of recurrent neural network known to be suitable for time-series data modeling. Furthermore, different configurations of LSTMs are investigated so that the proposed LSTM-based model can reflect the time-series traits of the temperature data. In particular, when a part of the data is detected as missing, it is restored by using the proposed model’s refinement function. After all the missing data are refined, the LSTM-based model is retrained using the refined data. Finally, the proposed LSTM-based temperature prediction model can predict the temperature through three time steps: 6, 12, and 24 h. Furthermore, the model is extended to predict 7 and 14 day future temperatures. The performance of the proposed model is measured by its root-mean-squared error (RMSE) and compared with the RMSEs of a feedforward deep neural network, a conventional LSTM neural network without any refinement function, and a mathematical model currently used by the meteorological office in Korea. Consequently, it is shown that the proposed LSTM-based model employing LSTM-refinement achieves the lowest RMSEs for 6, 12, and 24 h temperature prediction as well as for 7 and 14 day temperature prediction, compared to other DNN-based and LSTM-based models with either no refinement or linear interpolation. Moreover, the prediction accuracy of the proposed model is higher than that of the Unified Model (UM) Local Data Assimilation and Prediction System (LDAPS) for 24 h temperature predictions.

Weather is affected by a complex interplay of factors, including topography, location, and time. For the prediction of temperature in Korea, it is necessary to use data from multiple regions. To this end, we investigate the use of deep neural-network-based temperature prediction model time-series weather data obtained from an automatic weather station and image data from a regional data assimilation and prediction system (RDAPS). To accommodate such different types of data into a single model, a bidirectional long short-term memory (BLSTM) model and a convolutional neural network (CNN) model are chosen to represent the features from the time-series observed data and the RDAPS image data. The two types of features are combined to produce temperature predictions for up to 14 days in the future. The performance of the proposed temperature prediction model is evaluated by objective measures, including the root mean squared error and mean bias error. The experiments demonstrated that the proposed model combining both the observed and RDAPS image data is better in all performance measures for all prediction periods compared with the BLSTM-based model using observed data and the CNN-BLSTM-based model using RDAPS image data alone.

A CNN+LSTM (Convolutional Neural Network + Long Short-Term Memory) based deep hybrid neural network was established for the citywide daily PM_2.5 prediction in South Korea. The structural hyperparameters of the CNN+LSTM model were determined through comprehensive sensitivity tests. The input features were obtained from the ground observations and GFS forecast. The performance of CNN+LSTM was evaluated by comparison with PM_2.5 observations and with the 3-D CTM (three-dimensional chemistry transport model)-predicted PM_2.5. The newly developed hybrid model estimated more accurate ambient levels of PM_2.5 compared to the 3-D CTM. For example, the error and bias of the CNN+LSTM prediction were 1.51 and 6.46 times smaller than those by 3D-CTM simulation. In addition, based on IOA (Index of Agreement), the accuracy of CNN+LSTM prediction was 1.10–1.18 times higher than the 3-D CTM-based prediction. The importance of input features was indirectly investigated by sequential perturbing input variables. The most important meteorological and atmospheric environmental features were geopotential height and previous day PM_2.5. The obstacles of the current CNN+LSTM-based PM_2.5 prediction were also discussed. The promising result of this study indicates that DNN-based models can be utilized as an effective tool for air quality prediction.