Autoencoder-based deep belief regression network for air particulate matter concentration forecasting

Multi-scale deep learning and optimal combination ensemble approach for AQI forecasting using big data with meteorological conditions

Faced with the rapid update of nonlinear and irregular big data from the environmental monitoring system, both the public and managers urgently need reliable methods to predict possible air pollutions in the future. Therefore, a multi-scale deep learning (MDL) and optimal combination ensemble (OCE) approach for hourly air quality index (AQI) forecasting is proposed in this paper, named MDL-OCE model. Before normal modeling, all original data are preprocessed through missing data filling and outlier testing to ensure smooth computation. Due to the complexity of such big data, slope-based ensemble empirical mode decomposition (EEMD) is adopted to decompose the time series of AQI and meteorological conditions into a finite number of simple intrinsic mode function (IMF) components and one residue component. Then, to unify the number of components of different variables, the fine-to-coarse (FC) technique is used to reconstruct all components into high frequency component (HF), low frequency component (LF), and trend component (TC). For purpose of extracting the underlying relationship between AQI and meteorological conditions, the three components are respectively trained and predicted by different deep learning architectures (stacked sparse autoencoder (SSAE)) with a multilayer perceptron (MLP). The corresponding forecasting results of three components are merged by OCE method to better achieve the ultimate AQI forecasting outputs. The empirical results clearly demonstrate that our proposed MDL-OCE model outperforms other advanced benchmark models in terms of forecasting performances in all cases.

Double decomposition and optimal combination ensemble learning approach for interval-valued AQI forecasting using streaming data

To forecast possible future environmental risks, numerous models are developed to predict the hourly values or daily averages of air pollutant concentrations using streaming data (a kind of big data collected from the Internet). On the one hand, real-time hourly data is massive and redundant, making it difficult to process. On the other hand, daily averages cannot reflect the fluctuations of air pollutant concentrations throughout the day. Therefore, a double decomposition and optimal combination ensemble learning approach is proposed for interval-valued AQI (air quality index) forecasting in this paper. In the first decomposition, considering the strong seasonal representation of AQI, the original data of each year is decomposed into four seasonal subseries on the basis of the Chinese calendar. Subsequently, we reconstruct the data of the same season in different years to get a new seasonal series to reduce the interference of seasonal changes on AQI forecasting. In the second decomposition, due to the nonlinearity and irregularity of interval-valued AQI time series, BEMD (bivariate empirical mode decomposition) is employed to decompose the interval-valued signals into a finite number of complex-valued IMF (intrinsic mode function) components and one complex-valued residue component with different frequencies to reduce the complexity of interval times series. Interval multilayer perceptron (iMLP) is utilized to model the lower bound and the upper bound simultaneously of the total components to obtain the corresponding forecasting results, which are merged to produce the final interval-valued output by an optimal combination ensemble method. Empirical study results show that the proposed model with different datasets and different forecasting horizons is significantly better than other considered models for its superior forecasting performances.

Introducing a Hybrid Model SAE-BP for Regression Analysis of Soil Temperature With Hyperspectral Data

Soil temperature, as one of the critical meteorological parameters, plays a key role in physical, chemical and biological processes in terrestrial ecosystems. Accurate estimation of dynamic soil temperature is crucial for underground soil ecological research. In this work, a hybrid model SAE-BP is proposed by combining stacked auto-encoders (SAE) and back propagation (BP) algorithm to estimate soil temperature using hyperspectral remote sensing data. Experimental results show that the proposed SAE-BP model achieves a more stable and effective performance than the existing logistic regression (LR), support vector regression (SVR) and BP neural network with an average value of mean square error (MSE) = 1.926, mean absolute error (MAE) = 0.962 and coefficient of determination (R2) = 0.910. In addition, the effect of hidden structures and labeled training data ratios in SAE-BP is further explored. The SAE-BP model demonstrates the potential in high-dimensional and small hyperspectral datasets, representing a significant contribution to soil remote sensing.

An ensemble long short-term memory neural network for hourly PM2.5 concentration forecasting

To protect public health by providing an early warning, PM_2.5 concentration forecasting is an essential and effective work. In this paper, an ensemble long short-term memory neural network (E-LSTM) is proposed for hourly PM_2.5 concentration forecasting. The presented model is implemented using three steps: (1) ensemble empirical mode decomposition (EEMD) is firstly utilized for multi-modal feature extraction, (2) long short-term memory approach (LSTM) is then employed for multi-modal feature learning, and (3) inverse EEMD computation is finally used for multi-modal feature estimated integration. In each modeling process, the mode information of the PM_2.5 and the corresponding meteorological variables in 1-h advance are utilized as inputs to forecast the next mode information of the PM_2.5 concentration. To evaluate the performance of the E-LSTM model, two datasets collected from two environmental monitoring stations in Beijing, China, are investigated. It is demonstrated that the E-LSTM model inspired by ensemble learning, which constructs multiple LSTMs in different modes, obtained better forecasting performance than that using the single LSTM and feed forward neural network in terms of mean absolute percentage error (19.604% and 16.929%), root mean square error (12.077 μg m^-3 and 13.983 μg m^-3), and correlation coefficient criteria (0.994 and 0.991) respectively.