Integration of complete ensemble empirical mode decomposition with deep long short-term memory model for particulate matter concentration prediction

Deep-learning architecture for PM2.5 concentration prediction: A review

Accurately predicting the concentration of fine particulate matter (PM2.5) is crucial for evaluating air pollution levels and public exposure. Recent advancements have seen a significant rise in using deep learning (DL) models for forecasting PM2.5 concentrations. Nonetheless, there is a lack of unified and standardized frameworks for assessing the performance of DL-based PM2.5 prediction models. Here we extensively reviewed those DL-based hybrid models for forecasting PM2.5 levels according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We examined the similarities and differences among various DL models in predicting PM2.5 by comparing their complexity and effectiveness. We categorized PM2.5 DL methodologies into seven types based on performance and application conditions, including four types of DL-based models and three types of hybrid learning models. Our research indicates that established deep learning architectures are commonly used and respected for their efficiency. However, many of these models often fall short in terms of innovation and interpretability. Conversely, models hybrid with traditional approaches, like deterministic and statistical models, exhibit high interpretability but compromise on accuracy and speed. Besides, hybrid DL models, representing the pinnacle of innovation among the studied models, encounter issues with interpretability. We introduce a novel three-dimensional evaluation framework, i.e., Dataset-Method-Experiment Standard (DMES) to unify and standardize the evaluation for PM2.5 predictions using DL models. This review provides a framework for future evaluations of DL-based models, which could inspire researchers to standardize DL model usage in PM2.5 prediction and improve the quality of related studies.

A hybrid multi-scale fusion paradigm for AQI prediction based on the secondary decomposition

With rapid industrialization and urbanization, air pollution has become an increasingly severe problem. As a key indicator of air quality, accurate prediction of the air quality index (AQI) is essential for policymakers to establish effective early warning management mechanisms and adjust living plans. In this work, a hybrid multi-scale fusion prediction paradigm is proposed for the complex AQI time series prediction. First, an initial decomposition and integration of the original data is performed by combining the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and sample entropy (SE). Then, the subsequences, divided into high-frequency and low-frequency groups, are applied to different processing methods. Among them, the variational mode decomposition (VMD) is chosen to perform a secondary decomposition of the high-frequency sequence groups and integrated by using K-means clustering with sample entropy. Finally, multi-scale fusion training of sequence prediction results with different frequencies by using long short-term memory (LSTM) yields more accurate results with R2 of 0.9715, RMSE of 2.0327, MAE of 0.0154, and MAPE of 0.0488. Furthermore, validation of the AQI datasets acquired from four different cities demonstrates that the new paradigm is more robust and generalizable as compared to other baseline methods. Therefore, this model not only holds potential value in developing AQI prediction models but also serves as a valuable reference for future research on AQI control strategies.

Generalized global solar radiation forecasting model via cyber-secure deep federated learning

Recently, the increasing prevalence of solar energy in power and energy systems around the world has dramatically increased the importance of accurately predicting solar irradiance. However, the lack of access to data in many regions and the privacy concerns that can arise when collecting and transmitting data from distributed points to a central server pose challenges to current predictive techniques. This study proposes a global solar radiation forecasting approach based on federated learning (FL) and convolutional neural network (CNN). In addition to maintaining input data privacy, the proposed procedure can also be used as a global supermodel. In this paper, data related to eight regions of Iran with different climatic features are considered as CNN input for network training in each client. To test the effectiveness of the global supermodel, data related to three new regions of Iran named Abadeh, Jarqavieh, and Arak are used. It can be seen that the global forecasting supermodel was able to forecast solar radiation for Abadeh, Jarqavieh, and Arak regions with 95%, 92%, and 90% accuracy coefficients, respectively. Finally, in a comparative scenario, various conventional machine learning and deep learning models are employed to forecast solar radiation in each of the study regions. The results of the above approaches are compared and evaluated with the results of the proposed FL-based method. The results show that, since no training data were available from regions of Abadeh, Jarqavieh, and Arak, the conventional methods were not able to forecast solar radiation in these regions. This evaluation confirms the high ability of the presented FL approach to make acceptable predictions while preserving privacy and eliminating model reliance on training data.

Importance of secondary decomposition in the accurate prediction of daily-scale ozone pollution by machine learning

Machine learning (ML) models have been proven as a reliable tool in predicting ambient pollution concentrations at various places in the world. However, their performance in predicting the maximum daily 8-h averaged ozone (MDA8 O3), the metric often used for O3 pollution assessment and management, is relatively poorer. This is largely resulted from more irregular data fluctuations of the MDA8 O3 levels governed collectively by the synoptic condition, local photochemistry, and long-range transport. In order to improve the prediction accuracy of MDA8 O3, this study developed a secondary decomposition ML model framework which coupled the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) as the primary decomposition, the variational mode decomposition (VMD) as secondary decomposition, and the gate recurrent unit (GRU) ML model. By applying this secondary decomposition model framework on MDA8 O3 prediction for the first time, we showed that the prediction accuracy of MDA8 O3 is largely improved from R2 of 0.46 and RMSE of 30.4 μg/m3 for GRU without decomposition to R2 of 0.91 and RMSE of 12.6 μg/m3 over the Pearl River Delta of China. We also found that the prediction accuracy rate of O3 pollution non-attainments, an essential indicator for initiating contingency O3 pollution control, improved greatly from 14.9 % for GRU without decomposition to 72.5 %. The performance of O3 pollution non-attainment prediction is relatively higher in southwestern PRD, which is mainly due to greater number and severity of O3 non-attainments in southwestern cities located downwind of the emission hotspot area at central PRD. This study underscored the importance of secondary decomposition in accurately predicting daily-scale O3 concentration and non-attainments over the PRD, which can be extended to other photochemically active region worldwide to improve their O3 prediction accuracy and assist in O3 contingency control.

PM2.5 concentration prediction using weighted CEEMDAN and improved LSTM neural network

As the core of pollution prevention and management, accurate PM2.5 concentration prediction is crucial for human survival. However, due to the nonstationarity and nonlinearity of PM2.5 concentration data, the accurate prediction for PM2.5 concentration remains a challenge. In this study, a PM2.5 concentration prediction method using weighted complementary ensemble empirical mode decomposition with adaptive noise (WCEEMDAN) and improved long and short-term memory (ILSTM) neural network is proposed. Firstly, a novel WCEEMDAN method is proposed to correctly identify the non-stationary and non-linear characteristics and divide the PM2.5 sequences into various layers. Through the correlation analysis with PM2.5 data, these sub-layers are given different weights. Secondly, the adaptive mutation particle swarm optimization (AMPSO) algorithm is developed to obtain the main hyperparameters of the long short-term memory network (LSTM) neural network, improving the prediction accuracy of PM2.5 concentration. The optimization convergence speed and accuracy are improved by adjusting the inertia weight and introducing the mutation mechanism to enhance the global optimization ability. Finally, three groups of PM2.5 concentration data are utilized to verify the effectiveness of the proposed model. Compared with other methods, the experimental results demonstrate the superiority of the proposed model. The source code can be downloaded from https://github.com/zhangli190227/WCEENDAM-ILSTM .

Machine learning-based country-level annual air pollutants exploration using Sentinel-5P and Google Earth Engine

Climatic condition is triggering human health emergencies and earth's surface changes. Anthropogenic activities, such as built-up expansion, transportation development, industrial works, and some extreme phases, are the main reason for climate change and global warming. Air pollutants are increased gradually due to anthropogenic activities and triggering the earth's health. Nitrogen Dioxide (NO₂), Carbon Monoxide (CO), and Aerosol Optical Depth (AOD) are truthfully important for air quality measurement because those air pollutants are more harmful to the environment and human's health. Earth observational Sentinel-5P is applied for monitoring the air pollutant and chemical conditions in the atmosphere from 2018 to 2021. The cloud computing-based Google Earth Engine (GEE) platform is applied for monitoring those air pollutants and chemical components in the atmosphere. The NO₂ variation indicates high during the time because of the anthropogenic activities. Carbon Monoxide (CO) is also located high between two 1-month different maps. The 2020 and 2021 results indicate AQI change is high where 2018 and 2019 indicates low AQI throughout the year. The Kolkata have seven AQI monitoring station where high nitrogen dioxide recorded 102 (2018), 48 (2019), 26 (2020) and 98 (2021), where Delhi AQI stations recorded 99 (2018), 49 (2019), 37 (2020), and 107 (2021). Delhi, Kolkata, Mumbai, Pune, and Chennai recorded huge fluctuations of air pollutants during the study periods, where ~ 50-60% NO₂ was recorded as high in the recent time. The AOD was noticed high in Uttar Pradesh in 2020. These results indicate that air pollutant investigation is much necessary for future planning and management otherwise; our planet earth is mostly affected by the anthropogenic and climatic conditions where maybe life does not exist.

On the prediction of methane fluxes from pristine tropical peatland in Sarawak: application of a denitrification-decomposition (DNDC) model

Tropical peatlands have high potential function as a major source of atmospheric methane (CH₄) and can contribute to global warming due to their large soil carbon stock, high groundwater level (GWL), high humidity and high temperature. In this study, a process-based denitrification-decomposition (DNDC) model was used to simulate CH₄ fluxes in a pristine tropical peatland in Sarawak. To test the accuracy of the model, eddy covariance tower datasets were compared. The model was validated for the year 2014, which showed the good performance of the model for simulating CH₄ emissions. The monthly predictive ability of the model was better than the daily predictive ability, with a determination coefficient (R²) of 0.67, model error (ME) of 2.47, root mean square error (RMSE) of 3.33, mean absolute error (MAE) of 2.92 and mean square error (MSE) of 11.08. The simulated years of 2015 and 2016 showed the good performance of the DNDC model, although under- and overestimations were found during the drier and rainy months. Similarly, the monthly simulations for the year were better than the daily simulations for the year, showing good correlations at R² at 0.84 (2015) and 0.87 (2016). Better statistical performance in terms of monthly ME, RMSE, MAE and MSE at - 0.11, 3.38, 3.05 and 11.45 for 2015 and - 1.14, 5.28, 4.93 and 27.83 for 2016, respectively, was also observed. Although the statistical performance of the model simulation for daily average CH₄ fluxes was lower than that of the monthly average, we found that the results for total fluxes agreed well between the observed and the simulated values (E = 6.79% and difference = 3.3%). Principal component analysis (PCA) showed that CH₄, GWL and rainfall were correlated with each other and explained 41.7% of the total variation. GWL was found to be relatively important in determining the CH₄ fluxes in the naturally inundated pristine tropical peatland. These results suggest that GWL is an essential input variable for the DNDC model for predicting CH₄ fluxes from the pristine tropical peatland in Sarawak on a monthly basis.