Prediction of Air Quality Combining Wavelet Transform, DCCA Correlation Analysis and LSTM Model

Zhang, Zheng; Chen, Haibo; Huang, Xiaoli

doi:10.3390/app13052796

Cited by 5 publications

(4 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, Zhang et al [22] proposed a deep learning model for air quality prediction utilizing the long shortterm memory (LSTM) network. Their study included a series of experiments using Detrended Cross-Correlation Analysis (DCCA) to investigate the relationship between predicting levels of several air pollutants (SO2, NO2, PM10, PM2.5, O3, and CO) and meteorological data, such as temperature, barometric pressure, humidity, and wind speed.…”

Section: Literature Reviewsmentioning

confidence: 99%

Comparative Analysis Study for Air Quality Prediction in Smart Cities Using Regression Techniques

Al-Eidi,

Amsaad,

Darwish

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Air pollution has detrimental impacts on our physical health and the quality of our living environment, particularly in smart cities. Monitoring and predicting air pollution is crucial to empower individuals to make informed decisions that protect their health. Predicting air quality accurately plays an important effective action plan to mitigate air pollution and create healthier and more sustainable environments. This can be achieved by relying on the Air Quality Index, one of the most reliable indicators for air pollutant concentration levels in certain cities. This study provides a comparative analysis study for air quality prediction using three regression techniques: Random Forest regression, Linear regression, and Decision Tree regression, employing the AQI values. This comparison aims to identify the most efficient model based on various evaluation criteria, such as Mean Absolute Error and R 2 measures. Additionally, it considers both error rate minimization and processing time efficiency of each regression model evaluated within two distinct frameworks as other important measures to determine the best-fitted model. The findings of this study showcase the superiority of the Decision Tree regression technique over the other models, demonstrating its exceptional accuracy with a high R 2 score and low error rate. Moreover, integrating cloud computing technology has yielded significant improvements in model execution time, substantially enhancing the overall efficiency of the prediction process. By leveraging distributed computing resources, real-time air quality forecasting becomes feasible, enabling timely decision-making and proactive measures to address air pollution episodes.

show abstract

Section: Literature Reviewsmentioning

confidence: 99%

Comparative Analysis Study for Air Quality Prediction in Smart Cities Using Regression Techniques

Al-Eidi,

Amsaad,

Darwish

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Signal processing methods play a vital role in combined models and directly impact the model's predictive performance. Standard sequence preprocessing techniques include Wavelet Decomposition (WD) [50] and Empirical Mode Decomposition (EMD) [51]. The EMD decomposition algorithm doesn't rely on any basis function and differs significantly from wavelet decomposition.…”

Section: Introductionmentioning

confidence: 99%

Hybrid Climate Forecasting: Variational Mode Decomposition and Convolutional Neural Network with Long-Term Short Memory

Han,

Bazai,

Bhatti

et al. 2023

Pol. J. Environ. Stud.

View full text Add to dashboard Cite

Ozone (O 3 ) pollution has surfaced as a significant threat to urban air quality in contemporary years. The precise and efficient forecast of ozone levels is fundamental in the mitigation and management of ozone pollution. Even though the air quality monitoring network offers useful multi-source pollutant concentration data for predicting ozone levels, existing models still grapple with issues arising from outlier and redundant sites influencing prediction precision, and cross-contamination between different pollutants. Also, the non-linear and volatile nature of monthly runoff makes accurate prediction more complex, provide a more granular and timely view of atmospheric flow variations. In this research, we introduce a hybrid model that unites Variational Modal Decomposition (VMD), particularly useful for separating mixed signals or extracting meaningful patterns from noisy or complex data, Convolutional Long Short-Term Memory Neural Network (CNN-LSTM) is designed for processing sequences of data with grid-like structures, such as images or video frames. CNN-LSTMs use convolutional operations to capture spatial patterns and LSTM units to model temporal dependencies, making them effective for tasks like video analysis, image sequence prediction, and spatiotemporal data processing, and VMD-CNN-LSTM to counter these issues. We commence by deconstructing the historical data series from the Nanjing air quality monitoring stations using VMD. Then, the Ensemble Empirical Mode

show abstract

“…In recent years, the application of new powerful hybrid methods such as continuous and discrete wavelet analysis, combined with ML, has gained popularity. Recent publications in this line in the field of environmental sciences are, for example [20]- [22]. A combination of function expansions in a wavelet series with ARIMA models is used in [20].…”

Section: Introductionmentioning

confidence: 99%

“…Twelve algorithms and large amount of meteorological predictors have been used to achieve correlation coefficients of the forecasts about 88-89%. Air pollution data (SO2, NO2, PM10, PM2.5, O3, and CO) and four meteorological variables (temperature, barometric pressure, humidity, and wind speed) are modeled in [22] using wavelet de-noising, detrended correlation analysis, and long short-term memory (LSTM) methods.…”

Section: Introductionmentioning

confidence: 99%

Discrete Wavelet Transform and Ensemble Tree Algorithms for Air Pollutant Modeling: A Case Study

Gocheva-Ilieva,

Ivanov,

Stoimenova-Minova

et al. 2023

ijmst

View full text Add to dashboard Cite

Air pollution is one of the greatest environmental problems of our time on a global and local scale. Elevated and even low but constant levels of harmful emissions in the air in urbanized areas pose serious risks to the health of the population. This paper develops a new approach for statistical modeling of time series of air pollutants, depending on meteorological factors. A new framework based on discrete wavelet transform (DWT) is proposed for decomposing pollutant's time series as a sum of components that represent trend, seasonality, and other specific characteristics. A key element in the applied DWT is an adaptive scheme for selecting the threshold value to control the reverse DWT's accuracy for achieving better prediction of the time series values. The resulting components are modeled with cutting-edge predictive ensemble tree algorithms, including bagging, boosting, and stacking techniques. This approach is tested with real data measured with a mobile automated station in the Plovdiv region, Bulgaria. All models are evaluated, analyzed, and cross-validated. The models are applied for short-term pollution forecasts.

show abstract

Prediction of Air Quality Combining Wavelet Transform, DCCA Correlation Analysis and LSTM Model

Cited by 5 publications

References 24 publications

Comparative Analysis Study for Air Quality Prediction in Smart Cities Using Regression Techniques

Comparative Analysis Study for Air Quality Prediction in Smart Cities Using Regression Techniques

Hybrid Climate Forecasting: Variational Mode Decomposition and Convolutional Neural Network with Long-Term Short Memory

Discrete Wavelet Transform and Ensemble Tree Algorithms for Air Pollutant Modeling: A Case Study

Contact Info

Product

Resources

About