Forecasting Air Quality in Tripoli: An Evaluation of Deep Learning Models for Hourly PM2.5 Surface Mass Concentrations

Esager, Marwa Winis Misbah; Ünlü, Kamil Demirberk

doi:10.3390/atmos14030478

Cited by 11 publications

(5 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, the RF model is the one with the highest R 2 value in predictions. The result is similar to a study in Turkey and Libya that showed that the most important predictor variables of PM are its own lagged value and the decisionmaking capabilities of the machine learning and deep learning models in air quality management [34,35].…”

Section: Resultssupporting

confidence: 86%

“…Despite the good performance of the ML models, it may be difficult to capture some of the very low or high pollution episodes in a special scenario, such as the outbreak of the COVID-19 pandemic in early 2020. The result of this study is very similar to studies in other regions [34,35], with a high R 2 and low RMSE and MAE. diction of CO.…”

Section: Limitation Of the Studysupporting

confidence: 89%

See 1 more Smart Citation

Application of ANN, XGBoost, and Other ML Methods to Forecast Air Quality in Macau

Lei

2023

Sustainability

View full text Add to dashboard Cite

Air pollution in Macau has become a serious problem following the Pearl River Delta’s (PRD) rapid industrialization that began in the 1990s. With this in mind, Macau needs an air quality forecast system that accurately predicts pollutant concentration during the occurrence of pollution episodes to warn the public ahead of time. Five different state-of-the-art machine learning (ML) algorithms were applied to create predictive models to forecast PM2.5, PM10, and CO concentrations for the next 24 and 48 h, which included artificial neural networks (ANN), random forest (RF), extreme gradient boosting (XGBoost), support vector machine (SVM), and multiple linear regression (MLR), to determine the best ML algorithms for the respective pollutants and time scale. The diurnal measurements of air quality data in Macau from 2016 to 2021 were obtained for this work. The 2020 and 2021 datasets were used for model testing, while the four-year data before 2020 and 2021 were used to build and train the ML models. Results show that the ANN, RF, XGBoost, SVM, and MLR models were able to provide good performance in building up a 24-h forecast with a higher coefficient of determination (R2) and lower root mean square error (RMSE), mean absolute error (MAE), and biases (BIAS). Meanwhile, all the ML models in the 48-h forecasting performance were satisfactory enough to be accepted as a two-day continuous forecast even if the R2 value was lower than the 24-h forecast. The 48-h forecasting model could be further improved by proper feature selection based on the 24-h dataset, using the Shapley Additive Explanations (SHAP) value test and the adjusted R2 value of the 48-h forecasting model. In conclusion, the above five ML algorithms were able to successfully forecast the 24 and 48 h of pollutant concentration in Macau, with the RF and SVM models performing the best in the prediction of PM2.5 and PM10, and CO in both 24 and 48-h forecasts.

show abstract

Section: Resultssupporting

confidence: 86%

Section: Limitation Of the Studysupporting

confidence: 89%

Application of ANN, XGBoost, and Other ML Methods to Forecast Air Quality in Macau

Lei

2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…For predicting the air quality in Tripoli [14], Esager and Ünlü proposed an evaluation of deep learning models for hourly PM 2.5 surface mass concentrations. Since the analyzed data are a time series, the Box-Jenkins methodology is generally used to model such a dataset.…”

Section: Literature Reviewmentioning

confidence: 99%

Effective Air Quality Prediction Using Reinforced Swarm Optimization and Bi-Directional Gated Recurrent Unit

Gurumoorthy,

Kokku,

Falkowski-Gilski

et al. 2023

Sustainability

View full text Add to dashboard Cite

In the present scenario, air quality prediction (AQP) is a complex task due to high variability, volatility, and dynamic nature in space and time of particulates and pollutants. Recently, several nations have had poor air quality due to the high emission of particulate matter (PM2.5) that affects human health conditions, especially in urban areas. In this research, a new optimization-based regression model was implemented for effective forecasting of air pollution. Firstly, the input data were acquired from a real-time Beijing PM2.5 dataset recorded from 1 January 2010 to 31 December 2014. Additionally, the newer real-time dataset was recorded from 2016 to 2022 for four Indian cities: Cochin, Hyderabad, Chennai, and Bangalore. Then, data normalization was accomplished using the Min-Max normalization technique, along with correlation analysis for selecting highly correlated variables (wind direction, temperature, dew point, wind speed, and historical PM2.5). Next, the important features from the highly correlated variables were selected by implementing an optimization algorithm named reinforced swarm optimization (RSO). Further, the selected optimal features were given to the bi-directional gated recurrent unit (Bi-GRU) model for effective AQP. The extensive numerical analysis shows that the proposed model obtained a mean absolute error (MAE) of 9.11 and 0.19 and a mean square error (MSE) of 2.82 and 0.26 on the Beijing PM2.5 dataset and a real-time dataset. On both datasets, the error rate of the proposed model was minimal compared to other regression models.

show abstract

“…To overcome these shortcomings, models have been implemented using machine learning techniques, such as multi-layer perceptron [18], recurrent neural network [19], decision trees [20], random forests [21], and support vector machines [22]. Following recent developments in hardware, convolutional neural networks [23,24], long short-term memory (LSTM) [7,24], gated recurrent unit (GRU) [24,25], and bidirectional long short-term memory (Bi-LSTM) [26] have been widely used to forecast PM 2. 5 .…”

Section: Introductionmentioning

confidence: 99%

PM2.5 Concentration Forecasting Using Weighted Bi-LSTM and Random Forest Feature Importance-Based Feature Selection

Kim

Jung

et al. 2023

Atmosphere

View full text Add to dashboard Cite

Particulate matter (PM) in the air can cause various health problems and diseases in humans. In particular, the smaller size of PM2.5 enable them to penetrate deep into the lungs, causing severe health impacts. Exposure to PM2.5 can result in respiratory, cardiovascular, and allergic diseases, and prolonged exposure has also been linked to an increased risk of cancer, including lung cancer. Therefore, forecasting the PM2.5 concentration in the surrounding is crucial for preventing these adverse health effects. This paper proposes a method for forecasting the PM2.5 concentration after 1 h using bidirectional long short-term memory (Bi-LSTM). The proposed method involves selecting input variables based on the feature importance calculated by random forest, classifying the data to assign weight variables to reduce bias, and forecasting the PM2.5 concentration using Bi-LSTM. To compare the performance of the proposed method, two case studies were conducted. First, a comparison of forecasting performance according to preprocessing. Second, forecasting performance between deep learning (long short-term memory, gated recurrent unit, and Bi-LSTM) and conventional machine learning models (multi-layer perceptron, support vector machine, decision tree, and random forest). In case study 1, The proposed method shows that the performance indices (RMSE: 3.98%p, MAE: 5.87%p, RRMSE: 3.96%p, and R2:0.72%p) are improved because weights are given according to the input variables before the forecasting is performed. In case study 2, we show that Bi-LSTM, which considers both directions (forward and backward), can effectively forecast when compared to conventional models (RMSE: 2.70, MAE: 0.84, RRMSE: 1.97, R2: 0.16). Therefore, it is shown that the proposed method can effectively forecast PM2.5 even if the data in the high-concentration section is insufficient.

show abstract

Forecasting Air Quality in Tripoli: An Evaluation of Deep Learning Models for Hourly PM2.5 Surface Mass Concentrations

Cited by 11 publications

References 37 publications

Application of ANN, XGBoost, and Other ML Methods to Forecast Air Quality in Macau

Application of ANN, XGBoost, and Other ML Methods to Forecast Air Quality in Macau

Effective Air Quality Prediction Using Reinforced Swarm Optimization and Bi-Directional Gated Recurrent Unit

PM2.5 Concentration Forecasting Using Weighted Bi-LSTM and Random Forest Feature Importance-Based Feature Selection

Contact Info

Product

Resources

About