A Comparison of Machine Learning Methods to Forecast Tropospheric Ozone Levels in Delhi

Juarez, Eliana Kai; Petersen, Mark

doi:10.3390/atmos13010046

Cited by 26 publications

(9 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To summarize, the best model performance in classifying daily peaks was found for O 3 and CO. The O 3 contaminant is one of the easiest pollutants to predict due to its high dependence on solar radiation activity, which always peaks at noon anywhere on the planet [30]. Some variations may be common due to increased cloudiness; however, those are also easy to predict using trends of relative humidity and atmospheric pressure.…”

Section: Resultsmentioning

confidence: 99%

Ensemble Deep Learning for Classification of Pollution Peaks

Chau

ZALAKEVICIUTE

Rybarczyk

2022

WIT Transactions on Ecology and the Environment

View full text Add to dashboard Cite

The concentration peaks of atmospheric pollutants are the most challenging and important phenomena in air quality forecasting. The fact that these elevated levels of pollution do not seem to follow any specific pattern explains why current models still struggle to provide an accurate prediction of these harmful events for human health. The present study tackles this issue by testing several supervised learning methods to discriminate between peak and no peak of concentrations of five contaminants: NO2, CO, SO2, PM2.5, and O3. The classification performance of ensemble decision tree (gradient boosting machine (GBM)) models and ensemble deep learning (EDL) models are compared. The results reveal that the EDL outperforms the GBM model. An analysis of the variable importance (SHapley additive exPlanations (SHAP)) shows that both temporal and meteorological features have an impact on the proposed models. In particular, time of day and wind speed are the most important features to explain the performance of the ensemble DL models.

show abstract

Section: Resultsmentioning

confidence: 99%

Ensemble Deep Learning for Classification of Pollution Peaks

Chau

ZALAKEVICIUTE

Rybarczyk

2022

WIT Transactions on Ecology and the Environment

View full text Add to dashboard Cite

show abstract

“…Extreme gradient boosting (XGB) and RF were used to successfully forecast the hourly air quality in Delhi, India [12]. A study to predict the air quality in Beijing showed that GB performed much better in prediction accuracy and operation efficiency in comparison to XGB [13].…”

Section: Previous and Related Workmentioning

confidence: 99%

Using Machine Learning Methods to Forecast Air Quality: A Case Study in Macao

Lei

Monjardino³

et al. 2022

Atmosphere

View full text Add to dashboard Cite

Despite the levels of air pollution in Macao continuing to improve over recent years, there are still days with high-pollution episodes that cause great health concerns to the local community. Therefore, it is very important to accurately forecast air quality in Macao. Machine learning methods such as random forest (RF), gradient boosting (GB), support vector regression (SVR), and multiple linear regression (MLR) were applied to predict the levels of particulate matter (PM10 and PM2.5) concentrations in Macao. The forecast models were built and trained using the meteorological and air quality data from 2013 to 2018, and the air quality data from 2019 to 2021 were used for validation. Our results show that there is no significant difference between the performance of the four methods in predicting the air quality data for 2019 (before the COVID-19 pandemic) and 2021 (the new normal period). However, RF performed significantly better than the other methods for 2020 (amid the pandemic) with a higher coefficient of determination (R2) and lower RMSE, MAE, and BIAS. The reduced performance of the statistical MLR and other ML models was presumably due to the unprecedented low levels of PM10 and PM2.5 concentrations in 2020. Therefore, this study suggests that RF is the most reliable prediction method for pollutant concentrations, especially in the event of drastic air quality changes due to unexpected circumstances, such as a lockdown caused by a widespread infectious disease.

show abstract

“…Sethi et al [12] proposed a method to predict the concentration of PM2. Enebish et al, [8] Kiftiyani & Nazhifah [21] Masood & Ahmad [9] Usmani [10] Bozdag [11] Sethi et al [12] Sharma et al [22] Juarez & Petersen [23] Sharma et al [31] Castelli et al [32] Asgari et al [33] Chen et al [34] Gocheva-Ilieva et al [35] Lee et al [13] Doresawamy et al [14] Ma et al [15] Bhalgat et al [24] Shen et al [25] Ma et al [40] Bouzoukis et al [36] Bouzoukis et al [36] Masmoudi et al [37] Khan et al [26] Kanjo [27] Lepperod [29] Peng et al [38] Zhang et al [17] Rubal et al [28] Liu et al [39] Fu et al [ LR gave promising results, and after that, CBL was applied to selected features in which RF improved the veracity in predicting PM2.5…”

Section: Literature Reviewmentioning

confidence: 99%

Comparative Analysis of Machine Learning Techniques for Predicting Air Pollution

Ashraf¹,

Akram²,

Usman³

2022

Research Journal Of Computer Science And Information Technology

View full text Add to dashboard Cite

The modern and motorized way of life has cultured air pollution. Air pollution has become the biggest rival of robust living. This situation is becoming more lethal in developing countries and so in Pakistan. Hence, this inquiry was carried out to propose an architecture design that could make real-time prediction of air pollution with another purpose of scanning the frequently adopted algorithm in past investigations. In addition, it was also intended to narrate the toxic effects of air pollution on human health. So, this research was carried out on a large dataset of Seoul as an adequate dataset of Pakistan was not attainable. The dataset consisted of three years (2017-2019) including 647,512 instances and 11 attributes. The four distinctive algorithms termed Random Forest, Linear Regression, Decision Tree and XGBoosting were employed. It was inferred that XGB is more promising and feasible in predicting concentration level of NO2, O3, SO2, PM10, PM2.5 and CO with the lowest RMSE and MAE values of 0.0111, 0.0262, 0.0168, 49.64, 41.68 and 0.1856 and 0.0067, 0.0096, 0.0017, 12.28, 7.63 and 0.0982 respectively. Furthermore, it was found out as well that the Random Forest was preferred mostly in the previous studies related to air pollution prophecy while many probes supported that air pollution is very detrimental to human health especially long-lasting exposure causes lung cancer, respiratory and cardiovascular diseases.

show abstract

A Comparison of Machine Learning Methods to Forecast Tropospheric Ozone Levels in Delhi

Cited by 26 publications

References 60 publications

Ensemble Deep Learning for Classification of Pollution Peaks

Ensemble Deep Learning for Classification of Pollution Peaks

Using Machine Learning Methods to Forecast Air Quality: A Case Study in Macao

Comparative Analysis of Machine Learning Techniques for Predicting Air Pollution

Contact Info

Product

Resources

About