A Decadal Study of PM2.5 Concentrations over Delhi using MERRA-2 and Ground Measurements: Predictive Insights via Machine Learning
NOPR - NISCAIR Online Periodicals Repository
View Archive InfoField | Value | |
Title |
A Decadal Study of PM2.5 Concentrations over Delhi using MERRA-2 and Ground Measurements: Predictive Insights via Machine Learning
|
|
Creator |
Singh, Sumit
Singh, Vikash Kumar, Ajay Singh, Amarendra Srivastava, Atul Kumar Pathak, Virendra |
|
Subject |
PM2.5 concentrations
Delhi Machine learning models Air pollution MERRA-2 |
|
Description |
764-778
This study investigates the spatial and temporal variations of PM2.5 concentrations in Delhi from 2014 to 2023, utilizing ground-based measurements from the Central Pollution Control Board (CPCB) and MERRA-2 reanalysis data. The analysis reveals strong positive correlations (r > 0.90) across all districts, highlighting city-wide factors influencing PM2.5 levels, such as vehicular emissions, industrial activities, and regional weather patterns. Seasonal patterns show PM2.5 concentrations peaking during winter, attributed to lower temperatures, reduced wind speeds, and increased emissions from heating sources.To enhance the accuracy of PM2.5 predictions, various machine learning (ML) models were employed, including Extra Trees Regressor, Random Forest Regressor, Light Gradient Boosting Machine (LGBM) Regressor, and a Stacking Regressor. These models utilized MERRA-2 sub-parameters like Dust, Organic Carbon, Black Carbon, Sea Salt, and Sulfate. The Stacking Regressor demonstrated the best performance, achieving an R² value of 0.67 and a significant improvement in correlation with CPCB measurements (r = 0.86). The ML models significantly improved the prediction accuracy of PM2.5 concentrations compared to the original MERRA-2 data, reducing the Mean Bias from -39.4 μg/m3 toaround 10.4μg/m3 and the Root Mean Squared Error (RMSE) from 71.1 μg/m3 to below 40 μg/m3. Additionally, the Fraction of predictions within a factor of 2 increased from 0.61 for MERRA-2 to over 0.89 for all ML models.These findings underscore the effectiveness of integrating machine learning models with MERRA-2 sub-parameters to accurately estimate PM2.5 concentrations. This approach provides more reliable predictions of air quality, essential for developing targeted and effective air quality management strategies in Delhi. |
|
Date |
2024-09-17T11:20:52Z
2024-09-17T11:20:52Z 2024-09 |
|
Type |
Article
|
|
Identifier |
0975-0959 (Online); 0301-1208 (Print)
http://nopr.niscpr.res.in/handle/123456789/64546 https://doi.org/10.56042/ijpap.v62i9.11443 |
|
Language |
en
|
|
Publisher |
NIScPR-CSIR,India
|
|
Source |
IJPAP Vol.62(09) [September 2024]
|
|