Spatiotemporal analysis of fine particulate matter for India (1980–2021) from MERRA-2 using ensemble machine learning

Kumar, Vikas; Malyan, Vasudev; Sahu, Manoranjan; Biswal, Basudev; Pawar, Mayank; Dev, Inder

doi:10.1016/j.apr.2023.101834

Cited by 9 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, w was also calculated as a function of the BC to OA ratio (w=5.355(±0.50)×exp(-0.428(±0.25)×(BC/OA), R 2 =0.60). Here, OA was derived by multiplying OC by a factor of 1.8, a methodology consistent with previous studies (Turpin et 200 al., 2001;Chow et al, 2015;Navinya et al, 2020;Provençal et al, 2017;Kumar et al, 2023). Although this factor does not impact the R-square (R 2 ) of the relationship, it facilitates comparisons with other studies that have utilized the BC to OA ratio to derive kBrC,550.…”

Section: Spatial Variation Of Brc Absorption 195mentioning

confidence: 99%

“…Such an underestimation would propagate uncertainties to radiative forcing calculations, 300 especially over South Asia. 1.8 is widely used to convert OC into OA (Turpin et al, 2001;Chow et al, 2015;Navinya et al, 2020;Provençal et al, 2017;Kumar et al, 2023). The grey shaded area represents the relationship reported by previous studies (Saleh et al, 2014;Lu et al, 2015;Luo et al, 2022), and the equations for the shaded area are given in the supplementary information (S2, S3 and figure S1).…”

Section: Source Specific Brcmentioning

confidence: 99%

“…(a) Mean KBrC,550 versus BC to OA ratio (kBrC,550= 0.0365(±0.006)×(BC/OA)+0.0047(±0.0037), R 2 =0.93) and (b) w versus the BC to OA ratio (w=5.355(±0.50)×exp(-0.428(±0.25)×(BC/OA)), R 2 =0.60). Here, OA = OC x 1.8: the factor 3051.8 is widely used to convert OC into OA(Turpin et al, 2001;Chow et al, 2015;Navinya et al, 2020; Provençal et al, 2017;Kumar et al, 2023). The grey shaded area represents the relationship reported by previous studies(Saleh et al, 2014;Lu et al, 2015;Luo et al, 2022), and the equations for the shaded area are given in the supplementary information (S2, S3 and figureS1).…”

mentioning

confidence: 99%

See 2 more Smart Citations

Brownness of Organics in Anthropogenic Biomass Burning Aerosols over South Asia

Navinya,

Kapoor,

Anurag

et al. 2024

Preprint

View full text Add to dashboard Cite

Abstract. In South Asia, biomass is burned for energy and waste disposal, producing brown carbon (BrC) aerosols whose climatic impacts are highly uncertain. To assess these impacts, a real-world understanding of BrC’s physio-optical properties is essential. For this region, the order-of-magnitude variability in BrC’s spectral refractive index as a function of particle volatility distribution is poorly understood. This leads to oversimplified model parameterization and subsequent underestimation of regional radiative forcing. Here we used the field-collected aerosol samples from major anthropogenic biomass activities to examine the methanol-soluble BrC optical properties. We show a strong relation between the absorption strength, wavelength dependence, and thermo-optical fractions of carbonaceous aerosols. Our observations show strongly absorbing BrC near the Himalayan foothills that may accelerate glacier melt, further highlighting the limitations of climate models where variable BrC properties are not considered. These findings provide crucial inputs for refining climate models and developing effective regional strategies to mitigate BrC.

show abstract

Section: Spatial Variation Of Brc Absorption 195mentioning

confidence: 99%

Section: Source Specific Brcmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Brownness of Organics in Anthropogenic Biomass Burning Aerosols over South Asia

Navinya,

Kapoor,

Anurag

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…Shapley additive explanation (SHAP) is one such mathematical concept from cooperative game theory which is coupled with any ML model to explain and quantify the contribution of each predictor variable for each instance of prediction (Lundberg and Lee 2017). This helps in developing a better understanding of factors affecting air pollution overall and for episodical investigation (Wu et Kumar et al 2023). However, no study has explored ML models for visibility prediction or used methods like meteorological normalization and XML to quantify and understand the effect of meteorology on visibility degradation in GBK.…”

Section: Introductionmentioning

confidence: 99%

Estimating visibility and understanding factors influencing its variations at Bangkok airport using machine learning and a game theory-based approach

Aman,

Panyametheekul,

Sudhibrabha

et al. 2024

Preprint

View full text Add to dashboard Cite

In this study, a range of machine learning (ML) models including random forest, adaptive boosting, gradient boosting, extreme gradient boosting, light gradient boosting, cat boosting, and a stacked ensemble model, were employed to predict visibility at Bangkok airport. Furthermore, the impact of influential factors was examined using the Shapley method, an interpretable ML technique inspired by the game theory-based approach. Air pollutant data from seven Pollution Control Department monitoring stations, visibility, and meteorological data from the Thai Meteorological Department's Weather station at Bangkok Airport, ERA5_LAND, and ERA5 datasets, and time-related dummy variables were considered. Daytime visibility ((here, 8–17 local time) was screened for rainfall, and ML models were developed for visibility prediction during the dry season (November – April). The light gradient boosting model is identified as the most effective individual ML model with superior performance in three out of four evaluation metrics (i.e., highest ρ, zero MB, second lowest ME, and lowest RMSE). However, the SEM outperformed all the individual models in visibility prediction at both hourly and daily time scales. The seasonal mean and standard deviation of normalized meteorological visibility are lower than those of the original visibility, indicating more influence of meteorology than emission reduction on visibility improvement. The Shapley analysis identified RH, PM2.5, PM10, day of the season year, and O3 as the five most important variables. At low relative humidity (RH), there is no notable impact on visibility. Nevertheless, beyond this threshold, negative correlation between RH and visibility. An inverse correlation between visibility and both PM2.5 and PM10 was identified. Visibility is negatively correlated with O3 at lower to moderate concentrations, with diminishing impact at very high concentrations. The day of the season year (i.e., Julian day) (JD) exhibits an initial negative and later positive association with visibility, suggesting a periodic effect. The dependence of the Shapley values of PM2.5 and PM10 on RH, and the equal step size method to understand RH effects, suggest the effect of hygroscopic growth of aerosol on visibility. Findings from this research suggest the feasibility of employing machine learning techniques for predicting visibility and comprehending the factors influencing its fluctuations. Based on the above findings, certain policy–related implications, and future work have been suggested.

show abstract

“…Sayeed et al (Sayeed et al, 2022) improved the PM2.5 concentration in the continental United States using Random Forest (RF) approach coped with meteorology and aerosol species of MERRA-2. Some studies have demonstrated the feasibility of tree-based model to estimate PM2.5 concentrations in India (Kumar et al, 2023;Dhandapani et al, 2023;Bali et al, 2019). However, it is challenging to establish long-term, full-coverage, high accuracy, open-source PM data products in India due to insufficient model robustness and implementation capacity (Dey et al, 2020;Kumar et al, 2023).…”

Section: Introductionmentioning

confidence: 99%

Reconstructing long-term (1980–2022) daily ground particulate matter datasets in India (LongPMInd)

Wang,

Zhang,

Zhao

et al. 2024

Preprint

View full text Add to dashboard Cite

Abstract. Severe airborne particulate matter (PM, including PM2.5 and PM10) pollution in India has caused widespread concern. Accurate PM datasets are fundamental for scientific policymaking and health impact assessment, while surface observations in India are limited due to scarce sites and uneven distribution. In this work, a simple structured, efficient, and robust model based on the Light Gradient Boosting Machine (LightGBM) was developed to fuse multi-source data and estimate long-term (1980–2022) historical daily ground PM datasets in India (LongPMInd). The LightGBM model shows good accuracy with out-of-sample, out-of-site, and out-of-year cross-validation CV test R2 of 0.77, 0.70, and 0.66, respectively. Small performance gaps between PM2.5 training and testing (delta RMSE of 1.06, 3.83, and 7.74 μg m-3) indicate low overfitting risks. With great generalization ability, the open-accessible, long-term, and high-quality daily PM2.5 and PM10 products were then reconstructed (10 km, 1980–2022). It shows that India has experienced severe PM pollution in the Indo-Gangetic Plain (IGP), especially in winter. PM concentrations significantly increased (p<0.05) in most regions since 2000 (0.34 μg m-3 year-1). The turning point occurred in 2018 when the Indian government launched the National Clean Air Program, PM2.5 concentrations declined in most regions (- 0.78 μg m-3 year-1) during 2018–2022. Severe PM2.5 pollution caused continuous increased attributable premature mortalities, from 0.73 (95 % CI: 0.65–0.80) million in 2000 to 1.22 (95 % CI: 1.03–1.41) million in 2019, particularly in the IGP, where attributable mortality increased from 0.36 to 0.60 million. The LongPMInd datasets have the potential to support multi-applications of air quality management, public health, and climate change. The daily and monthly PM2.5 and PM10 datasets are publicly accessible at https://doi.org/10.5281/zenodo.10073944 (Wang et al., 2023a).

show abstract

Spatiotemporal analysis of fine particulate matter for India (1980–2021) from MERRA-2 using ensemble machine learning

Cited by 9 publications

References 30 publications

Brownness of Organics in Anthropogenic Biomass Burning Aerosols over South Asia

Brownness of Organics in Anthropogenic Biomass Burning Aerosols over South Asia

Estimating visibility and understanding factors influencing its variations at Bangkok airport using machine learning and a game theory-based approach

Reconstructing long-term (1980–2022) daily ground particulate matter datasets in India (LongPMInd)

Contact Info

Product

Resources

About