Machine learning models with explainable AI for PM2.5 prediction for Urban air quality assessment
4 affiliations
- 1Department of Civil Engineering, Yeshwantrao Chavan College of Engineering, Nagpur, India
- 2Department of Chemistry, Anjuman College of Engineering and Technology, Nagpur, India
- 3School of Civil Engineering, Lovely Professional University, Phagwara, Punjab, India
- 4Department of Civil Engineering, Symbiosis Institute of Technology, Pune Campus, Symbiosis International (Deemed University), Pune, India
Abstract
Fine particulate matter (PM2.5) remains a critical air quality issue in rapidly urbanizing Indian cities because of its strong association with respiratory, cardiovascular, environmental, and climatic impacts. This study aimed to develop an accurate and interpretable machine learning framework for predicting PM2.5 in Nagpur, Maharashtra, India. Approximately 4000 observations, including PM2.5, NO₂, SO₂, NH₃, O₃, wind speed, wind direction, relative humidity, solar radiation, and temperature, were utilized into 70% training and 30% testing subsets. Six machine learning models decision tree, extra trees, random forest, K-nearest neighbors, XGBoost, and SVR were developed and validated using 10-fold cross validation. The results indicated that the Decision Tree model achieved the highest prediction performance, with R² values of 0.94 and 0.90 for training and testing, respectively with lowest error values, with RMSE of 7.50-8.90 µg/m³, MAE of 5.40-6.60 µg/m³, and MAPE of 10.20-12.80%. SHAP analysis identified NO₂, O₃, RH, and NH₃ as the most influential predictors for processes in PM2.5variation. The overall model performance followed the order such as DT > ET > RF > KNN > XGBoost > SVR. The developed modeling framework can be applied to PM2.5 prediction in other regions by incorporating local emission profiles and meteorological dynamics.
Related
- Advancing Near-Term Water Quality Forecasting with Explainable Machine Learning and Probabilistic Uncertainty Quantification
- Tracing settlement dynamics in Latium vetus: Explainable machine learning perspectives from the Bronze to the Early iron age
- An explainable deep learning framework for sub-seasonal to seasonal agricultural drought prediction over India
- Revealing nonlinear and interaction mechanisms of resource and environmental carrying capacity through explainable machine learning
- Deciphering the impacts of meteorology on surface ozone variability in eastern China using explainable machine learning models
BibTeX
@article{waghmare2026machine,
title = {{Machine learning models with explainable AI for PM2.5 prediction for Urban air quality assessment}},
author = {Charuta Waghmare and Shahbaz Khan and Monali Wagh and Amit Kumar Dhir and Geeta Mehta and Vinaykumar S. Jatti and Khalid Ansari and Amruta Yadav},
journal = {MethodsX},
year = {2026},
month = oct,
doi = {10.1016/j.mex.2026.104217},
url = {https://europepmc.org/article/PMC/PMC13718848},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Machine learning models with explainable AI for PM2.5 prediction for Urban air quality assessment
AU - Charuta Waghmare
AU - Shahbaz Khan
AU - Monali Wagh
AU - Amit Kumar Dhir
AU - Geeta Mehta
AU - Vinaykumar S. Jatti
AU - Khalid Ansari
AU - Amruta Yadav
PY - 2026
DA - 2026/10/17
JO - MethodsX
DO - 10.1016/j.mex.2026.104217
UR - https://europepmc.org/article/PMC/PMC13718848
AB - Fine particulate matter (PM2.5) remains a critical air quality issue in rapidly urbanizing Indian cities because of its strong association with respiratory, cardiovascular, environmental, and climatic impacts. This study aimed to develop an accurate and interpretable machine learning framework for predicting PM2.5 in Nagpur, Maharashtra, India. Approximately 4000 observations, including PM2.5, NO₂, SO₂, NH₃, O₃, wind speed, wind direction, relative humidity, solar radiation, and temperature, were utilized into 70% training and 30% testing subsets. Six machine learning models decision tree, extra trees, random forest, K-nearest neighbors, XGBoost, and SVR were developed and validated using 10-fold cross validation. The results indicated that the Decision Tree model achieved the highest prediction performance, with R² values of 0.94 and 0.90 for training and testing, respectively with lowest error values, with RMSE of 7.50-8.90 µg/m³, MAE of 5.40-6.60 µg/m³, and MAPE of 10.20-12.80%. SHAP analysis identified NO₂, O₃, RH, and NH₃ as the most influential predictors for processes in PM2.5variation. The overall model performance followed the order such as DT > ET > RF > KNN > XGBoost > SVR. The developed modeling framework can be applied to PM2.5 prediction in other regions by incorporating local emission profiles and meteorological dynamics.
SN - 2215-0161
ER -