Supplementary Material_Random Forest Modelling of Multi-City PM2.5 Variability using CMIP6 Predictors

Source
DataCite
Published
2026
Country
India
License
Open Data Commons Attribution
Themes
Air Quality & Pollution, Climate & Temperature, Machine Learning & AI

Get the data from DataCite

About this dataset

This project investigates the long-term evolution of PM₂.₅ concentrations over Delhi, Pune, and Mumbai by integrating Random Forest machine learning with meteorological predictors from four CMIP6 General Circulation Models under SSP245 and SSP585 scenarios. Historical relationships between climate variables and PM₂.₅ were used to generate projections extending to 2100 and to identify future pollution hotspots and associated uncertainties. The resulting datasets can be reused for atmospheric science, climate change, public health, exposure assessment, and urban sustainability studies, and may support policy development and mitigation planning. The uniqueness of this work lies in combining multiple CMIP6 GCMs with a Random Forest framework and a multi-model ensemble approach to capture nonlinear climate–PM₂.₅ interactions and quantify inter-model variability. The project is intended...

How the data was collected

The source metadata does not specify a detailed collection methodology. Provenance: this record was harvested from DataCite and published by Designsafe-CI. Consult the original source for methodological details, temporal coverage, and access constraints.

Browse sustainability datasets on SusanHub