PM2.5 Air Pollution Forecasts for Newcastle City Centre, Thailand
by Rachadawan Darlai·Updated 2mo ago
65.8 MB8files
Available on 1 platform
Sign in to view source links and access this dataset
Description
A 65.8 MB repository contains a dataset, code, and forecast results for PM2.5 concentrations in Newcastle city centre, Thailand. The project by Rachadawan Darlai, last updated in April 2026, uses Gaussian Process Regression to provide reproducible air pollution forecasting and analysis. It includes CSV data, Python notebooks, and supporting files for model training and prediction.
Use Cases
Train and test Gaussian Process Regression models for PM2.5 forecasting based on the provided code and data.
Analyze temporal patterns of urban air pollution in a specific city centre based on the described location.
Reproduce and validate air pollution forecast results based on the included notebooks and instructions.
Modify forecasting parameters and time windows for PM2.5 concentration based on the project's adaptable framework.
Strengths
Includes full code and instructions for reproducible forecasting using Gaussian Process Regression.
Dataset and project files are packaged together in a 65.8 MB repository for immediate use.
Released under a permissive CC-BY-4.0 license, allowing for reuse and modification.
Limitations
Row count and specific column-level documentation are absent; field semantics must be inferred after download.
Geographic coverage is limited to a single urban centre, which may limit generalizability.
Description metadata is limited; actual data quality and temporal coverage require manual inspection after download.
Provenance
Source
Rachadawan Darlai via figshare.
Collection Method
Likely contains sensor measurements or derived data for forecasting, as described in the project overview.
Time Range
null
Freshness
Last updated 2026-04-14 08:36:36; freshness should be verified.
Geography
Newcastle city centre, Thailand.
Requires Python 3.x and a Jupyter Notebook environment to run the provided `gp_forecast.ipynb` code.