Processed dataset for: Meteorological characterization of the Pantanal Biome using K-Means clustering

This repository contains the processed dataset used in the manuscript entitled:

"Meteorological characterization of the Pantanal Biome using K-Means clustering"

The dataset includes monthly aggregated meteorological and fire occurrence variables used for statistical analysis and clustering. The variables provided are:

- Date: Observation date (YYYY-MM-DD)- RH: Relative humidity (%), calculated from air temperature and dew point temperature (ERA5)- PREC: Precipitation (mm), obtained from the MERGE product (INPE)- TMAX: Maximum temperature (°C), obtained from the SAMeT product (INPE)- FOCOS: Number of fire occurrences, obtained from the Queimadas Program (INPE)- Cluster: Cluster classification derived from K-means clustering

Data sources:- ERA5 reanalysis dataset (air temperature and dew point temperature): https://cds.climate.copernicus.eu/datasets- MERGE precipitation product (INPE): http://ftp.cptec.inpe.br/modelos/tempo/MERGE/GPM/DAILY- SAMeT maximum temperature product (INPE): http://ftp.cptec.inpe.br/modelos/tempo/SAMeT/DAILY/TMAX- Queimadas Program (INPE): http://www.inpe.br/queimadas/bdqueimadas

Processing:Relative humidity was calculated from air temperature and dew point temperature.All variables were aggregated to a monthly scale.Clustering was performed using the K-means algorithm.

Temporal coverage:2003–2024

Spatial coverage:Pantanal Biome, Brazil

Notes:This dataset contains processed data derived from publicly available sources. All processing steps were performed by the authors.

License:This dataset is distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0).