# Ecosphere Forecasting — Data

来源：https://www.kaggle.com/competitions/ecosphere-forecasting/data

采集时间：2026-10-20T06:58:36Z

## Files

- **train.csv** - The training set containing input features and corresponding air quality levels.
- **test.csv** - The test set for which predictions will be made.


## Columns

- `Temperature_C` - Average temperature of the region in °C.
- `Humidity_%` - Relative humidity recorded in the region.
- `PM2.5_Concentration_µg_m3` - Fine particulate matter levels.
- `PM10_Concentration_µg_m3` - Coarse particulate matter levels.
- `NO2_Concentration_ppb` - Nitrogen dioxide levels.
- `SO2_Concentration_ppb` - Sulfur dioxide levels.
- `CO_Concentration_ppm` - Carbon monoxide levels.
- `Proximity_to_Industrial_Areas_km` - Distance to the nearest industrial zone.
- `Population_Density_people_km2` - Number of people per square kilometer in the region.
- `Air_Quality_Level` - The target variable representing air quality levels, categorized as:
  - **Good**: Clean air with low pollution levels.
  - **Moderate**: Acceptable air quality but with some pollutants present.
  - **Poor**: Noticeable pollution that may cause health issues for sensitive groups.
  - **Hazardous**: Highly polluted air posing serious health risks to the population.

---

This dataset focuses on air quality assessment across various regions.