Hourly Air Quality Index (AQI) of Bangladesh (2000-2025)

🌍 Bangladesh Air Quality Index (AQI) Dataset (2000-2025)

Comprehensive Historical Air Pollution Data Across 103 Cities

---

 📊 Dataset Overview

This dataset provides **comprehensive air quality measurements** for **103 cities** across Bangladesh, spanning from **2000 to 2025**. It contains over **3.19 million hourly observations** of key air pollutants and environmental indicators, making it one of the most extensive air quality datasets for Bangladesh available for public use.

Key Features:✅ **103 cities** covering all major regions of Bangladesh✅ **3.18+ million hourly observations** (2000-2025)✅ **8 pollutant measurements**: PM10, PM2.5, CO, CO₂, NO₂, SO₂, O₃, AQI✅ **Precise geolocation** with latitude/longitude coordinates✅ **Standardized format** with consistent column naming✅ **Research-ready** for environmental science, public health, and ML applications

---

📋 Dataset Summary

| **Property**            | **Value**                                    ||-------------------------|----------------------------------------------|| **Total Records**       | 3,193,198 rows                              || **Number of Cities**    | 103 cities                                  || **Time Period**         | 2000-2025 (25 years)                        || **Temporal Resolution** | Hourly measurements                         || **File Format**         | CSV (Comma-separated values)                || **Total Columns**       | 13                                          || **Geographic Coverage** | All major regions of Bangladesh             |

---📅 City-wise Data Coverage

| **City Name** | **From Date** | **Total Rows** ||---------------|---------------|----------------|| Dhaka | 2000-01-01 | 227,016 || Narsingdi | 2020-01-01 | 37,991 || Rangpur | 2022-08-04 | 28,993 || Sherpur | 2022-08-04 | 28,993 || Dinājpur | 2022-08-04 | 28,993 || Lākshām | 2022-08-04 | 28,993 || Comilla | 2022-08-04 | 28,993 || Thākurgaon | 2022-08-04 | 28,993 || Teknāf | 2022-08-04 | 28,993 || Tungi | 2022-08-04 | 28,993 || Sylhet | 2022-08-04 | 28,993 || Dohār | 2022-08-04 | 28,993 || Jamālpur | 2022-08-04 | 28,993 || Shibganj | 2022-08-04 | 28,993 || Sātkhira | 2022-08-04 | 28,993 || Sirājganj | 2022-08-04 | 28,993 || Netrakona | 2022-08-04 | 28,993 || Sandwīp | 2022-08-04 | 28,993 || Shāhzādpur | 2022-08-04 | 28,993 || Rāmganj | 2022-08-04 | 28,993 || Rājshāhi | 2022-08-04 | 28,993 || Purbadhala | 2022-08-04 | 28,993 || Pirojpur | 2022-08-04 | 28,993 || Panchagarh | 2022-08-04 | 28,993 || Patiya | 2022-08-04 | 28,993 || Parbatipur | 2022-08-04 | 28,993 || Nārāyanganj | 2022-08-04 | 28,993 || Nālchiti | 2022-08-04 | 28,993 || Nāgarpur | 2022-08-04 | 28,993 || Nageswari | 2022-08-04 | 28,993 || Mymensingh | 2022-08-04 | 28,993 || Muktāgācha | 2022-08-04 | 28,993 || Mirzāpur | 2022-08-04 | 28,993 || Maulavi Bāzār | 2022-08-04 | 28,993 || Morrelgonj | 2022-08-04 | 28,993 || Mehendiganj | 2022-08-04 | 28,993 || Mathba | 2022-08-04 | 28,993 || Lalmanirhat | 2022-08-04 | 28,993 || Kushtia | 2022-08-04 | 28,993 || Kālīganj | 2022-08-04 | 28,993 || Jhingergācha | 2022-08-04 | 28,993 || Joypur Hāt | 2022-08-04 | 28,993 || Ishurdi | 2022-08-04 | 28,993 || Habiganj | 2022-08-04 | 28,993 || Gaurnadi | 2022-08-04 | 28,993 || Gafargaon | 2022-08-04 | 28,993 || Feni | 2022-08-04 | 28,993 || Rāipur | 2022-08-04 | 28,993 || Sarankhola | 2022-08-04 | 28,993 || Chilmāri | 2022-08-04 | 28,993 || Chhāgalnāiya | 2022-08-04 | 28,993 || Lālmohan | 2022-08-04 | 28,993 || Khagrachhari | 2022-08-04 | 28,993 || Chhātak | 2022-08-04 | 28,993 || Bhātpāra Abhaynagar | 2022-08-04 | 28,993 || Bherāmāra | 2022-08-04 | 28,993 || Bhairab Bāzār | 2022-08-04 | 28,993 || Bāndarban | 2022-08-04 | 28,993 || Kālia | 2022-08-04 | 28,993 || Baniachang | 2022-08-04 | 28,993 || Bājitpur | 2022-08-04 | 28,993 || Badarganj | 2022-08-04 | 28,993 || Narail | 2022-08-04 | 28,993 || Tungipāra | 2022-08-04 | 28,993 || Sarishābāri | 2022-08-04 | 28,993 || Sakhipur | 2022-08-04 | 28,993 || Raojān | 2022-08-04 | 28,993 || Phultala | 2022-08-04 | 28,993 || Pālang | 2022-08-04 | 28,993 || Pār Naogaon | 2022-08-04 | 28,993 || Nabīnagar | 2022-08-04 | 28,993 || Lakshmīpur | 2022-08-04 | 28,993 || Kesabpur | 2022-08-04 | 28,993 || Jahedpur | 2022-08-04 | 28,993 || Hājīganj | 2022-08-04 | 28,993 || Farīdpur | 2022-08-04 | 28,993 || Uttar Char Fasson | 2022-08-04 | 28,993 || Chittagong | 2022-08-04 | 28,993 || Char Bhadrāsan | 2022-08-04 | 28,993 || Bera | 2022-08-04 | 28,993 || Burhānuddin | 2022-08-04 | 28,993 || Sātkania | 2022-08-04 | 28,993 || Cox's Bāzār | 2022-08-04 | 28,993 || Khulna | 2022-08-04 | 28,993 || Bhola | 2022-08-04 | 28,993 || Barisāl | 2022-08-04 | 28,993 || Jessore | 2022-08-04 | 28,993 || Pābna | 2022-08-04 | 28,993 || Tāngāil | 2022-08-04 | 28,993 || Bogra | 2022-08-04 | 28,993 || Pīrgaaj | 2022-08-04 | 28,993 || Nawābganj | 2022-08-04 | 28,993 || Mādārīpur | 2022-08-04 | 28,993 || Kishorganj | 2022-08-04 | 28,993 || Manikchari | 2022-08-04 | 28,993 || Bhāndāria | 2022-08-04 | 28,993 || Fatikchari | 2022-08-04 | 28,993 || Saidpur | 2022-08-04 | 28,993 || Nowlamary | 2022-08-04 | 28,993 || Magura | 2022-08-04 | 28,993 || Azimpur | 2022-08-04 | 28,993 || Gaibandha | 2022-08-04 | 28,993 || Paltan | 2022-08-04 | 28,993 |

---

🌐 Geographic Coverage

The dataset includes air quality data from **103 cities** distributed across Bangladesh, covering:

- **Major Metropolitan Areas**: Dhaka, Chittagong, Sylhet, Rajshahi, Khulna, Barisāl, Rangpur- **Divisional Cities**: All 8 divisions represented- **District Headquarters**: 50+ district-level cities- **Sub-district Towns**: 40+ upazila-level locations- **Coastal Regions**: Cox's Bāzār, Teknāf, Sandwīp- **Border Areas**: Panchagarh, Thākurgaon, Bandarban- **River Delta Cities**: Multiple locations in the Ganges-Brahmaputra-Meghna delta

**Geographic Coordinates Range:**- **Latitude**: 20.75°N to 26.63°N- **Longitude**: 88.01°E to 92.67°E

---

📌 Column Descriptions

The dataset contains **13 columns** with detailed air quality and location information:

🔢 Identifier & Location Columns

| **Column**   | **Type** | **Description**                                           | **Example**        ||--------------|----------|-----------------------------------------------------------|--------------------|| `city_id`    | Integer  | Unique numeric identifier for each city                   | `1185241`          || `city_name`  | String   | Official name of the city                                 | `Dhaka`            || `lat`        | Float    | Latitude coordinate (decimal degrees, WGS84)              | `23.7104`          || `lon`        | Float    | Longitude coordinate (decimal degrees, WGS84)             | `90.40744`         |

⏰ Temporal Column

| **Column**   | **Type** | **Description**                                           | **Example**              ||--------------|----------|-----------------------------------------------------------|--------------------------|| `datetime`   | String   | Date and time of measurement (ISO 8601 format)            | `2022-08-04T00:00`       |

🌫️ Air Pollutant Columns

| **Column**            | **Type** | **Unit**    | **Description**                                                      | **Typical Range**  ||-----------------------|----------|-------------|----------------------------------------------------------------------|--------------------|| `pm10`                | Float    | μg/m³       | Particulate Matter ≤10 micrometers (coarse dust, pollen)             | 10-500 μg/m³       || `pm2_5`               | Float    | μg/m³       | Particulate Matter ≤2.5 micrometers (fine particles from combustion) | 5-300 μg/m³        || `carbon_monoxide`     | Float    | μg/m³       | CO - Colorless, odorless gas from incomplete combustion              | 200-10,000 μg/m³   || `carbon_dioxide`      | Float    | μg/m³       | CO₂ - Greenhouse gas indicator                                       | 600,000-900,000 μg/m³|| `nitrogen_dioxide`    | Float    | μg/m³       | NO₂ - Reddish-brown gas from vehicle emissions                      | 20-200 μg/m³       || `sulphur_dioxide`     | Float    | μg/m³       | SO₂ - Gas from fossil fuel combustion                                | 5-100 μg/m³        || `ozone`               | Float    | μg/m³       | O₃ - Ground-level ozone (photochemical pollutant)                    | 50-150 μg/m³       |

 📈 Composite Index

| **Column** | **Type** | **Description**                                                          | **Scale**       ||------------|----------|--------------------------------------------------------------------------|-----------------|| `aqi`      | Float    | Air Quality Index (US EPA standard) - Composite measure of air quality  | 0-500+          |

AQI Scale Reference:- 0-50: Good (Green)- 51-100: Moderate (Yellow)- 101-150: Unhealthy for Sensitive Groups (Orange)- 151-200: Unhealthy (Red)- 201-300: Very Unhealthy (Purple)- 301+: Hazardous (Maroon)

---

🎯 Use Cases

### 🔬 **Research Applications**1. **Air Quality Trend Analysis**: Study long-term pollution trends across Bangladesh (2000-2025)2. **Seasonal Pattern Detection**: Identify seasonal variations in pollutant concentrations3. **Spatial Analysis**: Compare air quality between urban and rural areas4. **Health Impact Studies**: Correlate air pollution with public health data5. **Climate Change Research**: Analyze the relationship between air quality and climate variables

### 🤖 **Machine Learning & Data Science**1. **AQI Prediction Models**: Train models to forecast future air quality2. **Anomaly Detection**: Identify unusual pollution events or data irregularities3. **Feature Engineering**: Create temporal features (hour, day, month, season) for modeling4. **Clustering Analysis**: Group cities by pollution profiles5. **Time Series Forecasting**: Predict pollutant concentrations using LSTM, ARIMA, Prophet

### 🏛️ **Policy & Urban Planning**1. **Environmental Policy Evaluation**: Assess the impact of pollution control measures2. **Urban Development Planning**: Inform sustainable city development strategies3. **Public Health Interventions**: Design targeted health advisories during high-pollution periods4. **Industrial Zone Planning**: Identify optimal locations for industrial activities

### 💼 **Business & Public Services**1. **Smart City Applications**: Integrate with IoT systems for real-time monitoring2. **Health Advisory Systems**: Create public air quality notification services3. **Insurance Risk Assessment**: Evaluate environmental risk factors4. **Real Estate Analytics**: Assess property values based on air quality

---

## 📂 Sources & Methodology

Data Collection- **Collection Period**: 2000-2025- **Measurement Frequency**: Hourly observations- **Quality Control**: Automated validation and consistency checks

### **Geographic Data**- **City List**: Compiled from Bangladesh administrative divisions- **Coordinates**: WGS84 coordinate system (EPSG:4326)- **City Selection**: Includes divisional, district, and major upazila headquarters

---

## 🛠️ Technical Specifications

- **Encoding**: UTF-8- **Delimiter**: Comma (`,`)- **Date Format**: ISO 8601 (`YYYY-MM-DDTHH:MM`)- **Missing Values**: Empty cells or `null`- **Numeric Precision**: Float (up to 6 decimal places for coordinates)- **File Structure**: Single merged CSV file (`AQI Bangladesh.csv`)

---

## 📚 Citation

If you use this dataset in your research or project, please cite it as:

### **APA Format**```Bangladesh Air Quality Index Dataset (2000-2025). (2025). Comprehensive hourly air pollution measurements for 103 cities in Bangladesh. Retrieved from [https://www.kaggle.com/datasets/shakilofficial0/hourly-air-quality-index-aqi-of-bangladesh](Kaggle/shakilofficial0)```

### **BibTeX Format**```bibtex@dataset{bangladesh_aqi_2025,  title={Bangladesh Air Quality Index Dataset (2000-2025)},  author={[shakilofficial0/Kaggle]},  year={2025},  description={Comprehensive hourly air pollution measurements for 103 cities in Bangladesh},  url={[https://www.kaggle.com/datasets/shakilofficial0/hourly-air-quality-index-aqi-of-bangladesh]},  note={3,193,198 observations covering PM10, PM2.5, CO, CO2, NO2, SO2, O3, and AQI}}```

### **MLA Format**```"Bangladesh Air Quality Index Dataset (2000-2025)." Comprehensive Hourly Air Pollution Measurements for 103 Cities in Bangladesh, 2025. Web. [Access Date].```

---

## 📜 License

This dataset is released under the **Creative Commons Attribution 4.0 International (CC BY 4.0)** license.

**You are free to:**- ✅ Share — copy and redistribute the material- ✅ Adapt — remix, transform, and build upon the material- ✅ Commercial use — use for any purpose, including commercially

**Under the following terms:**- 📝 **Attribution** — You must give appropriate credit, provide a link to the license, and indicate if changes were made

For more details, visit: https://creativecommons.org/licenses/by/4.0/

---

## 🔄 Updates & Maintenance

- **Last Updated**: November 2025- **Update Frequency**: Dataset includes data up to 2025- **Version**: 1.0- **Status**: Complete dataset with historical data (2000-2025)

---

## 🔗 Related Resources

- **OpenWeatherMap Air Pollution API**: https://openweathermap.org/api/air-pollution- **Bangladesh Air Quality**: https://aqicn.org/city/bangladesh/- **WHO Air Quality Guidelines**: https://www.who.int/news-room/feature-stories/detail/what-are-the-who-air-quality-guidelines- **US EPA AQI Guide**: https://www.airnow.gov/aqi/aqi-basics/

---

## 🙏 Acknowledgments

- **OpenWeatherMap** for providing comprehensive air quality data via their API- **Bangladesh Meteorological Department** for supporting air quality monitoring initiatives- **Contributors** who helped validate and improve this dataset

---

## 🏷️ Keywords

`air quality`, `AQI`, `Bangladesh`, `pollution`, `PM2.5`, `PM10`, `environmental data`, `time series`, `geospatial data`, `climate change`, `public health`, `machine learning`, `data science`, `atmospheric science`, `urban planning`, `South Asia`

---

**📍 Dataset Statistics at a Glance:**

| Metric | Value ||--------|-------|| 🏙️ Cities | 103 || 📊 Total Records | 3,193,198 || 📅 Years Covered | 25 (2000-2025) || 🕐 Temporal Resolution | Hourly || 📏 Pollutants Measured | 8 || 🗂️ File Format | CSV |

---

*This dataset represents one of the most comprehensive air quality resources for Bangladesh, enabling researchers, policymakers, and data scientists to better understand and address air pollution challenges in the region.* 🌱