.history/README_20250328221159.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+<img src="./figures/toar_classifier_v2.png" alt="My image" with="100">

.history/README_20250328221727.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+
+<img src="./figures/toar_classifier_v2.png" alt="My image" with="100">

.history/README_20250328221948.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with="100">

.history/README_20250328221958.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with="100">

.history/README_20250328222004.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with="100">
+

.history/README_20250328222021.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+

.history/README_20250328222519.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+### Run code
\ No newline at end of file

.history/README_20250328222601.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+
+
+### Run code
\ No newline at end of file

.history/README_20250328223018.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+`data` is the folder contening all data use in this work and the prediction of station cotegory form Machine Learning (ML) model.
+
+### Run code
\ No newline at end of file

.history/README_20250328223037.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+`data` is the folder contening all data use in this work and the prediction of station cotegory form Machine Learning (ML) model.
+
+### Run code
\ No newline at end of file

.history/README_20250328223328.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+`data` is the folder contening all data use in this work and the prediction of station cotegory form Machine Learning (ML) model.
+`TOAR-classifier_v2.ipynb` is the notebook contening the code
+`requirements.txt` containts 
+
+### Run code
\ No newline at end of file

.history/README_20250328223358.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+`data` is the folder contening all data use in this work and the prediction of station cotegory form Machine Learning (ML) model.
+`TOAR-classifier_v2.ipynb` is the notebook contening the code
+`requirements.txt` containts all neccessary packages.
+
+### Run code
\ No newline at end of file

.history/README_20250328223446.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+### Files
+`data` is the folder contening all data use in this work and the prediction of station cotegory form Machine Learning (ML) model.
+`TOAR-classifier_v2.ipynb` is the notebook contening the code
+`requirements.txt` containts all neccessary packages.
+
+### Run code
\ No newline at end of file

.history/README_20250328223627.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+### Files
+`data` is the folder contening all data use in this work, including the predictions of station cotegories form Machine Learning (ML) model.
+`TOAR-classifier_v2.ipynb` is the notebook contening the code
+`requirements.txt` contains all neccessary packages.
+
+### Run code
\ No newline at end of file

.history/README_20250328223710.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+### Files
+`data` is the folder contening all data use in this work, including the predictions of station cotegories form Machine Learning (ML) model.
+
+`TOAR-classifier_v2.ipynb` is the notebook contening the code
+
+`requirements.txt` contains all neccessary packages.
+
+### Run code
\ No newline at end of file

.history/README_20250328223741.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+### Files
+`data` is the folder contening all data use in this work, including the predictions of station cotegories form Machine Learning (ML) model.
+
+`TOAR-classifier_v2.ipynb` is the notebook contening the code
+
+`requirements.txt` contains all neccessary packages.
+
+### Run code

.history/README_20250328224638.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+### Files
+`data` is the folder contening all data use in this work, including the predictions of station cotegories form Machine Learning (ML) model.
+
+`TOAR-classifier_v2.ipynb` is the notebook contening the code
+
+`requirements.txt` contains all neccessary packages.
+
+### Run code
+#### Install required packages
+Install all the required packages for the project by uncommenting the first cell in the notebook and running the cell
\ No newline at end of file

.history/README_20250328224640.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+### Files
+`data` is the folder contening all data use in this work, including the predictions of station cotegories form Machine Learning (ML) model.
+
+`TOAR-classifier_v2.ipynb` is the notebook contening the code
+
+`requirements.txt` contains all neccessary packages.
+
+### Run code
+#### Install required packages
+Install all the required packages for the project by uncommenting the first cell in the notebook and running the cell
\ No newline at end of file

.history/README_20250328224932.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+### Files
+`data` is the folder contening all data use in this work, including the predictions of station cotegories form Machine Learning (ML) model.
+
+`TOAR-classifier_v2.ipynb` is the notebook contening the code
+
+`requirements.txt` contains all neccessary packages.
+
+### Run code
+clone the project by running the following
+`https://gitlab.jsc.fz-juelich.de/esde/toar-public/ml_toar_station_classification.git`
+#### Install required packages
+Install all the required packages for the project by uncommenting the first cell in the notebook and running the cell
\ No newline at end of file

.history/README_20250328225642.md

+## TOAR-classifier v2: A data-driven classification tool for global air quality stations
+This study develops a machine learning approach to classify 23,974 air quality monitoring stations in the TOAR database as urban, suburban, or rural using K-means clustering and an ensemble of supervised classifiers. The proposed method outperforms existing classifications, improving suburban accuracy and providing a more reliable foundation for air quality assessments.
+<img src="./figures/toar_classifier_v2.png" alt="My image" with=100>
+
+### Files
+`data` is the folder contening all data use in this work, including the predictions of station cotegories form Machine Learning (ML) model.
+
+`TOAR-classifier_v2.ipynb` is the notebook contening the code
+
+`requirements.txt` contains all neccessary packages.
+
+### Run code
+NB: This has been test on Ubuntu 24.04
+clone the project by running the following
+`https://gitlab.jsc.fz-juelich.de/esde/toar-public/ml_toar_station_classification.git`
+change directory to ml_toar_station_classification, `cd ml_toar_station_classification`
+creat virtual environment `python -m venv TOAR-classifier_v2` # feel free to change the virtual environment as convenient 
+activate the created venv `python -m ipykernel install --user --name=TOAR-classifier_v2 --display-name "Python (TOAR-classifier_v2)"`
+
+
+
+#### Install required packages
+Install all the required packages for the project by uncommenting the first cell in the notebook and running the cell
\ No newline at end of file