Application of deep learning techniques for analysis and prediction of particulate matter at Kota city, India
Air pollution significantly threatens human health and the environment, making accurate prediction of pollutant concentrations crucial for effective mitigation. This study leverages deep learning models, specifically Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, to predict c...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Bologna
2024-12-01
|
| Series: | EQA |
| Subjects: | |
| Online Access: | https://eqa.unibo.it/article/view/20687 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549908245479424 |
|---|---|
| author | Lovish Sharma Hajari Singh Mahendra Pratap Choudhary |
| author_facet | Lovish Sharma Hajari Singh Mahendra Pratap Choudhary |
| author_sort | Lovish Sharma |
| collection | DOAJ |
| description | Air pollution significantly threatens human health and the environment, making accurate prediction of pollutant concentrations crucial for effective mitigation. This study leverages deep learning models, specifically Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, to predict concentrations of PM10 and PM2.5. The analysis utilizes hourly air quality data from July 1, 2017, to December 30, 2022, collected from the portals of the Central Pollution Control Board (CPCB) and Rajasthan State Pollution Control Board (RSPCB) for Kota city Rajasthan. Data preprocessing involves cleaning, normalization using a min-max scaler, and handling missing values with Multiple Imputation in XLSTAT. The methodology encompasses dataset loading, preprocessing, and data splitting, followed by model training and evaluation. Python libraries such as Pandas, Numpy, TensorFlow, and Matplotlib are employed for data analysis and visualization. Performance metrics, including Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and R2 score, are calculated to assess the models' predictive accuracy. The results demonstrate that GRU model effectively capture temporal dependencies in air quality data, offering reliable predictions for PM10 and PM2.5 concentrations with 41.85 and 17.73 RMSE values for PM10 and PM2.5 . These findings underscore the potential of deep learning models in air pollution forecasting, providing valuable insights for policymakers to implement timely interventions. |
| format | Article |
| id | doaj-art-205d7dbe66404ffbb3397faaae8513c0 |
| institution | Kabale University |
| issn | 2039-9898 2281-4485 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | University of Bologna |
| record_format | Article |
| series | EQA |
| spelling | doaj-art-205d7dbe66404ffbb3397faaae8513c02025-01-10T11:17:44ZengUniversity of BolognaEQA2039-98982281-44852024-12-016610711510.6092/issn.2281-4485/2068719059Application of deep learning techniques for analysis and prediction of particulate matter at Kota city, IndiaLovish Sharma0Hajari Singh1Mahendra Pratap Choudhary2Department of Civil Engineering, Rajasthan Technical University, Kota (Raj.)Department of Civil Engineering, Rajasthan Technical University, Kota (Raj.)Department of Civil Engineering, Rajasthan Technical University, Kota (Raj.)Air pollution significantly threatens human health and the environment, making accurate prediction of pollutant concentrations crucial for effective mitigation. This study leverages deep learning models, specifically Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, to predict concentrations of PM10 and PM2.5. The analysis utilizes hourly air quality data from July 1, 2017, to December 30, 2022, collected from the portals of the Central Pollution Control Board (CPCB) and Rajasthan State Pollution Control Board (RSPCB) for Kota city Rajasthan. Data preprocessing involves cleaning, normalization using a min-max scaler, and handling missing values with Multiple Imputation in XLSTAT. The methodology encompasses dataset loading, preprocessing, and data splitting, followed by model training and evaluation. Python libraries such as Pandas, Numpy, TensorFlow, and Matplotlib are employed for data analysis and visualization. Performance metrics, including Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and R2 score, are calculated to assess the models' predictive accuracy. The results demonstrate that GRU model effectively capture temporal dependencies in air quality data, offering reliable predictions for PM10 and PM2.5 concentrations with 41.85 and 17.73 RMSE values for PM10 and PM2.5 . These findings underscore the potential of deep learning models in air pollution forecasting, providing valuable insights for policymakers to implement timely interventions.https://eqa.unibo.it/article/view/20687air pollutionmachine learningpm10pm2.5lstmgru |
| spellingShingle | Lovish Sharma Hajari Singh Mahendra Pratap Choudhary Application of deep learning techniques for analysis and prediction of particulate matter at Kota city, India EQA air pollution machine learning pm10 pm2.5 lstm gru |
| title | Application of deep learning techniques for analysis and prediction of particulate matter at Kota city, India |
| title_full | Application of deep learning techniques for analysis and prediction of particulate matter at Kota city, India |
| title_fullStr | Application of deep learning techniques for analysis and prediction of particulate matter at Kota city, India |
| title_full_unstemmed | Application of deep learning techniques for analysis and prediction of particulate matter at Kota city, India |
| title_short | Application of deep learning techniques for analysis and prediction of particulate matter at Kota city, India |
| title_sort | application of deep learning techniques for analysis and prediction of particulate matter at kota city india |
| topic | air pollution machine learning pm10 pm2.5 lstm gru |
| url | https://eqa.unibo.it/article/view/20687 |
| work_keys_str_mv | AT lovishsharma applicationofdeeplearningtechniquesforanalysisandpredictionofparticulatematteratkotacityindia AT hajarisingh applicationofdeeplearningtechniquesforanalysisandpredictionofparticulatematteratkotacityindia AT mahendrapratapchoudhary applicationofdeeplearningtechniquesforanalysisandpredictionofparticulatematteratkotacityindia |