Air Quality Prediction With Machine Learning Algorithms
Research Topic :
The sustenance of human life relies on the air we breathe. It is imperative to continuously monitor and comprehend its quality for our overall well-being. The detrimental effects of air pollution are evident, leading to millions worldwide experiencing physiological ailments and succumbing to respiratory fatalities. Scientific evidence underscores that air pollution stands as the paramount environmental peril. The surge in toxic gas emissions, a consequence of rapid industrialization and escalating population levels, has taken a severe toll on our health. Unbridled pollution has precipitated a marked deterioration in air quality, significantly impacting our overall well-being.
In this project, we want to measure air pollution using data science and machine learning algorithms and reduce the cost of future measurements by doing this with as few measurement units as possible.
Data Set :
Our data set (Air Quality ) contains averages of hourly responses of a gas multi-sensor system deployed in an Italian region and gas range references from an analyzer.
This dataset contains 9358 instances of hourly averaged responses from an array of 5 metal oxide chemical sensors embedded in an Air Quality Chemical Multisensor Device. The device was located on the field in a significantly polluted area, at road level, within an Italian city. Data were recorded from March 2004 to February 2005 (one year) representing the longest freely available recordings of on-field deployed air quality chemical sensor device responses. Ground Truth hourly averaged concentrations for CO, Non-Metanic Hydrocarbons, Benzene, Total Nitrogen Oxides (NOx), and Nitrogen Dioxide (NO2) and was provided by a co-located reference certified analyzer. Missing values are tagged with -200 value.
Related Works :
Air Quality Prediction By Machine Learning Models: A Predictive Study On The Indian Coastal City of Visakhapatnam
This study applied AQI to Visakhapatnam city in Andhra Pradesh, India, from July 2017 to September 2022, focusing on 12 pollutants and 10 meteorological parameters LightGBM, Random Forest, Catboost, Adaboost, and XGBoost. Using various machine learning models including AQI is claimed to be predicted with 0.76 RMSE, 0.58 MSE, and 0.60 MAE. So, by leveraging historical data and machine learning algorithms, they believe they can accurately predict future urban air quality levels on a global scale.
Prediction of Air Quality Index Using Machine Learning Techniques: A Comparative Analysis
In this article, researchers aimed to find the most effective way to estimate AQI (Air Quality Index) to help climate control. This article aims to develop a different solution to this problem by developing a new algorithm named SMOTE. In this article, researchers compare results with and without using the SMOTE algorithm.
Prediction of Air Quality Index Using Supervised Machine Learning Algorithms
This paper uses various machine learning algorithms to predict the Air Quality Index used to control pollution to avoid significant health concerns. Researchers used Multiple Linear Regression (MLR), Support Vector Regression (SVR), and Random Forest Regression (RFR), algorithms and compared them by using MSE and RMSE.
Air Quality Index (AQI) Prediction Using Machine Learning for Ahmedabad City
This study aims to compare various machine learning methods such as SARIMA, SVM, and LSTM for air quality index prediction for the city of Ahmedabad in Gujarat, India. This study is carried out based on the data provided by the Center. It focuses on support vector machine algorithms with the Pollution Control Board of India and the RBF kernel model. Therefore, the results obtained are comparatively better when compared with SARIMA and LSTM models as well as other kernels of support vector machine models for Ahmedabad city.
