World Air Quality Index by City and Coordinates

Keywords: World, Air Quality

Background

The World Air Quality Index by City and Coordinates dataset is a comprehensive collection of air quality information from various cities around the world. The dataset contains 14 columns. The objective of this project was to utilize deep learning techniques, specifically an Artificial Neural Network (ANN) model, to predict the Air Quality Index (AQI) based on the given city names and coordinates. The ANN model was developed using the Sequential API in TensorFlow or Kera’s. The dataset was preprocessed by encoding the categorical variables such as 'Country' and 'City', while the numerical variables were appropriately normalized to ensure compatibility with the ANN model. The target class for the prediction task consisted of several AQI categories, including 'Good', 'Moderate', 'Unhealthy', 'Unhealthy for Sensitive Groups', 'Very Unhealthy', and 'Hazardous'. The ANN model was configured with a kernel initializer of "random uniform" and an activation function of "SoftMax" since the target class belongs to multiclass classification. The architecture of the model included an input layer, followed by 5 hidden layers.

Aim & Objectives

Aim
To Predict the World Air Quality Based on City using DL Method
Objective
Develop an accurate Artificial Neural Network (ANN) model to predict Air Quality Index (AQI) categories based on city names and coordinates, leveraging deep learning techniques. The project aims to showcase the effectiveness of ANN models in categorizing and predicting air quality, with the objective of providing reliable tools for real-world applications in global air quality monitoring and management.

Research Methodology

ANN Technique used

Software & Tools

Jupyter, Google Collab

— Preview truncated. The complete document (full chapters, references, diagrams, and appendices) is shared with clients as part of project delivery. —