Multi-Site Air Pollutant Prediction Using Long Short Term Memory

The current pandemic highlights the significance and impact of air pollution on individuals. When it comes to climate sustainability, is a major challenge. Because distinctive nature, unpredictability, great changeability in reality toxins particulates, detecting quality puzzling task. Simultaneously, ability predict or classify monitor becoming increasingly important, particularly urban areas, due well documented negative resident’s health environment. To better comprehend condition quality, this research proposes predicting levels from real-time data. This study use deep learning techniques forecast levels. Layers, activation functions, number epochs were used create suggested Long Short-Term Memory (LSTM) network based neural layer design. proposed Deep Learning as structure for high-accuracy prediction investigated obtained accuracy nearly 82% compared earlier records. Determining Air Quality Index (AQI) danger would assist government finding appropriate ways authorize approaches reduce pollutants keep inhabitants informed about findings.