A comparative analysis of LSTM and ARIMA for enhanced real-time air pollutant levels forecasting using sensor fusion with ground station data

One of the most basic needs any human being to survive is air. Unfortunately, this need polluted by many natural factors like volcanic eruptions, forest fires, and man-induced transportation emission. Unpolluted air now an ideal environment that can never be achieved. So, pollution levels should monitored continuously. However, monitoring will not fix environment. Forecasting these make society more aware help prepare safety measures. This research paper aims forecast pollutant comparing futuristic machine learning models, which are Long Short-Term Memory (LSTM) Auto-Regressive Integrated Moving Average (ARIMA) performed on ground station data from Central Pollution Control Board (CPCB), collected a low-cost IoT hardware setup, fused data. The LSTM ARIMA models have been used in future. Further, main novelty show concept sensor fusion increases accuracy dataset. outputs obtained after implementing accurate results when compared with sensors.