AN EFFICIENT AIR QUALITY INDEX MONITORING AND PREDICTION SYSTEM USING FEMTO SAT TECHNOLOGY AND MACHINE LEARNING

Abstract

In recent times, the global population surge has led to a parallel increase in air pollution levels, posing significant threats to the economy, environment, and public well-being. Traditionally, air pollution is measured by placing sensors on buildings spaced a certain distance apart. Nevertheless, there are disadvantages to this strategy, such as higher power consumption for sensor operation in each house and restricted application in remote areas with inadequate infrastructure. Using satellite data from FEMTOSAT for autonomous air pollution monitoring, analysis and mitigation emerges as a ground-breaking solution to these problems. This innovative approach circumvents the limitations associated with traditional methods, offering a more comprehensive and versatile solution. FEMTOSAT leverages the capabilities of LoRa (Long Range) communication, a crucial component in the Internet of Things (IoT), enabling data transmission over extended distances while consuming minimal power. LoRa communication is essential to the FEMTOSAT installation because it makes information sharing between the satellite and ground stations easier. Data is transmitted and received using radio frequency (RF) impulses, which make for a dependable and effective form of communication. The Air Quality Index (AQI) for a particular place is then determined using the environmental data that was gathered by the satellite. An important metric for measuring air quality, the AQI provides information about the degree of pollution or cleanliness in a particular place. The AQI is determined by a number of factors, including the concentrations of pollutants including NO2, CO, O3, PM2.5, SO2, and PM10. Making use of machine learning (ML) techniques such as Support Vector Machines (SVM), direct regression, time series analysis and logistic regression to forecast and analyse AQI trends makes it very efficient. One of the distinctive features of this study is the development of AQI mappings, which are derived from the comprehensive AQI data collected at specific locations. It has been shown via thorough investigation that ML-based AQI prediction models are more consistent and dependable overall. Accuracy and precision have been ensured in the data collection process through the simplified integration of new technology and smart sensors. Only machine learning algorithms can manage the complex analysis needed to produce safe and reliable predictions from large datasets in the field of environmental monitoring. The main objective of this effort is exemplified by the integration of Integrated Sensors as the payload in the FEMTOSAT mission. The benefits of the system—such as its affordability, lightweight construction, resilience, redundancy and low power consumption—highlight FEMTOSAT's applicability and effectiveness in handling the intricate problems related to air pollution monitoring.