Main Track: Environmental Monitoring

Weather constitutes a crucial factor that impacts many of the human outdoor activities, whether they are related to obligations or pleasure. In the contemporary era, due to climate change, the weather is more unstable and the forecasting task is more challenging than ever. By combining the Internet of Things (IoT) with Artificial Intelligence (AI), a new research field emerges that is called Artificial Intelligence of Things (AIoT) and could offer significant possibilities for the research community in order to efficiently tackle the short-term weather forecasting. Renewable energy sources constitute solutions for the achievement of sustainability development goals and could also offer power autonomy in a weather forecasting station. In the present research study, everWeather is proposed as a low-cost, self-powered weather forecasting station based on the AIoT paradigm and renewable energy. The proposed solution combines a variety of low-cost environmental sensors, the prowess of solar energy and an appropriate lightweight Machine Learning (ML) algorithm such as the Multiple Linear Regression (MLR) in order to forecast physical weather for the next half hour. Preliminary experiments have been conducted for the proposed solution validation and the corresponding results highlighted that the performance of the everWeather station is quite satisfactory, in terms of reliability and forecasting accuracy.