This project aims to develop a cost-effective weather forecasting system using the Arduino Nano 33 BLE Sense. By utilizing Tiny Machine Learning (TinyML), our model can run efficiently on constrained hardware, enabling real-time weather predictions without internet connectivity. This system can be particularly relevant for users in resource-limited areas (including outdoor enthusiasts, remote weather stations and educational institutions), where access to continuous network connectivity or high-powered hardware is often unavailable or expensive.
Our approach aims to deliver reliable weather predictions by capturing key environmental metrics like temperature and barometric pressure. This will ensure that the system remains practical for low-resource applications, providing accurate and timely forecasts even in areas with minimal infrastructure. Our goal is to contribute to broader accessibility in cost-efficient weather forecasting, and our code is available here to encourage future reproducibility.
