A low footprint olive grove weather forecasting using a single-layered seasonal attention encoder-decoder model

Weather forecasting is essential in various applications such as olive smart farming. Farmers use the predicted weather data to take appropriate actions with the aim of increasing the crop production. Many deep learning models have been developed for tackling such a problem. However, olive groves are located in remote areas with no Internet connectivity, therefore these models are not applicable as they require either powerful processors or communication with cloud servers for inference. In this work, we propose a deep learning encoder-decoder model that uses a seasonal attention mechanism for time series forecasting of weather variables. The proposed model is non-complex, yet more powerful, compared to the more complex models in the literature. We use this model as the core of a framework that preprocess the training and testing data, train the model, and deploy the model on a resource-constrained microcontroller. Using real-life weather datasets of Spanish, Greek, and Chinese weather stations, we prove that the proposed model achieves a higher prediction accuracy compared to the existing literature. More specifically, the achieved prediction mean absolute error (MAE) is 2.13 °C and root mean squared error (RMSE) is 2.64 °C. This outstanding accuracy performance is achieved with the model requiring only 37.6 kB of memory for storing the model parameters with a total memory requirement of 50.1 kB. Since the model is relatively non-complex, we implement it on the Raspberry Pi Pico platform which has a very low cost with minimal power consumption compared to other embedded platforms. We also build a prototype and test it to verify the model's ability to achieve the target objective in real-life scenarios.