Transforming Crop Drying Operations Through IoT and Data-Driven Solutions

Digital agriculture plays a crucial role in enhancing crop management and reducing reliance on manual labor by monitoring crops in real-time and controlling them automati-cally. However, while digital agriculture has made substantial progress, the advancement of labor-intensive agricultural ma-chinery, particularly in the crop dryer machine, has not kept pace, underscoring the imperative for innovation in this domain. This paper proposes a digital crop dryer equipped with IoT sensors and a sophisticated management system, designed to automate and optimize the drying process. This dryer not only monitors real-time data, including temperature, humidity, and crop weights, but also uses a camera to directly observe crop conditions. Furthermore, we have developed a deep learning-based predictive model that uses data analysis to forecast the moisture content of drying crops and determine optimal endpoint of the drying process, achieving a prediction performance with an <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$R^{2}$</tex> score of approximately 0.985.