Find in Library

By utilizing radio-frequency sensed data, this study explores the field of precision agriculture and acknowledges the critical role it plays in improving agricultural operations. Specifically, a moisture estimation framework is proposed that employ different machine learning models and feature selection algorithms to estimate the moisture content in grapes. The results show a 12.12% reduction in RMSE, a 12% reduction in MAE, and a 2.22% increase in <inline-formula> <tex-math notation="LaTeX">$R^{2}$ </tex-math></inline-formula> values compared to a state-of-the-art model utilizing conventional regression-based techniques. These results highlight the superiority of the moisture estimation framework against their regression-based counterparts. Essentially, this work highlights the potential for revolutionizing agriculture through enhanced accuracy and sustainability of agricultural operations by using state-of-the-art machine learning algorithms together with radio-frequency sensed data.