Establishing a Prediction Model for Tea Leaf Moisture Content Using the Free-Space Method’s Measured Scattering Coefficient

The rapid and nondestructive detection of tea leaf moisture content (MC) is great significance to processing with an automatic assembly line. This study proposes MC method based on microwave scattering parameters (SPs). Through the established free-space electromagnetic measurement device, 901 different frequency points are taken between 2.45 6 GHz using a vector network analyzer (VNA). SPs leaves contents (5.72–55.26%) at bulk density sample thicknesses were measured. relationship frequency, S21 amplitude content, thickness, was analyzed correlation coefficients, analysis, model construction. Back propagation (BP) neural network, decision tree (DT), random forest (RF) prediction models amplitude, phase SPs, samples as inputs. results showed that RF-based had best performance, determination coefficient (R2) = 0.998, mean absolute error (MAE) 0.242, root square (RMSE) 0.614. Compared other testing processes for tea, this simpler more accurate. provides new MC, which may have potential applications in processing.