Convolutional neural network model for soil moisture prediction and its transferability analysis based on laboratory Vis-NIR spectral data

Laboratory visible near infrared reflectance (Vis-NIR, 400-2500 nm) spectroscopy has the advantages of simplicity, fast and non-destructive which was used for SM prediction. However, many previously proposed models are difficult to transfer to unknown target areas without recalibration. In this study, we first developed a suitable Convolutional Neutral Network (CNN) model and transferred the model to other target areas for two situations using different soil sample backgrounds under 1) the same measurement conditions (DSSM), and 2) under different measurement conditions (DSDM). We also developed the CNN models for the target areas based on their own datasets and traditional PLS models was developed to compare their performances. The results show that one dimensional model (1D-CNN) performed strongly for SM prediction with average R-2 up to 0.989 and RPIQ up to 19.59 in the laboratory environment (DSSM). Applying the knowledge-based transfer learning method to an unknown target area improved the R-2 from 0.845 to 0.983 under the DSSM and from 0.298 to 0.620 under the DSDM, which performed better than data-based spiking calibration method for traditional PLS models. The results show that knowledge-based transfer learning was suitable for SM prediction under different soil background and measurement conditions and can be a promising approach for remotely estimating SM with the increasing amount of soil dataset in the future.