A Variable Frequency Agricultural Sensing Method Based on Deep Prediction

To address the challenges of low data validity and limited energy efficiency in agricultural IoT, we propose a deep predictive agricultural variable-frequency sensing method. First, we construct a hybrid prediction model, denoted as SVMD-TCN-R-GRU-T (STRGT). This model integrates successive variational mode decomposition (SVMD) with an optimized TCN-GRU architecture, thereby improving prediction accuracy. Building on this framework, we design a frequency conversion sampling method under dual detection analysis (FCSDDA). This approach employs wavelet transform to determine the minimum sampling rate and incorporates dynamic time warping evaluate data variation. The dual detection mechanism enables real-time adjustment of sensor acquisition frequency. Experimental results demonstrate that the proposed model significantly outperforms conventional models in terms of RMSE, MAE, and MAPE. When the STRGT outputs are applied as inputs to the FCSDDA algorithm, the system achieved optimal improvements in energy efficiency improvement rate (84.61%) and data value density (0.3368), exceeding the performance of other prediction model variants. These findings confirm that prediction accuracy directly influences adaptive sensing performance. This indicates that the method can effectively achieve dual optimization of energy saving and data validity in testing scenarios. In the future, more agricultural sensing scenarios can be validated.