Integrating IoT and Wireless Sensor Networks for Precision Agriculture Using TD-CNN-LSTM

Precision agriculture has difficulties in the management of spatial and temporal data for crop monitoring and irrigation planning. This research introduces a novel TD-CNNLSTM model that incorporates IoT-enabled Wireless Sensor Networks to tackle these challenges. The model efficiently captures spatial and temporal patterns by integrating convolutional and LSTM layers. The results indicate an accuracy of 97.2%, precision of 0.96, and an $F 1$-score of 0.955, significantly surpassing baseline models such as Random Forest and LSTM-only. These measures confirm its exceptional efficacy in yield prediction and the optimisation of irrigation timing. This study presents a comprehensive, scalable system that enhances precision agriculture by increasing efficiency and sustainability compared to current methods.