Short-Term Temperature Prediction of Farmland Microclimate Based on a GABP-Net Model

In response to the challenge of insufficient accuracy in short-term air temperature prediction under severe changes in agricultural microclimate, a hybrid prediction model based on GABP-Net (Gated-Attention and BP Parallel Network) neural network and attention mechanism is proposed. The proposed GABP-Net provides a comprehensive feature fusion framework through two parallel branches: the Gated-Attention branch, built on a GRU followed by multi-head attention, captures local temporal dependencies, with the multi-head attention component adaptively reweighting the GRU outputs across multiple heads to capture diverse temporal patterns; meanwhile, the BP branch, a Backpropagation neural network operating on the flattened input, extracts global contextual features. Their parallel combination enables the model to simultaneously leverage both local dynamics and global representations. Taking 28.2 hectares of farmland in Pingdu, Qingdao as the research object, based on observation data collected every 2 h from September to October 2025, combined with meteorological station measurements and background meteorological prediction data, key meteorological factors such as temperature, radiation, and pressure were selected as input features. The results showed that in the 6-h, 12 h, and 24-h prediction tasks, the model’s R2 reached 0.9654, 0.9759, and 0.9622, respectively. The MAE was 0.95 °C, 0.84 °C, and 1.04 °C, respectively, and the RMSE was ≤1.32 °C, significantly better than the single BP (Backpropagation) and GRU (Gated Recurrent Unit) models. Research has shown that this hybrid model effectively improves prediction stability under realistic field conditions with naturally imperfect sensor data and wide temperature variations (overall range 39 °C, maximum diurnal difference 21.6 °C), providing reliable technical support for microclimate regulation in precision agriculture.