With the continuous development of Earth science, soil temperature has received more and more attention in Earth system research as an important parameter. The change of soil temperature (T_s) in different regions and related time series is affected by many factors, which bring certain difficulties to the accuracy of soil temperature prediction and the robustness of the algorithm. In this paper, an embedded network prediction model based on the gated recurrent unit (GRU) model is proposed to learn the local and global features of historical temperature for improving the prediction performance of soil temperature. We input different steps into the GRU model, and the output is weighted to obtain the final prediction result. In order to obtain the global characteristics of soil temperature, we connect the previous steps to the output layer directly, and the local characteristics of soil temperature are obtained through the following steps. This paper uses the soil temperature data from two meteorological stations (Laegern and Fluehli) in Switzerland as the input data to predict the soil temperature for different soil depths (5 cm, 10 cm, and 15 cm) at different time points (6 hrs, 12 hrs, and 24 hrs), using RMSE, MAE, MSE, and performance indicators as evaluation criteria to verify the accuracy of prediction. As the experimental results show, our method has the best performance compared to the others (artificial neural networks (ANN), extreme learning machine model (ELM), long short-term memory network (LSTM), gated recurrent unit network (GRU)). In particular, we estimated the soil temperature at the soil depth of 10 cm of the Fluehli station in the coming 6 hrs; our method achieved the best performance; and, meanwhile, our model achieved the maximum value of (0.9914) and the minimum values of RMSE (0.4668), MAE (0.2585), and MSE (0.2214) compared with the other four models. Therefore, our model can not only predict the soil temperature at different depths but also improve the accuracy.

中文翻译：

---

一种新的土壤温度预测的嵌入式估计模型

随着地球科学的不断发展，土壤温度作为一个重要参数在地球系统研究中越来越受到重视。土壤温度的变化 ( T _s) 的不同区域及相关时间序列受多种因素影响，给土壤温度预测的准确性和算法的鲁棒性带来一定的困难。本文提出了一种基于门控循环单元（GRU）模型的嵌入式网络预测模型来学习历史温度的局部和全局特征，以提高土壤温度的预测性能。我们将不同的步骤输入到 GRU 模型中，并对输出进行加权以获得最终的预测结果。为了获得土壤温度的全局特征，我们将前面的步骤直接连接到输出层，通过以下步骤获得土壤温度的局部特征。性能指标作为评价标准来验证预测的准确性。实验结果表明，与其他方法（人工神经网络（ANN）、极限学习机模型（ELM）、长短期记忆网络（LSTM）、门控循环单元网络（GRU））相比，我们的方法具有最佳性能. 特别是我们估算了Fluehli站10 cm土层未来6小时的土壤温度；我们的方法取得了最好的性能；同时，与其他四个模型相比，我们的模型实现了最大值(0.9914) 和最小值 RMSE (0.4668)、MAE (0.2585) 和 MSE (0.2214)。因此，我们的模型不仅可以预测不同深度的土壤温度，还可以提高精度。