Sequence-to-Sequence Learning for Prediction of Soil Temperature and Moisture

Abstract

Soil temperature and moisture play a significant influence on vegetation and climate. Measurements of soil temperature and moisture can now be obtained through soil temperature and moisture sensors, but the measurements can only be done for a specified period of time in the past. Predicting soil temperature and moisture for the future is of significant importance because it can provide guidance on making plant plans. With deep learning algorithms, the characteristics of soil temperature and moisture in a certain upcoming period can be predicted from data measured in the past. In this letter, we develop a sequence-to-sequence learning model for multistep ahead prediction, which features a long short-term memory (LSTM)-based encoder–decoder structure for modeling long-term temporal correlations as well as an autoencoder for modeling spatial correlations (i.e., considering data from neighboring locations). For performance evaluation, we use real data collected by the temperature and moisture sensors on soils at the Heihe River Basin in the west of China. Our experimental results show that: 1) the proposed model significantly outperforms two widely used time series analysis algorithms, autoregressive integrated moving average (ARIMA) and support vector regression (SVR), and 2) the proposed spatial encoder–decoder LSTM modeling method is indeed effective in that the root-mean-squared error (RMSE) and mean absolute error (MAE) are only 0.22 °C and 0.17 °C for 24-h (144 steps ahead) prediction of soil temperature and the values are only 0.28% and 0.23% for soil moisture.