Soil temperature and moisture have a close relationship, the accurate controlling of which is important for crop growth. Mechanistic models built by previous studies need exhaustive parameters and seldom consider time stochasticity and lagging effect. To circumvent these problems, this study designed a data-driven stochastic model analyzing soil moisture-heat coupling. Firstly, three vector autoregression models are built using hourly data on soil moisture and temperature at the depth of 10, 30, and 90 cm. Secondly, from impulse response functions, the time lag and intensity of two variables’ response to one unit of positive shock can be obtained, which describe the time length and strength at which temperature and moisture affect each other, indicating the degree of coupling. Thirdly, Granger causality tests unfold whether one variable’s past value helps predict the other’s future value. Analyzing data obtained from Shangqiu Experiment Station in Central China, we obtained three conclusions. Firstly, moisture’s response time lag is 25, 50, and 120 h, while temperature’s response time lag is 50, 120, and 120 h at 10, 30, and 90 cm. Secondly, temperature’s response intensity is 0.2004, 0.0163, and 0.0035 °C for 1% variation in moisture, and moisture’s response intensity is 0.0638%, 0.0163%, and 0.0050% for 1 °C variation in temperature at 10, 30, and 90 cm. Thirdly, the past value of soil moisture helps predict soil temperature at 10, 30, and 90 cm. Besides, the past value of soil temperature helps predict soil moisture at 10 and 30 cm, but not at 90 cm. We verified this model by using data from a different year and linking it to soil plant atmospheric continuum model.
Data-Driven Machine-Learning Model in District Heating System for Heat Load Prediction: A Comparison Study