Wang, W.H., 2020. Prediction method of unsaturated soil water content under different irrigation intensities. In: Guido Aldana, P.A. and Kantamaneni, K. (eds.), Advances in Water Resources, Coastal Management, and Marine Science Technology. Journal of Coastal Research, Special Issue No. 104, pp. 832–837. Coconut Creek (Florida), ISSN 0749-0208.

In order to improve the efficiency of agricultural irrigation, ensure the normal growth of crops, realize water-saving and energy-saving automatic irrigation and soil moisture content monitoring, a prediction method of unsaturated soil water content under different irrigation intensity was proposed. Firstly, soil samples were collected and soil moisture sensor was used to measure soil moisture content every 12 h. when it was lower than the set threshold value, the solenoid valve was automatically opened for irrigation, and when it was higher than the set value, irrigation was stopped. The near infrared spectrum data of soil samples were collected, and then the prediction model was constructed by using variable weight stacking automatic encoder combined with support vector regression to realize the prediction of unsaturated soil moisture content. The experimental results show that the designed prediction method can accurately predict the unsaturated soil water content, and provide a certain reference for intelligent irrigation.