Soil moisture is one of the main factors in agricultural production and hydrological cycles, and its precise prediction is important for the rational use and management of water resources. However, soil moisture involves complex structural characteristics and meteorological factors, and it is difficult to establish an ideal mathematical model for soil moisture prediction. Existing prediction models have problems such as prediction accuracy, generalization, and multi-feature processing capability, and prediction performance must improve. Based on this, taking the Beijing area as the research object, the deep learning regression network (DNNR) with big data fitting capability was proposed to construct a soil moisture prediction model. By integrating the dataset, analyzing the time series of the predictive variables, and clarifying the relationship between features and predictive variables through the Taylor diagram, selected meteorological parameters can provide effective weights for moisture prediction. Test results prove that the deep learning model is feasible and effective for soil moisture prediction. Its’ good data fitting and generalization capability can enrich the input characteristics while ensuring high accuracy in predicting the trends and values of soil moisture data and provides an effective theoretical basis for water-saving irrigation and drought control.
Abstract. The weighing lysimeters provide scientist the basic information for research related to the evapotranspiration, high quality of the collected data from lysimeters is of great significance. However there are many factors that can affect the measurement accuracy of the weighing lysimeter. In this paper, a data acquisition system was developed to collect the data from 24 weighing lysimeters. The calibration process of the load cell was described. An outlier detection method based on the 3-sigma rule and the median filter was proposed to improve the measurement accuracy of the weighing lysimeters. The performance of the proposed method was compared with the method based on Savitzky-Golay filter. Results show that the standard deviations of the 15-point median filter and the 15-point Savitzky-Golay filter applied to the 283 data points were 0.413Kg and 0.422Kg respectively, which means that the performance of the median filter was better than the Savitzky-Golay filter. Moreover the outliers were successfully eliminated using the median filter and were not removed by the Savitzky-Golay filter.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.