Abstract: A farmland reference crop evapotranspiration prediction method based on uncertainty of meteorological factors, includes: S1. acquiring a set number of groups of weather forecast data of a prediction region within a preset time period; S2. inputting each group of weather forecast data into a Bayesian probability forecast system to obtain corrected weather forecast data; and S3. inputting each group of the corrected weather forecast data into a trained RBF neural network, and predicting to obtain a farmland reference crop evapotranspiration. In the present invention, the Bayesian probability forecast system is configured to correct the weather forecast data and eliminate uncertainty of weather forecast data to obtain the accurate reference crop evapotranspiration forecasted by the RBF neural network using these data.

Abstract: Through exploration of the characteristics of a crop canopy structure and the variation laws in the crop development processes, a three-dimensional crop canopy structure model and a dynamic maize growth simulation are established by fusing the three-dimensional crop canopy structure model. The model describes the crop growth and development stages by adopting growing degree-days, carries out dynamic simulation on a two-dimensional maize canopy structure by adopting a Logistic equation, and characterizes veins, leaf margin and the like by adopting a spatial topological structure. On this basis, a dynamic simulation method for a three-dimensional spatial crop canopy structure is finally established, the coupling simulation of multiple hydrothermal carbonization processes in a complex farmland ecosystem is realized, and thus the simulation capability and universality of the crop model are effectively improved.

Abstract: A farmland reference crop evapotranspiration prediction method based on uncertainty of meteorological factors, includes: S1. acquiring a set number of groups of weather forecast data of a prediction region within a preset time period; S2. inputting each group of weather forecast data into a Bayesian probability forecast system to obtain corrected weather forecast data; and S3. inputting each group of the corrected weather forecast data into a trained RBF neural network, and predicting to obtain a farmland reference crop evapotranspiration. In the present invention, the Bayesian probability forecast system is configured to correct the weather forecast data and eliminate uncertainty of weather forecast data to obtain the accurate reference crop evapotranspiration forecasted by the RBF neural network using these data.