Insufficient Irrigation Model Research And Forecast System Development Based On Android Platform

The shortage of water resources has long been an important factor restricting agricultural sustainable development,the research of insufficient irrigation theory has a guiding significance for agricultural water-saving irrigation in arid and semi-arid area of China,which to a certain extent can also reduce the impact of water shortages,but the actual application is still subject to many restrictions;with the development of information and communication,combining the agricultural basic theory and modem science technology provides a good view for the application of irrigation theory,agricultural informatization has become a hot topic at the present stage.In this paper,we take a research on the insufficient irrigation model,and develop an Android irrigation forecast software based on irrigation model.The main contents and results of this study are as follows:1)Introduce an insufficient irrigation forecast method base on "water balance model+dual crop coefficient method of+FAO-PM formula",the FAO-PM formula is the standard ET0(reference crop evapotranspiration)calculation method recommended by FAO-56 file,which needs complete meteorological data.According to the shortage of meteorological data in agricultural production,in this paper,the weather forecast information is used as the forecast parameter,and the BP neural network and ANFIS algorithm are used to establish the prediction model to estimate the ETO.The forecast results show that the two models can achieve high precision and high correlation,the MRE of BP-ET0 model is smaller than ANFIS-ET0 model(0.131 mm/d<0.188 mm/d)and also has higher correlation coefficient(0.979>0.948),as a conclude,the BP-ET0 model has better prediction effect.2)Developed an insufficient irrigation forecast software based on Android platform which transplanted the insufficient irrigation forecast method based on meteorological data and weather forecast data;In order to improve the function system of forecasting system,the query function of irrigation related data is integrated as well.3)In order to verify the reliability of the software,this paper predict the irrigation amount of spring maize with forecast software,the prediction results show that these two irrigation forecast method can achieve high prediction accuracy,in which the MRE of irrigation forecast method based on the meteorological data is 5.2%and the MRE of irrigation forecast method based on the weather forecast is 7.11%.On the whole,the software developed in this paper has high prediction accuracy and practicability,moreover the ETO forecast model based on weather forecast is applied to the non full irrigation forecast,and the results are good and can be used for agricultural irrigation management and technical guidance.