Farmland reference crop evapotranspiration prediction method based on improved BP neural network

Abstract

The invention discloses a farmland reference crop evapotranspiration prediction method based on an improved BP neural network. The method comprises the steps of obtaining the meteorological data of afarmland reference crop growth environment according to weather forecast information, and calculating the farmland reference crop evapotranspiration through a PM method; constructing a training set and a test set, and performing preprocessing; adopting an LM algorithm to construct a BP neural network model considering rainfall factors, and carrying out training optimization; and utilizing the optimized BP neural network model to predict the evapotranspiration of the farmland reference crops according to the meteorological data of the test set. According to the invention, the LM algorithm is used to construct the BP neural network model considering rainfall factors; the farmland reference crop evapotranspiration is used as the measured value to train and optimize the model, the convergencedegree and calculation speed of the model are improved, the nonlinear relation between the farmland reference crop evapotranspiration and the driving factors of the farmland reference crop evapotranspiration is effectively constructed, and therefore the prediction precision and prediction effect of the farmland reference crop evapotranspiration are remarkably improved.

Description

technical field [0001] The invention belongs to the technical field of reference crop transpiration prediction, and in particular relates to a farmland reference crop evapotranspiration prediction method based on an improved BP neural network. Background technique [0002] Reference crop transpiration is the process by which soil and crops express water that diffuses into the atmosphere through transpiration and transpiration, and is a key factor in water balance and irrigation scheduling. Its calculation and prediction methods have not only become an important field of research on the water cycle and water balance of farmland ecosystems, but also play an important role in specifying farmland irrigation systems and allocating water and soil resources. Therefore, in order to better manage crop irrigation water consumption and improve crop water use efficiency, it is urgent to accurately predict reference crop transpiration. [0003] Reference crop transpiration can be direct...

AI Technical Summary

Problems solved by technology

[0005] The PM model recommended by FAO-56 is the standard model for the prediction of reference crop transpiration. However, due to the lack of necessary meteorological data, its application is limited. In addition, there is a complex nonlinear relationship between reference crop transpiration and its driving factors. Traditional statistical methods cannot get satisfactory results

Images