Irrigation method based on dynamic multilayer extreme learning machine

Abstract

The invention relates to an irrigation method based on a dynamic multilayer extreme learning machine. The irrigation method comprises first collecting a plurality of training data, which comprises soil environment data, meteorological data and crop coefficients of irrigated crops; then performing normalization processing on each group of the training data to form a training set; training the multilayer extreme learning machine by using the training set to obtain a final model; and finally collecting test data, performing normalization processing on the test data, inputting the processed test data into the final model so as to obtain a predicted water amount required by irrigation, and performing irrigation according to the predicted water amount required by irrigation. In the irrigation method provided by the invention, a strategy of ''seeking common points while reserving difference'' is adopted according to calculation accuracy. If the calculation result of the re-input data by using a model meets the accuracy requirement, the model is output, otherwise incremental learning training is performed on the basis of the existing model to obtain a dynamically adjusted model. The irrigation method provided by the invention increases the calculation accuracy of water volumes required by irrigation, reduces the time consumption and calculation cost of prediction of the water volumes required by irrigation, and reaches the goals of reasonable use of water resources and reasonable irrigation of crops.

Description

technical field [0001] The invention belongs to the field of intelligent irrigation of the agricultural internet of things, and relates to an irrigation method based on a dynamic multi-layer extreme learning machine. Background technique [0002] The Agricultural Internet of Things is a highly integrated and comprehensive application of a new generation of information technology in the agricultural field. It plays an important leading role in the development of agricultural informatization in my country, changes the traditional agricultural production mode, and promotes the transformation of agriculture to the direction of intelligence and refinement. A large number of sensor nodes are used to collect real-time information on the crop production environment, and a monitoring system is formed through network technology to help farmers find problems in time and accurately determine the location of the problem. Turn the production mode that originally relied on isolated machine...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to overcome the problems of small data processing scale, slow data processing speed and few types of training data in the prior art, and provide a kind of training system with fast data processing, large data processing scale, and relatively low data parameter types. An irrigation method that can accurately calculate the water demand of crops in a short time

Images