Computing method of reference crop evapotranspiration based on PCA and L-M algorithms

• Main Authors: LIU CHENGSHUAI, CHEN YOUQIAN, HAN ZHENYUE, WU QIANG, LIU SHANSHAN, JIAN SHENGQI, HU CAIHONG, YANG FAN, ZHANG XUELI, NIU CHAOJIE, LUO QINGYUAN
• Format: Patent
• Language: Chinese; English
• Published: 11.05.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention provides a PCA and L-M algorithm-based reference crop evapotranspiration calculation method, which is used for solving the technical problems of more calculation input items and complicated calculation of the existing reference crop evapotranspiration. The method comprises the following steps: firstly, acquiring historical meteorological data of a research area, and screening out typical years through hydrological frequency analysis; secondly, comprehensive indexes of historical meteorological data of typical years are extracted through a PCA statistical method; then, training the comprehensive indexes by using an L-M algorithm to obtain a basic network; and finally, calculating the reference crop evapotranspiration of the to-be-solved time period by using the basic network, and judging the simulation precision of the basic network. According to the method, feature extraction and dimensionality reduction are carried out on the multivariate meteorological data through a PCA statistical method, th