Predicting solutions of the Lotka-Volterra equation using hybrid deep network

作     者：Zi-Fei Lin Yan-Ming Liang Jia-Li Zhao Jiao-Rui Li Zi-Fei Lin;Yan-Ming Liang;Jia-Li Zhao;Jiao-Rui Li

作者机构：School of StatisticsXi’an University of Finance and EconomicsXi’an 710100China China(Xi’an)Institute for Silk Road ResearchXi’an 710100China 

出 版 物：《Theoretical & Applied Mechanics Letters》 (力学快报（英文版）)

年 卷 期：2022年第12卷第6期

页      面：423-431页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 07[理学] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 070102[理学-计算数学] 0811[工学-控制科学与工程] 0701[理学-数学] 0801[工学-力学（可授工学、理学学位）] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the National Natural Science Foundation of China(No.11902234) Natural Science Basic Research Program of Shaanxi(No.2020JQ-853) China(Xi’an)Silk Road Research Institute Scientific Research Project(No.2019ZD02) Shaanxi Provincial Department of Education Youth Innovation Team Scientific Research Project(No.22JP025) the Young Talents Development Support Program of Xi’an University of Finance and Economics 

主　　题：Lotka-Volterra equations HDN-LV algorithm Stochastic Lotka-Volterra equations Parameter optimization 

摘      要：Prediction of Lotka-Volterra equations has always been a complex problem due to their dynamic *** this paper,we present an algorithm for predicting the Lotka-Volterra equation and investigate the prediction for both the original system and the system driven by *** demonstrates that deep learning can be applied in dynamics of *** is the first study that uses deep learning algorithms to predict Lotka-Volterra *** numerical examples are presented to illustrate the performances of the proposed algorithm,including Predator nonlinear breeding and prey competition systems,one prey and two predator competition systems,and their respective *** the results suggest that the proposed algorithm is feasible and effective for predicting Lotka-Volterra ***,the influence of the optimizer on the algorithm is discussed in *** results indicate that the performance of the machine learning technique can be improved by constructing the neural networks appropriately.