The existence of soil macropores is a common phenomenon.Due to the existence of soil macropores,the amount of solute loss carried by water is deeply modified,which affects watershed hydrologic response.In this study,a...The existence of soil macropores is a common phenomenon.Due to the existence of soil macropores,the amount of solute loss carried by water is deeply modified,which affects watershed hydrologic response.In this study,a new improved BP(Back Propagation)neural network method,using Levenberg–Marquand training algorithm,was used to analyze the solute loss on slopes taking into account the soil macropores.The rainfall intensity,duration,the slope,the characteristic scale of macropores and the adsorption coefficient of ions,are used as the variables of network input layer.The network middle layer is used as hidden layer,the number of hidden nodes is five,and a tangent transfer function is used as its neurons transfer function.The cumulative solute loss on the slope is used as the variable of network output layer.A linear transfer function is used as its neurons transfer function.Artificial rainfall simulation experiments are conducted in indoor experimental tanks in order to verify this model.The error analysis and the performance comparison between the proposed method and traditional gradient descent method are done.The results show that the convergence rate and the prediction accuracy of the proposed method are obviously higher than that of traditional gradient descent method.In addition,using the experimental data,the influence of soil macropores on slope solute loss has been further confirmed before the simulation.展开更多
In regards to soil macropores,the solute loss carried by overland flow is a very complex process.In this study,a fuzzy neural network(FNN)model was used to analyze the solute loss on slopes,taking into account the soi...In regards to soil macropores,the solute loss carried by overland flow is a very complex process.In this study,a fuzzy neural network(FNN)model was used to analyze the solute loss on slopes,taking into account the soil macropores.An artificial rainfall simulation experiment was conducted in indoor experimental tanks,and the verification of the model was based on the results.The characteristic scale of the macropores,the rainfall intensity and duration,the slope and the adsorption coefficient of ions,were chosen as the input variables to the Sugeno FNN model.The cumulative solute loss quantity on the slope was adopted as the output variable of the Sugeno FNN model.There were three membership functions,and the type of membership function was gbellmf(generalized bell membership function).The hybrid learning algorithm,which combines the back propagation algorithm with a least square method,was applied to train and optimize the network parameters,and the optimal network parameters were determined.The simulation results showed that the simulated values were consistent with the measured values.展开更多
基金This research was financially supported by the National Natural Science Foundation of China(No.41301037)the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(No.11KJB170008)Innovation and Entrepreneurship Training Program for College Students in Jiangsu Province(No.201910300106Y).For the help in carrying out the experiments,I wish to thank for Professor Rui Xiaofang,Hohai University,China.
文摘The existence of soil macropores is a common phenomenon.Due to the existence of soil macropores,the amount of solute loss carried by water is deeply modified,which affects watershed hydrologic response.In this study,a new improved BP(Back Propagation)neural network method,using Levenberg–Marquand training algorithm,was used to analyze the solute loss on slopes taking into account the soil macropores.The rainfall intensity,duration,the slope,the characteristic scale of macropores and the adsorption coefficient of ions,are used as the variables of network input layer.The network middle layer is used as hidden layer,the number of hidden nodes is five,and a tangent transfer function is used as its neurons transfer function.The cumulative solute loss on the slope is used as the variable of network output layer.A linear transfer function is used as its neurons transfer function.Artificial rainfall simulation experiments are conducted in indoor experimental tanks in order to verify this model.The error analysis and the performance comparison between the proposed method and traditional gradient descent method are done.The results show that the convergence rate and the prediction accuracy of the proposed method are obviously higher than that of traditional gradient descent method.In addition,using the experimental data,the influence of soil macropores on slope solute loss has been further confirmed before the simulation.
基金supported by the National Natural Science Foundation of China(No.41301037)the Natural Science Foundation of Jiangsu Province(BK20201136,BK20191401)+1 种基金the Natural Science Foundation of the Jiangsu Higher Education Institutions of China(No.11KJB170008)Innovation and Entrepreneurship Training Program for College Students in Jiangsu Province(No.201910300106Y).
文摘In regards to soil macropores,the solute loss carried by overland flow is a very complex process.In this study,a fuzzy neural network(FNN)model was used to analyze the solute loss on slopes,taking into account the soil macropores.An artificial rainfall simulation experiment was conducted in indoor experimental tanks,and the verification of the model was based on the results.The characteristic scale of the macropores,the rainfall intensity and duration,the slope and the adsorption coefficient of ions,were chosen as the input variables to the Sugeno FNN model.The cumulative solute loss quantity on the slope was adopted as the output variable of the Sugeno FNN model.There were three membership functions,and the type of membership function was gbellmf(generalized bell membership function).The hybrid learning algorithm,which combines the back propagation algorithm with a least square method,was applied to train and optimize the network parameters,and the optimal network parameters were determined.The simulation results showed that the simulated values were consistent with the measured values.
