Based on potted plant experiment, BP-artifieial neural network was used to simulate crop evapotranspiration and 3 kinds of artificial neural network models were constructed as ET1 （meteorological factors）, ET2（ met...Based on potted plant experiment, BP-artifieial neural network was used to simulate crop evapotranspiration and 3 kinds of artificial neural network models were constructed as ET1 （meteorological factors）, ET2（ meteorological factors and sowing days） and ET3 （meteorological factors, sowing days and water content）. And the predicted result was compared with actual value ET that was obtained by weighing method. The results showed that the ET3 model had higher calculation precision and an optimum BP-artificial neural network model for calculating crop evapotranspiration.展开更多
Predicting evaporation rate is one of important elements for hydrology planning. There are several methods to estimate evaporation from a water surface. The objective of this study was to test the capability of artifi...Predicting evaporation rate is one of important elements for hydrology planning. There are several methods to estimate evaporation from a water surface. The objective of this study was to test the capability of artificial neural networks （ANNs） to predict evaporation using 10 years data set （1999 to 2008） from Ahvaz meteorological station and has been compared with values obtained using pan evaporation. Software Qnet 2000 has been utilized to model the evaporation. The Qnet 2000 was trained with monthly climate data （Solar radiation, minimum and maximum temperature, minimum and maximum relative humidity, and wind velocity） as input. The model was approximately implemented 144 times that finally hyperbolic secant stimulant function of 4 input parameters including minimum temperature, maximum temperature, solar radiation and wind velocity and 6 nodes in hidden layer has been yielded the best outcome. Correlation coefficients （R2） in training and testing sections are to 97.4% and 97.3% respectively. Also maximum errors in training and testing sections equaled to 18% and 24% respectively. Results showed ANNs approach works well for the data set used in this region.展开更多
基金Supported by the National Natural Science Foundation of China(50609022)~~
文摘Based on potted plant experiment, BP-artifieial neural network was used to simulate crop evapotranspiration and 3 kinds of artificial neural network models were constructed as ET1 （meteorological factors）, ET2（ meteorological factors and sowing days） and ET3 （meteorological factors, sowing days and water content）. And the predicted result was compared with actual value ET that was obtained by weighing method. The results showed that the ET3 model had higher calculation precision and an optimum BP-artificial neural network model for calculating crop evapotranspiration.
文摘Predicting evaporation rate is one of important elements for hydrology planning. There are several methods to estimate evaporation from a water surface. The objective of this study was to test the capability of artificial neural networks （ANNs） to predict evaporation using 10 years data set （1999 to 2008） from Ahvaz meteorological station and has been compared with values obtained using pan evaporation. Software Qnet 2000 has been utilized to model the evaporation. The Qnet 2000 was trained with monthly climate data （Solar radiation, minimum and maximum temperature, minimum and maximum relative humidity, and wind velocity） as input. The model was approximately implemented 144 times that finally hyperbolic secant stimulant function of 4 input parameters including minimum temperature, maximum temperature, solar radiation and wind velocity and 6 nodes in hidden layer has been yielded the best outcome. Correlation coefficients （R2） in training and testing sections are to 97.4% and 97.3% respectively. Also maximum errors in training and testing sections equaled to 18% and 24% respectively. Results showed ANNs approach works well for the data set used in this region.
