Research of Soil Moisture Content Forecast Model Based on Genetic Algorithm BP Neural Network

摘要：

Soil moisture forecast model based on genetic neural network is es-tablished because the soil moisture forecasting is nonlinear and complex. The weights and threshold value of BP network are optimized according to the total situation optimization ability of genetic algorithm, which can avoid effectively that BP network is vulnerable to run into the local minimum value as its poor total optimization ability. The model is applied to Hongxing farm in Heilongjiang Province to predict the soil moisture. The forecasting result shows that the model has favorable forecasting precision, which indicates that the genetic neural network model is feasible and effective to predict the soil moisture.

关键词： GA-BP soil in the field moisture forecasting modeling forecast precision

作者: Caojun Huang Lin Li Souhua Ren Zhisheng Zhou

作者单位: College of Information and Technology of Heilongjiang Bayi Agricultural University,Daqing 163319, China

会议类型: 国际会议

会议名称: The 4th IFIP International on Computer and Computing Technologies in Agriculture and the 4th Symposium on Development of Rural Information(第四届国际计算机及计算机技术在农业中的应用研讨会暨第四届中国农业信息化发展论坛 CCTA 2010)

会议地点: 南昌

会议语种:英文

页码: 309-316

在线出版日期: 2010-10-22（万方平台首次上网日期，不代表论文的发表时间）