【摘要】 土壤墒情预报是农田适时适量灌水的基础 .田间土壤水分的变化受到外界气象因素及土壤特性、作物长势等的影响 ,关系比较复杂 .本文利用北京市永乐店试验站冬小麦返青后的土壤水分试验资料 ,建立了土壤墒情预报的BP网络模型 ,模型中同时考虑了多个因素对土壤贮水量的影响 .利用部分实测资料对网络进行训练 ,然后对 2年不同灌水处理下的土壤贮水量进行预测 ,取得了较好的效果 ,表明BP神经网络用于墒情预报是可行的 .更多还原

【Abstract】 Based on the field soil moisture observation data for winter wheat in Yongledian Experimental Station,Beijing,during growing period,a back-propagation(BP) network model for soil moisture forecast is established.The model takes main factors influencing soil moisture regime into account.The network is trained by part of observation data before the application to forecast of soil moisture with different irrigation treatment in two years.The predicted soil moisture fairly well agrees with the observation data.更多还原