论文部分内容阅读
ET0是计算作物需水量、进行农田灌溉管理及区域水资源优化配置的重要依据。以新疆焉耆盆地绿洲区为例,将ANFIS应用于逐日ET0预测中。根据研究区各气象要素的相关分析结果,选择系统输入变量为日最高气温和日均风速;利用不同水文年共1462组数据对系统进行训练,建立ET0预测模型。利用该模型对研究区2011年的365组数据进行预测效果检验,并与PM模型计算值为标准进行对比,结果表明:ANFIS系统预测平均相对误差绝对值为6.5%;通过t检验,预测值和标准值相差不大,在0.01的置信度下,无显著差异;回归分析表明,预测值和标准值相关系数为0.9911,且数据均匀分布在直线y=x附近,模型具有较高的精度和稳定性。研究结果为干旱区灌区农田灌溉管理及水资源配置提供了一定参考。
ET0 is an important basis for calculating crop water demand, farmland irrigation management and regional water resources optimal allocation. Taking the oasis area of Yanqi Basin in Xinjiang as an example, ANFIS is applied to daily ET0 prediction. According to the correlation analysis results of each meteorological element in the study area, the input variables of the system are selected as the daily maximum temperature and the average daily wind speed. The ET0 prediction model is established by using 1462 sets of data in different hydrological years to train the system. The model is used to test the prediction results of 365 sets of data in 2011 in the study area and compared with the calculated values of PM model. The results show that: the absolute relative error of ANFIS prediction is 6.5%; by t test, There was no significant difference between the standard values and the confidence level of 0.01. Regression analysis showed that the correlation coefficient between the predicted value and the standard value was 0.9911, and the data was uniformly distributed around the straight line y = x. The model has high accuracy and stability Sex. The results provide some reference for farmland irrigation management and water resources allocation in arid area.