Evolutionary neural networks for monthly pan evaporation modeling
Evolutionary neural networks for monthly pan evaporation modeling
复制标题
DOI：
10.1016/j.jhydrol.2013.06.011
复制
发表时间：
2013-08-19
影响因子：
6.4
通讯作者：
Kisi, Ozgur
中科院分区：
文献类型：
--
作者：
Kisi, Ozgur
估算蒸发量对水资源的监测、调查和管理具有重要意义。提出了应用进化神经网络(ENN)对月蒸发量进行建模的方法。研究中使用了土耳其地中海地区安塔利亚和梅尔辛两个观测站的太阳辐射、气温、相对湿度、风速和蒸发皿蒸发数据。在研究的第一部分，将ENN模型分别与模糊遗传(FG)、神经模糊(ANFIS)、人工神经网络(ANN)和斯蒂芬斯-斯图尔特(SS)方法估计安塔利亚站和梅尔辛站的蒸发量进行了比较。比较结果表明，ENN模型总体上优于FG、ANFIS、ANN和SS模型。在研究的第二部分中，使用两个站的输入数据对估算Mersin‘s PAN蒸发量的模型进行了比较。结果表明，ENN模型的预测效果优于FG、ANFIS和ANN模型。结果表明，ENN方法可以较好地估算月蒸发量。以全天候资料为输入的新奥模式对安塔利亚站和梅尔辛站的平均绝对误差分别为0.749 mm和0.759 mm。(C)2013爱思唯尔B.V.保留所有权利。
Estimating pan evaporation is very important for monitoring, survey and management of water resources. This study proposes the application evolutionary neural networks (ENN) for modeling monthly pan evaporations. Solar radiation, air temperature, relative humidity, wind speed and pan evaporation data from two stations, Antalya and Mersin, in Mediterranean Region of Turkey are used in the study. In the first part of the study, ENN models are compared with those of the fuzzy genetic (FG), neuro-fuzzy (ANFIS), artificial neural networks (ANN) and Stephens-Stewart (SS) methods in estimating pan evaporations of Antalya and Mersin stations, separately. Comparison results indicate that the ENN models generally perform better than the FG, ANFIS, ANN and SS models. In the second part of the study, models are compared with each other in estimating Mersin's pan evaporations using input data of both stations. Results reveal that the ENN models performed better than the FG, ANFIS and ANN models. It was concluded that monthly pan evaporations can be successfully estimated by the ENN method. The performance of the ENN model with full weather data as inputs presents 0.749 and 0.759 mm of mean absolute error for the Antalya and Mersin stations, respectively. (C) 2013 Elsevier B.V. All rights reserved.