@ARTICLE {CWE / 1062/2018,作者= {},Journal = {当前世界环境},Publisher = {},标题= {估算希腊山区的空气温度统计模型},年= {},月份= {},卷= {39},URL = {www.a-i-l-s-a.com/article/1061/},页面= {547-552},抽象= {当前工作侧重于估计空气温度(t)条件在两个高海拔(ALT)网站(1580米),每一个在山(MT)AENOS在Cephalonia,希腊岛上的不同方向(MT)Aenos,通过使用两个众所周知的统计模型,简单的线性回归(SLR)和多层Perceptron(MLP),最常用的人工神经网络之一。更具体地说,高替代地点中的平均值,最大和最小T的估计是基于两个下替代网站(1100米)的各自的T数据,东南第一和西北方向的第二个数据,并单独进行每个方向。通过测定系数(R2)和平均绝对误差(MAE)来评估SLR和MLP模型的性能。结果表明,关于东南方向的平均值,最大和最小T的估计,所检查的模型(SLR和MLP)提供了非常令人满意的结果(R2为0.96至0.98),平均t估计相对更好,如确认由最低的MAE(0.83)。对于西北方向,与东南方向的各自估计相比,T估计不太准确(降低R2和更高的MAE),但是,结果被认为是足够的(R2和MAE分别为0.92和1.00至1.40。 In general, the estimations of the mean T were better than those of the extreme ones (minimum and maximum T). In addition, better results (higher R2 and lower, in general, MAE) were obtained when T estimations were based on T data derived from sites located at areas with similar surroundings, as in the case of dense and tall vegetation of the sites at southeast orientation, irrespective of applied method.}, number = {52}, doi = {10.12944/CWE.12.3.07} }